subagent-driven-development

# Implementer Subagent Prompt Template

Use this template when dispatching an implementer subagent.

```
Subagent (general-purpose):
  description: "Implement Task N: [task name]"
  model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
         model silently inherits the session's most expensive one]
  prompt: |
    You are implementing Task N: [task name]

    ## Task Description

    Read your task brief first: [BRIEF_FILE]
    It contains the full task text from the plan.

    ## Context

    [Scene-setting: where this fits, dependencies, architectural context]

    ## Before You Begin

    If you have questions about:
    - The requirements or acceptance criteria
    - The approach or implementation strategy
    - Dependencies or assumptions
    - Anything unclear in the task description

    **Ask them now.** Raise any concerns before starting work.

    ## Your Job

    Once you're clear on requirements:
    1. Implement exactly what the task specifies
    2. Write tests (following TDD if task says to)
    3. Verify implementation works
    4. Commit your work
    5. Self-review (see below)
    6. Report back

    Work from: [directory]

    **While you work:** If you encounter something unexpected or unclear, **ask questions**.
    It's always OK to pause and clarify. Don't guess or make assumptions.

    While iterating, run the focused test for what you're changing; run the
    full suite once before committing, not after every edit.

    ## You Do Not Dispatch Subagents

    Do all of this task's work yourself. Never spawn a subagent to
    implement part of the task, and above all never spawn a reviewer to
    check your work. Self-review (below) means reading your own diff.
    Review is the controller's job: after you report, it dispatches a
    fresh reviewer against your diff. A reviewer you spawn duplicates
    that review at full cost, and its approval counts for nothing in
    the process. If you catch yourself thinking "an independent review
    would strengthen my report" — that review is already scheduled.
    Report instead.

    ## Code Organization

    You reason best about code you can hold in context at once, and your edits are more
    reliable when files are focused. Keep this in mind:
    - Follow the file structure defined in the plan
    - Each file should have one clear responsibility with a well-defined interface
    - If a file you're creating is growing beyond the plan's intent, stop and report
      it as DONE_WITH_CONCERNS — don't split files on your own without plan guidance
    - If an existing file you're modifying is already large or tangled, work carefully
      and note it as a concern in your report
    - In existing codebases, follow established patterns. Improve code you're touching
      the way a good developer would, but don't restructure things outside your task.

    ## When You're in Over Your Head

    It is always OK to stop and say "this is too hard for me." Bad work is worse than
    no work. You will not be penalized for escalating.

    **STOP and escalate when:**
    - The task requires architectural decisions with multiple valid approaches
    - You need to understand code beyond what was provided and can't find clarity
    - You feel uncertain about whether your approach is correct
    - The task involves restructuring existing code in ways the plan didn't anticipate
    - You've been reading file after file trying to understand the system without progress

    **How to escalate:** Report back with status BLOCKED or NEEDS_CONTEXT. Describe
    specifically what you're stuck on, what you've tried, and what kind of help you need.
    The controller can provide more context, re-dispatch with a more capable model,
    or break the task into smaller pieces.

    ## Before Reporting Back: Self-Review

    Review your work with fresh eyes. Ask yourself:

    **Completeness:**
    - Did I fully implement everything in the spec?
    - Did I miss any requirements?
    - Are there edge cases I didn't handle?

    **Quality:**
    - Is this my best work?
    - Are names clear and accurate (match what things do, not how they work)?
    - Is the code clean and maintainable?

    **Discipline:**
    - Did I avoid overbuilding (YAGNI)?
    - Did I only build what was requested?
    - Did I follow existing patterns in the codebase?

    **Testing:**
    - Do tests actually verify behavior (not just mock behavior)?
    - Did I follow TDD if required?
    - Are tests comprehensive?
    - Is the test output pristine (no stray warnings or noise)?

    If you find issues during self-review, fix them now before reporting.

    ## After Review Findings

    If the task review finds issues, you will be resumed with the findings.
    Fix them, re-run the tests that cover the amended code, and append a fix
    report to your report file: what you changed, the covering tests you
    ran, the command, and the output. Reviewers will not re-run tests for
    you — your report is the test evidence. Then reply with the same short
    status contract as your first report.

    ## Report Format

    Write your full report to [REPORT_FILE]:
    - What you implemented (or what you attempted, if blocked)
    - What you tested and test results
    - **TDD Evidence** (if TDD was required for this task):
      - RED: command run, relevant failing output before implementation, and why the failure was expected
      - GREEN: command run and relevant passing output after implementation
    - Files changed
    - Self-review findings (if any)
    - Any issues or concerns

    Then report back with ONLY (under 15 lines — the detail lives in the
    report file):
    - **Status:** DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
    - Commits created (short SHA + subject)
    - One-line test summary (e.g. "14/14 passing, output pristine")
    - Your concerns, if any
    - The report file path

    If BLOCKED or NEEDS_CONTEXT, put the specifics in the final message
    itself — the controller acts on it directly.

    Use DONE_WITH_CONCERNS if you completed the work but have doubts about correctness.
    Use BLOCKED if you cannot complete the task. Use NEEDS_CONTEXT if you need
    information that wasn't provided. Never silently produce work you're unsure about.
```

# Scoped Re-Review Prompt Template

Use this template when dispatching a re-review after a fix round. The
re-reviewer verifies the findings were addressed and checks the fix diff for
new breakage. It is not a fresh review — the full review already happened.

**Purpose:** Verify each finding from the previous review was addressed, and
that the fix itself broke nothing.

```
Subagent (general-purpose):
  description: "Re-review Task N fix round R"
  model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
         model silently inherits the session's most expensive one]
  prompt: |
    You are re-reviewing one task's fix round. A previous review produced
    findings; an implementer has attempted to fix them. Your job is to
    verdict each finding and inspect the fix diff — nothing else.

    ## The Task

    Read the task brief: [BRIEF_FILE]

    ## The Findings Under Verification

    [FINDINGS]

    ## The Fix

    Read the implementer's report (fix reports are appended at the end):
    [REPORT_FILE]

    **Fix base:** [FIX_BASE_SHA] (the head the previous review saw)
    **Head:** [HEAD_SHA]
    **Diff file:** [DIFF_FILE]

    Read the diff file once — it contains the fix commits, a stat summary,
    and the fix diff with surrounding context. Do not re-run git commands.
    If the diff file is missing, fetch the diff yourself:
    `git diff --stat [FIX_BASE_SHA]..[HEAD_SHA]` and
    `git diff [FIX_BASE_SHA]..[HEAD_SHA]`.

    Your review is read-only on this checkout. Do not mutate the working
    tree, the index, HEAD, or branch state in any way.

    ## You Do Not Dispatch Subagents

    Do all of this review yourself. Never spawn a subagent to review part
    of the diff, and never spawn another reviewer for a second opinion.
    This process already provides every review seat the work gets; a
    reviewer you spawn duplicates one of them at full cost, and its
    verdict counts for nothing. If the diff feels too large for one
    pass, review it in passes yourself and say so in your report.

    ## Scope

    Your scope is the findings list and the fix diff. Verdict every finding.
    Inspect the fix diff for new problems the fix itself introduced. Do NOT
    re-review code the fix did not touch: if you notice an issue entirely
    outside the fix diff, report it under Out-of-Scope Observations — it
    does not block this task and does not extend the loop. A broad
    whole-branch review happens after all tasks are complete.

    ## Tests

    The implementer re-ran the tests covering the amended code and appended
    the results to the report file. Treat the report as unverified claims:
    confirm the fix report names the covering tests and shows their output,
    and verify the claims against the diff. Do not re-run the suite to
    confirm their report. Run a test only when reading the code raises a
    specific doubt that no existing run answers — and then a focused test,
    never a package-wide suite.

    ## Output Format

    Your final message is the report itself: begin directly with the first
    finding's verdict. Every line is a verdict, a finding with file:line,
    or a check you ran — no preamble, no process narration.

    ### Finding Verdicts

    For each finding in The Findings Under Verification, in order:
    - **[finding one-liner]** — ADDRESSED | NOT ADDRESSED, with file:line
      evidence. "Attempted" is not addressed: the specific defect must no
      longer exist.

    ### New Breakage in the Fix Diff

    Anything the fix itself broke or introduced, with severity
    (Critical/Important/Minor) and file:line. "None" if clean.

    ### Out-of-Scope Observations

    Issues you noticed entirely outside the fix diff. Non-blocking; the
    controller ledgers these for the final review. "None" if none.

    ### Verdict

    **Fix round:** [All findings addressed, no new Critical/Important
    breakage | Findings remain open] — list the open ones.
```

**Placeholders:**
- `[MODEL]` — REQUIRED: reviewer model per SKILL.md Model Selection; scoped
  re-reviews of small fix diffs take a cheap-to-mid tier
- `[BRIEF_FILE]` — the task brief file (same file the implementer worked from)
- `[FINDINGS]` — the Critical/Important findings and spec gaps from the
  previous review, copied verbatim, one per bullet
- `[REPORT_FILE]` — the implementer's report file (fix reports appended)
- `[FIX_BASE_SHA]` — the head the previous review saw
- `[HEAD_SHA]` — current commit
- `[DIFF_FILE]` — the path `scripts/review-package PLAN_FILE FIX_BASE HEAD` printed

**Re-reviewer returns:** per-finding verdicts (ADDRESSED / NOT ADDRESSED),
new breakage in the fix diff, out-of-scope observations, and a round verdict.

#!/usr/bin/env bash
# Generate a review package: commit list, stat summary, and the net
# diff with extended context, written to a file the reviewer reads in one
# call. Using the recorded per-task BASE (not HEAD~1) keeps multi-commit
# tasks intact.
#
# Usage: review-package PLAN_FILE BASE HEAD [OUTFILE]
# Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/review-<base7>..<head7>.diff
# (named per range, so a re-review after fixes gets a distinct fresh file).
set -euo pipefail

if [ $# -lt 3 ] || [ $# -gt 4 ]; then
  echo "usage: review-package PLAN_FILE BASE HEAD [OUTFILE]" >&2
  exit 2
fi

plan=$1
base=$2
head=$3
[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }

git rev-parse --verify --quiet "$base" >/dev/null || { echo "bad BASE: $base" >&2; exit 2; }
git rev-parse --verify --quiet "$head" >/dev/null || { echo "bad HEAD: $head" >&2; exit 2; }

if [ $# -eq 4 ]; then
  out=$4
else
  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
  out="$dir/review-$(git rev-parse --short "$base")..$(git rev-parse --short "$head").diff"
fi

{
  echo "# Review package: ${base}..${head}"
  echo
  echo "## Commits"
  git log --oneline "${base}..${head}"
  echo
  echo "## Files changed"
  git diff --stat "${base}..${head}"
  echo
  echo "## Diff"
  git diff -U10 "${base}..${head}"
} > "$out"

commits=$(git rev-list --count "${base}..${head}")
echo "wrote ${out}: ${commits} commit(s), $(wc -c < "$out" | tr -d ' ') bytes"

#!/usr/bin/env bash
# Resolve and ensure the working-tree directory SDD uses for one plan's
# short-lived artifacts: task briefs, implementer reports, review packages,
# and the progress ledger. Print the plan directory's absolute path.
#
# One directory per plan (.superpowers/sdd/<plan-basename>/) so a follow-up
# plan in the same working tree can never read or overwrite another plan's
# artifacts. A stale ledger misread as current progress makes controllers
# skip whole task sequences — plan-scoping removes that failure structurally.
#
# The workspace lives in the working tree (not under .git/) because Claude Code
# treats .git/ as a protected path and denies agent writes there — which blocks
# an implementer subagent from writing its report file. A self-ignoring
# .gitignore at .superpowers/sdd/ keeps every plan's workspace out of
# `git status` and out of accidental commits without modifying any tracked file.
#
# Single source of truth for the workspace location, so task-brief and
# review-package cannot drift to different directories.
#
# Usage: sdd-workspace PLAN_FILE
set -euo pipefail

if [ $# -ne 1 ]; then
  echo "usage: sdd-workspace PLAN_FILE" >&2
  exit 2
fi

plan=$1
[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }

slug=$(basename "$plan" .md)
[ -n "$slug" ] && [ "$slug" != "." ] && [ "$slug" != ".." ] \
  || { echo "cannot derive a workspace name from: $plan" >&2; exit 2; }

root=$(git rev-parse --show-toplevel)
base="$root/.superpowers/sdd"
dir="$base/$slug"
mkdir -p "$dir"
printf '*\n' > "$base/.gitignore"
cd "$dir" && pwd

#!/usr/bin/env bash
# Extract one task's full text from an implementation plan into a file the
# implementer reads in one call, so the task text never has to be pasted
# through the controller's context.
#
# Usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]
# Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/task-<N>-brief.md
# (per plan and per worktree; concurrent runs of the SAME plan in the same
# working tree share it).
set -euo pipefail

if [ $# -lt 2 ] || [ $# -gt 3 ]; then
  echo "usage: task-brief PLAN_FILE TASK_NUMBER [OUTFILE]" >&2
  exit 2
fi

plan=$1
n=$2
[ -f "$plan" ] || { echo "no such plan file: $plan" >&2; exit 2; }

if [ $# -eq 3 ]; then
  out=$3
else
  dir=$("$(cd "$(dirname "$0")" && pwd)/sdd-workspace" "$plan")
  out="$dir/task-${n}-brief.md"
fi

awk -v n="$n" '
  /^```/ { infence = !infence }
  !infence && /^#+[ \t]+Task[ \t]+[0-9]+/ {
    intask = ($0 ~ ("^#+[ \t]+Task[ \t]+" n "([^0-9]|$)"))
  }
  intask { print }
' "$plan" > "$out"

if [ ! -s "$out" ]; then
  echo "task ${n} not found in ${plan} (no heading matching 'Task ${n}')" >&2
  exit 3
fi

echo "wrote ${out}: $(wc -l < "$out" | tr -d ' ') lines"

---
name: subagent-driven-development
description: Use when executing implementation plans with independent tasks in the current session
---

# Subagent-Driven Development

Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.

**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

**Core principle:** Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration

**Narration:** between tool calls, narrate at most one short line — the
ledger and the tool results carry the record.

**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.

**Rulings, not stalls.** A running plan does not wait on a human. Conflicts,
ambiguities, plan defects, a cap you would have asked to exceed — decide
them. The spec is the binding authority, the plan is its argument, and your
judgment settles what neither answers. Record every decision in the ledger as
`Ruling: <what you decided> — <why> — <what it costs if wrong>`, and keep
going. A wrong ruling costs rework your human partner can see and undo; a
session parked on a question costs their whole day and buys nothing.

Four things stop you, and only these: an irreversible or destructive
operation; a security-sensitive action; a side effect outside this worktree
that norms say you ask about first (a merge, a push to a shared branch, a
publish); and a plan so broken that every path forward is a guess. For those,
stop and ask.

## When to Use

```dot
digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Stay in this session?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "executing-plans" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}
```

**vs. Executing Plans (parallel session):**
- Same session (no context switch)
- Fresh subagent per task (no context pollution)
- Review after each task (spec compliance + code quality), broad review at the end
- Faster iteration (no human-in-loop between tasks)

## The Process

```dot
digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
        "Implementer asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer implements, tests, commits, self-reviews" [shape=box];
        "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
        "Spec ✅ and quality approved?" [shape=diamond];
        "Finding conflicts with plan text?" [shape=diamond];
        "Rule on the conflict, ledger the ruling" [shape=box];
        "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [shape=box];
        "Dispatch scoped re-review (./re-review-prompt.md)" [shape=box];
        "All findings addressed?" [shape=diamond];
        "R = 5?" [shape=diamond];
        "Adjudicate each open finding" [shape=box];
        "Any load-bearing finding?" [shape=diamond];
        "Rule and continue; stop only if every path forward is a guess" [shape=box];
        "Park findings in ledger with rulings" [shape=box];
        "Append completion to ledger, mark todo complete" [shape=box];
    }

    "Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [shape=box];
    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" [shape=box];
    "Final review clean: delete this plan's workspace" [shape=box];
    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];

    "Setup: worktree, ledger check, read plan, pre-flight review" -> "Dispatch implementer subagent (./implementer-prompt.md)";
    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer asks questions?";
    "Implementer asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Implementer implements, tests, commits, self-reviews";
    "Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
    "Implementer implements, tests, commits, self-reviews" -> "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)";
    "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
    "Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
    "Spec ✅ and quality approved?" -> "Finding conflicts with plan text?" [label="no"];
    "Finding conflicts with plan text?" -> "Rule on the conflict, ledger the ruling" [label="yes"];
    "Rule on the conflict, ledger the ruling" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model";
    "Finding conflicts with plan text?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no"];
    "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" -> "Dispatch scoped re-review (./re-review-prompt.md)";
    "Dispatch scoped re-review (./re-review-prompt.md)" -> "All findings addressed?";
    "All findings addressed?" -> "Append completion to ledger, mark todo complete" [label="yes"];
    "All findings addressed?" -> "R = 5?" [label="no"];
    "R = 5?" -> "Fix round R of 5: R≤3 resume implementer; R≥4 fresh implementer, more capable model" [label="no - next round"];
    "R = 5?" -> "Adjudicate each open finding" [label="yes - breaker trips"];
    "Adjudicate each open finding" -> "Any load-bearing finding?";
    "Any load-bearing finding?" -> "Rule and continue; stop only if every path forward is a guess" [label="yes"];
    "Any load-bearing finding?" -> "Park findings in ledger with rulings" [label="no"];
    "Park findings in ledger with rulings" -> "Append completion to ledger, mark todo complete";
    "Append completion to ledger, mark todo complete" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
    "More tasks remain?" -> "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [label="no"];
    "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" -> "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals";
    "Final findings? ONE fix dispatch, one scoped re-review, adjudicate residuals" -> "Final review clean: delete this plan's workspace";
    "Final review clean: delete this plan's workspace" -> "Use superpowers:finishing-a-development-branch";
}
```

## Setup

Ensure the work happens in an isolated workspace: use
superpowers:using-git-worktrees to create one or verify the existing one.
Never start implementation on a main/master branch without your human
partner's explicit consent.

Conversation memory does not survive compaction. In real sessions,
controllers that lost their place have re-dispatched entire completed task
sequences — the single most expensive failure observed. Track progress in
a ledger file, not only in todos.

- Each plan owns a workspace: at skill start, run this skill's
  `scripts/sdd-workspace PLAN_FILE` — it prints the plan's git-ignored
  directory (`<repo-root>/.superpowers/sdd/<plan-basename>/`), home to
  every artifact for THIS plan: ledger, briefs, reports, review packages.
  Another plan's directory is never yours to read or write.
- Check for this plan's ledger at `<workspace>/progress.md`. If its first
  line names your plan file, tasks with a `Task <N>: complete` line are DONE
  — do not re-dispatch them; resume at the first task without one. A task
  whose last line is a fix round is mid-loop: resume the loop at the next
  round. A ledger whose first line names a different plan file — or a stray
  ledger at the old flat path `.superpowers/sdd/progress.md` — is another
  plan's progress: leave it in place and start your own, fresh.
- Create the ledger with its identity as the first line:
  `# SDD ledger — plan: <plan file path>`.
- The ledger is your recovery map: the commits it names exist in git even
  when your context no longer remembers creating them. After compaction,
  trust the ledger and `git log` over your own recollection.
- `git clean -fdx` will destroy the workspace (it's git-ignored scratch); if
  that happens, recover from `git log`.

Read the plan once, note its context and Global Constraints, and create a
todo per task. If the plan names a Spec, read that too: the spec is the
authority the plan argues from, and conflicts inside the plan resolve
against it. A plan with no reachable spec gets a ledger note saying so —
rulings made without one are provisional.

Before dispatching Task 1, scan the plan once for conflicts, writing down
what you checked as you check it:

- tasks that contradict each other or the plan's Global Constraints
- anything the plan explicitly mandates that the review rubric treats as a
  defect (a test that asserts nothing, verbatim duplication of a logic block)

The scan's output is a table, not a verdict. One row for every pair of tasks
that share a file or an interface: the two tasks, what one produces against
what the other consumes, and what you found. One row for every task: whether
its own text agrees with itself — the tests it specifies against the code it
specifies, the files it creates against the files it later touches. "The scan
is clean" without those rows is not a scan you ran.

Write the table to the ledger. Rule on everything you find before execution
begins — each finding against the plan text that mandates it — and record
each ruling in the ledger. If the scan is clean, proceed without comment.
Rule on each conflict it surfaces — the spec is the binding authority, the
plan is its argument — record the ruling beside its row, and dispatch
Task 1. The review loop remains the net for conflicts that only emerge from
implementation.

## Model Selection

Use the least powerful model that can handle each role to conserve cost and increase speed.

**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.

**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.

**Architecture and design tasks**: use the most capable available model.
The final whole-branch review is one of these — dispatch it on the most
capable available model, not the session default.

**Review tasks**: choose the model with the same judgment, scaled to the
diff's size, complexity, and risk. A small mechanical diff does not need the
most capable model; a subtle concurrency change does. Scoped re-reviews of
small fix diffs take a cheap-to-mid tier.

**Fix-loop escalation (rounds 4-5)**: use a model at least one tier above
the implementer that got stuck.

**Always specify the model explicitly when dispatching a subagent.** An
omitted model inherits your session's model — often the most capable and
most expensive — which silently defeats this section.

**Turn count beats token price.** Wall-clock and context cost scale with how
many turns a subagent takes, and the cheapest models routinely take 2-3× the
turns on multi-step work — costing more overall. Use a mid-tier model as the
floor for reviewers and for implementers working from prose descriptions.
When the task's plan text contains the complete code to write, the
implementation is transcription plus testing: use the cheapest tier for
that implementer. Single-file mechanical fixes also take the cheapest tier.

**Task complexity signals (implementation tasks):**
- Touches 1-2 files with a complete spec → cheap model
- Touches multiple files with integration concerns → standard model
- Requires design judgment or broad codebase understanding → most capable model

## The Task Loop

**Batch small same-shape work.** When the plan lists several tasks that are
each a small, independent edit of the same kind — the same one-line fix,
constant change, or field addition repeated across files — do not dispatch
one subagent per task. Compose ONE dispatch brief listing every file and
its change, send the whole batch to a single subagent, and review its diff
as one unit. Reserve one-dispatch-per-task for work that needs its own
judgment, its own tests, or its own review surface.

Everything you paste into a dispatch prompt — and everything a subagent
prints back — stays resident in your context for the rest of the session
and is re-read on every later turn. Hand artifacts over as files.

**Waiting on dispatched subagents:** never poll a wait interface with
short timeouts, and never sit in one silent, open-ended wait either.
While you have local work — ledger updates, packaging the next review,
reading reports — keep working; child results arrive on their own.
When you are genuinely idle, wait in bounded stretches (five to ten
minutes, where your platform allows), and between stretches post one
line of status and reconcile your live children: list them, and chase
any that finished without reporting. A bounded stretch keeps nearly
all of a long wait's efficiency while guaranteeing a stuck or lost
child is noticed within minutes, not at the end of the session.

### 1. Dispatch the implementer

Record BASE (`git rev-parse HEAD`) before dispatching — the review package
and fix-round diffs need it.

- **Task brief:** before dispatching an implementer, run this skill's
  `scripts/task-brief PLAN_FILE N` — it extracts the task's full text to a
  uniquely named file and prints the path. Compose the dispatch so the
  brief stays the single source of
  requirements. Your dispatch should contain: (1) one line on where this
  task fits in the project; (2) the brief path, introduced as "read this
  first — it is your requirements, with the exact values to use verbatim";
  (3) interfaces and decisions from earlier tasks that the brief cannot
  know; (4) your resolution of any ambiguity you noticed in the brief;
  (5) the report-file path and report contract. Exact values (numbers,
  magic strings, signatures, test cases) appear only in the brief. Never
  make a subagent read the whole plan file.
- **Report file:** name the implementer's report file after the brief
  (brief `…/task-N-brief.md` → report `…/task-N-report.md`) and put it in
  the dispatch prompt. The implementer writes the full report there and
  returns only status, commits, a one-line test summary, and concerns.
- A dispatch prompt describes one task, not the session's history. Do not
  paste accumulated prior-task summaries ("state after Tasks 1-3") into
  later dispatches — a real session's dispatch hit 42k chars of which 99%
  was pasted history. A fresh subagent needs its task, the interfaces it
  touches, and the global constraints. Nothing else.
- The dispatch carries the no-subagents contract (it is in the
  implementer template): the implementer never dispatches subagents —
  not helpers, and never a reviewer. Review arrives from you, after the
  report. In real sessions, every reviewer a worker spawned duplicated
  the task review the controller dispatched anyway — a full extra
  review seat per task.
- If an earlier task parked a finding in the area this task touches, carry
  a pointer to that ledger entry in the dispatch.
- Record the implementer's agent identity from the dispatch result —
  fix-loop rounds 1-3 resume this agent.
- Never dispatch multiple implementation subagents in parallel (conflicts).

Template: [implementer-prompt.md](implementer-prompt.md)

### 2. Handle the report

Implementer subagents report one of four statuses. Handle each appropriately:

**DONE:** Generate the review package (`scripts/review-package PLAN_FILE BASE HEAD`, from this skill's directory — it prints the unique file path it wrote; BASE is the commit you recorded before dispatching the implementer — never `HEAD~1`, which silently drops all but the last commit of a multi-commit task), then dispatch the task reviewer with the printed path.

**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.

**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.

**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
1. If it's a context problem, provide more context and re-dispatch with the same model
2. If the task requires more reasoning, re-dispatch with a more capable model
3. If the task is too large, break it into smaller pieces
4. If the plan itself is wrong, rule on the correction, ledger it, and re-dispatch with the ruling carried in the dispatch

**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.

If the implementer asks questions — before starting or mid-task — answer
clearly and completely, provide additional context if needed, and don't
rush it into implementation.

### 3. Review the task

Per-task reviews are task-scoped gates. The broad review happens once, at the
final whole-branch review. Never skip the task review, and never accept a
report missing either verdict — spec compliance AND task quality are both
required. Implementer self-review never replaces the task review; both are
needed.

- Hand the reviewer its diff as a file: run this skill's
  `scripts/review-package PLAN_FILE BASE HEAD` and pass the reviewer the file path
  it prints (or, without bash: `git log --oneline`, `git diff --stat`,
  and `git diff -U10` for the range, redirected to one uniquely named
  file). The output never enters your own context, and the reviewer sees
  the commit list, stat summary, and full diff with context in one Read
  call. Use the BASE you recorded before dispatching the implementer —
  never `HEAD~1`, which silently truncates multi-commit tasks. Never
  dispatch a task reviewer without a diff file.
- **Reviewer inputs:** the task reviewer gets three paths — the same brief
  file, the report file, and the review package — plus the global
  constraints that bind the task.
- The global-constraints block you hand the reviewer is its attention
  lens. Copy the binding requirements verbatim from the plan's Global
  Constraints section or the spec: exact values, exact formats, and the
  stated relationships between components ("same layout as X", "matches
  Y"). The reviewer's template already carries the process rules (YAGNI,
  test hygiene, review method) — the constraints block is for what THIS
  project's spec demands.
- Do not add open-ended directives like "check all uses" or "run race tests
  if useful" without a concrete, task-specific reason
- Do not ask a reviewer to re-run tests the implementer already ran on the
  same code — the implementer's report carries the test evidence
- Do not pre-judge findings for the reviewer — never instruct a reviewer to
  ignore or not flag a specific issue. If you believe a finding would be a
  false positive, let the reviewer raise it and adjudicate it in the review
  loop. If the prompt you are writing contains "do not flag," "don't treat X
  as a defect," "at most Minor," or "the plan chose" — stop: you are
  pre-judging, usually to spare yourself a review loop.
The task reviewer may report "⚠️ Cannot verify from diff" items — requirements
that live in unchanged code or span tasks. These do not block the rest of the
review, but you must resolve each one yourself before marking the task
complete: you hold the plan and cross-task context the reviewer
lacks. If you confirm an item is a real gap, treat it as a failed spec
review — it enters the fix loop with the other findings.

Template: [task-reviewer-prompt.md](task-reviewer-prompt.md)

### 4. The fix loop

The loop triggers when the review reports spec ❌, any Critical or Important
finding, or a ⚠️ item you confirmed as a real gap.

Before the loop starts, two routes leave it immediately:

- Record Minor findings in the progress ledger as you go
  (`Task <N>: minor (deferred): <one-liner>`), and point the final
  whole-branch review at that list so it can triage which must be fixed
  before merge. A roll-up nobody reads is a silent discard. Minor findings
  never enter the loop.
- A finding labeled plan-mandated — or any finding that conflicts with
  what the plan's text requires — is yours to rule on: weigh the finding
  against the plan text, decide with the spec as the binding authority, and
  ledger the ruling before you act on it. Do not dismiss the finding because
  the plan mandates it, and do not dispatch a fix that contradicts the plan
  without a recorded ruling.
Everything else enters the loop. A fix round is one fix dispatch plus one
scoped re-review. Five rounds maximum per task:

**Rounds 1-3 — resume the original implementer.** Send it the open findings
verbatim. Its context is intact: it knows the task, the code, and its own
choices. If your harness cannot send another message to a live subagent,
dispatch a fresh implementer carrying the brief path, the report-file path,
and the findings — the report file is the persistent memory either way.

**Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
Model Selection), with the brief path, the report-file path, the open
findings, and this framing: "A prior implementer attempted this task
[N] times; you own it now. Read the report file for what was tried." A loop
that survives three resumes usually means the implementer cannot see its
own problem — fresh eyes and a capability bump in one move.

**Every round, either way:** the implementer fixes, re-runs the tests
covering the amended code, appends its fix report to the same report file,
and returns the short contract. Before re-dispatching the reviewer, confirm
the fix report contains the covering tests, the command run, and the
output; dispatch the re-review once all three are present. Name the
covering test files in the fix message — a one-line fix does not need the
whole suite.

**The re-review is scoped.** Run `scripts/review-package PLAN_FILE FIX_BASE HEAD`
where FIX_BASE is the head the previous review saw, and dispatch
[re-review-prompt.md](re-review-prompt.md) with the findings list, the
brief, the report file, and the printed diff path. The re-reviewer verdicts
each finding ADDRESSED or NOT ADDRESSED and flags new breakage in the fix
diff only. New Critical/Important breakage in the fix diff joins the open
findings list. Out-of-scope observations go to the ledger as deferred
minors — they never extend the loop.

**After each round,** append to the ledger:
`Task <N>: fix round <R>/5 (<X> addressed, <Y> open — <finding one-liners>; commits <a7>..<b7>)`

Never fix findings yourself in the controller session — your context stays
clean for coordination, and controller fixes skip review.

**The breaker.** When round 5's re-review still leaves findings open, stop
dispatching. Adjudicate each open finding yourself — you hold the plan and
the cross-task context the reviewer lacks:

- **The reviewer is wrong, or the point is contestable:** park it —
  `Task <N>: parked — <finding> — Ruling: <why the code stands>`. The final
  review sees both sides.
- **Real, but nothing downstream builds on it:** park it the same way, with
  a ruling that says it's real and deferred.
- **Real and load-bearing** — a later task builds on it, or it reveals a
  plan defect: rule on the smallest change that unblocks the dependent work,
  ledger it as `Task <N>: Ruling: <finding> — <what you decided and why>`,
  and carry it into the next task's dispatch. Parking a structural failure
  silently lets every dependent task build on it. Stop only when the defect
  leaves every path forward a guess.

Adjudicate only at the cap. Adjudicating earlier to end a loop is
pre-judging with a different name. Every adjudication is a ledger entry —
a silent discard is forbidden.

### 5. Complete the task

When the review comes back clean — or every open finding is parked with a
ruling at the cap — append the completion line to the ledger in the same
message as your other bookkeeping:

- `Task <N>: complete (commits <base7>..<head7>, review clean)`
- `Task <N>: complete (commits <base7>..<head7>, <K> parked)` after a
  tripped breaker

Then mark the todo complete and move on. Never move to the next task while
the review has open Critical/Important issues that are neither fixed nor
parked-with-ruling at the cap.

## Final Review

The final whole-branch review gets a package too: run
`scripts/review-package PLAN_FILE MERGE_BASE HEAD` (MERGE_BASE = the commit the
branch started from, e.g. `git merge-base main HEAD`) and include the
printed path in the final review dispatch, so the final reviewer reads
one file instead of re-deriving the branch diff with git commands. Dispatch
on the most capable available model (see Model Selection), using
superpowers:requesting-code-review's
[code-reviewer.md](../requesting-code-review/code-reviewer.md). Point it at
the ledger's deferred-minor and parked lines so it can triage which must be
fixed before merge.

If the final whole-branch review returns findings, dispatch ONE fix subagent
with the complete findings list — not one fixer per finding.
Per-finding fixers each rebuild context and re-run suites; a real
session's final-review fix wave cost more than all its tasks combined.
Then run exactly one scoped re-review of the fix wave
(`scripts/review-package PLAN_FILE FIX_BASE HEAD` over the fix range,
[re-review-prompt.md](re-review-prompt.md)).
Adjudicate any residual findings as in the task loop's breaker: park with
rulings, or rule on the load-bearing ones and ledger what you decided. Only
the four classes above stop you here. There is no second fix wave —
residual load-bearing findings surface to your human partner when
finishing-a-development-branch presents the options.

## Finish

Before you delete anything, collect every ledger line containing `Ruling:` —
preflight rulings, parked findings, breaker adjudications, all of them — into
your final message under "Rulings I made", in the order you made them, each
with what it costs if wrong. The list is exhaustive: if the ledger holds a
ruling, the list holds it. That list is the only place the decisions you
took on your human partner's behalf reach them — they read it and rework
whatever you got wrong. A ruling that dies with the workspace was a decision
made in secret.

When the final whole-branch review is clean and its fixes are merged,
delete this plan's workspace (`rm -rf <workspace>`) — the git history is
the record now. Sibling directories belong to other plans; leave them
alone.

Use superpowers:finishing-a-development-branch.

## Common Rationalizations

| Excuse | Reality |
|--------|---------|
| "Close enough on spec compliance" | Reviewer found spec gaps = not done. Fix or hit the cap and adjudicate — those are the only exits. |
| "I'll fix it myself, dispatching is overhead" | Controller fixes pollute your context and skip review. Resume the implementer. |
| "One more round will converge" | Past the cap, rounds don't converge — the failure is structural. Adjudicate and route. |
| "The reviewer will just find something new anyway" | Scoped re-reviews verify fixes; they cannot wander. New findings on untouched code go to the ledger, not the loop. |
| "This finding is obviously wrong, I'll drop it" | You adjudicate only at the cap, and every ruling is a ledger entry. Silent discards are forbidden. |
| "The fix was small, skip the re-review" | Unreviewed fixes are how regressions land. Every round ends with a scoped re-review. |
| "Reviews slow the loop down" | The loop without reviews is just unverified churn. Reviews are the loop's brakes and steering. |
| "Ledger bookkeeping is overhead" | The ledger is what survives compaction. Controllers without one have re-dispatched entire completed task sequences. |
| "The implementer spawned its own reviewer — free extra assurance" | It's a duplicate seat reviewing the same diff; the task review is the gate. A worker-spawned reviewer is a defect to flag, not rigor. |

## Example Workflow

```
You: I'm using Subagent-Driven Development to execute this plan.

[Setup: worktree verified]
[Read plan file once: docs/superpowers/plans/feature-plan.md]
[Resolve workspace: scripts/sdd-workspace docs/superpowers/plans/feature-plan.md — no ledger inside, fresh start]
[Create todos for all tasks]

Task 1: Hook installation script

[Run task-brief for Task 1; dispatch implementer with brief + report paths + context]

Implementer: "Before I begin - should the hook be installed at user or system level?"

You: "User level (~/.config/superpowers/hooks/)"

Implementer: [Later]
  - Implemented install-hook command
  - Added tests, 5/5 passing
  - Self-review: Found I missed --force flag, added it
  - Committed

[Run review-package PLAN_FILE BASE HEAD; dispatch task reviewer with the printed path]
Task reviewer: Spec ✅ - all requirements met, nothing extra.
  Strengths: Good test coverage, clean. Issues: None. Task quality: Approved.

[Ledger: Task 1: complete (commits a1b2c3d..d4e5f6a, review clean)]

Task 2: Recovery modes

[Run task-brief for Task 2; dispatch implementer with brief + report paths + context]

Implementer: [No questions]
  - Added verify/repair modes
  - 8/8 tests passing
  - Committed

[Run review-package PLAN_FILE BASE HEAD; dispatch task reviewer with the printed path]
Task reviewer: Spec ❌:
  - Missing: Progress reporting (spec says "report every 100 items")
  Issues (Important): Magic number (100)

[Fix round 1: resume the implementer with both findings]
Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
  Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.

[Run review-package PLAN_FILE FIX_BASE HEAD; dispatch scoped re-review]
Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
  Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
  Verdict: all findings addressed.

[Ledger: Task 2: fix round 1/5 (2 addressed, 0 open; commits d4e5f6a..b7c8d9e)]
[Ledger: Task 2: complete (commits d4e5f6a..b7c8d9e, review clean)]

...

[After all tasks]
[Run review-package PLAN_FILE MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
Final reviewer: All requirements met. Deferred minors triaged: none block merge.

[Delete this plan's workspace — the record now lives in git]

Done! Using superpowers:finishing-a-development-branch.
```

# Task Reviewer Prompt Template

Use this template when dispatching a task reviewer subagent. The reviewer
reads the task's diff once and returns two verdicts: spec compliance and
code quality.

**Purpose:** Verify one task's implementation matches its requirements (nothing
more, nothing less) and is well-built (clean, tested, maintainable)

```
Subagent (general-purpose):
  description: "Review Task N (spec + quality)"
  model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
         model silently inherits the session's most expensive one]
  prompt: |
    You are reviewing one task's implementation: first whether it matches its
    requirements, then whether it is well-built. This is a task-scoped gate,
    not a merge review — a broad whole-branch review happens separately after
    all tasks are complete.

    ## What Was Requested

    Read the task brief: [BRIEF_FILE]

    Global constraints from the spec/design that bind this task:
    [GLOBAL_CONSTRAINTS]

    ## What the Implementer Claims They Built

    Read the implementer's report: [REPORT_FILE]

    ## Diff Under Review

    **Base:** [BASE_SHA]
    **Head:** [HEAD_SHA]
    **Diff file:** [DIFF_FILE]

    Read the diff file once — it contains the commit list, a stat summary,
    and the full diff with surrounding context, and it is your view of the
    change. The diff's context lines ARE the changed files: do not Read a
    changed file separately unless a hunk you must judge is cut off
    mid-function — and say so in your report. Do not re-run git commands.
    If the diff file is missing, fetch the diff yourself:
    `git diff --stat [BASE_SHA]..[HEAD_SHA]` and `git diff [BASE_SHA]..[HEAD_SHA]`.
    Do not crawl the broader codebase. Inspect code outside the diff only
    to evaluate a concrete risk you can name — one focused check per named
    risk, and name both the risk and what you checked in your report.
    Cross-cutting changes are legitimate named risks: if the diff changes
    lock ordering, a function or API contract, or shared mutable state,
    checking the call sites is the right method.

    Your review is read-only on this checkout. Do not mutate the working
    tree, the index, HEAD, or branch state in any way.

    ## You Do Not Dispatch Subagents

    Do all of this review yourself. Never spawn a subagent to review part
    of the diff, and never spawn another reviewer for a second opinion.
    This process already provides every review seat the work gets; a
    reviewer you spawn duplicates one of them at full cost, and its
    verdict counts for nothing. If the diff feels too large for one
    pass, review it in passes yourself and say so in your report.

    ## Do Not Trust the Report

    Treat the implementer's report as unverified claims about the code. It
    may be incomplete, inaccurate, or optimistic. Verify the claims against
    the diff. Design rationales in the report are claims too: "left it per
    YAGNI," "kept it simple deliberately," or any other justification is the
    implementer grading their own work. Judge the code on its merits — a
    stated rationale never downgrades a finding's severity.

    ## Tests

    The implementer already ran the tests and reported results with TDD
    evidence for exactly this code. Do not re-run the suite to confirm their
    report. Run a test only when reading the code raises a specific doubt
    that no existing run answers — and then a focused test, never a
    package-wide suite, race detector run, or repeated/high-count loop. If
    heavy validation seems warranted, recommend it in your report instead of
    running it. If you cannot run commands in this environment, name the
    test you would run.

    Warnings or other noise in the implementer's reported test output are
    findings — test output should be pristine.

    Evidence you cannot see is not evidence that doesn't exist. If the
    report or its test evidence looks truncated, or you cannot locate the
    results it claims, re-read the file at its stated path — and if it is
    genuinely missing or garbled, report that as a gap for the controller.
    Re-running the suite to regenerate what you failed to read is not
    verification; illegibility of the evidence is not invalidation of it.

    ## Part 1: Spec Compliance

    Compare the diff against What Was Requested:

    - **Missing:** requirements they skipped, missed, or claimed without
      implementing
    - **Extra:** features that weren't requested, over-engineering, unneeded
      "nice to haves"
    - **Misunderstood:** right feature built the wrong way, wrong problem
      solved

    If the brief lists several files each with its own change (a batched
    dispatch), check the diff against that list file by file: every listed
    file must have its corresponding hunk. A listed file the diff never
    touches is a Missing finding, no matter how clean the rest of the
    batch looks.

    If a requirement cannot be verified from this diff alone (it lives in
    unchanged code or spans tasks), report it as a ⚠️ item instead of
    broadening your search.

    ## Part 2: Code Quality

    **Code quality:**
    - Clean separation of concerns?
    - Proper error handling?
    - DRY without premature abstraction?
    - Edge cases handled?

    **Tests:**
    - Do the new and changed tests verify real behavior, not mocks?
    - Are the task's edge cases covered?

    **Structure:**
    - Does each file have one clear responsibility with a well-defined interface?
    - Are units decomposed so they can be understood and tested independently?
    - Is the implementation following the file structure from the plan?
    - Did this change create new files that are already large, or
      significantly grow existing files? (Don't flag pre-existing file
      sizes — focus on what this change contributed.)

    Your report should point at evidence: file:line references for every
    finding and for any check you would otherwise answer with a bare
    "yes." A tight report that cites lines gives the controller everything
    it needs.

    Your final message is the report itself: begin directly with the
    spec-compliance verdict. Every line is a verdict, a finding with
    file:line, or a check you ran — no preamble, no process narration,
    no closing summary.

    ## Calibration

    Categorize issues by actual severity. Not everything is Critical.
    Important means this task cannot be trusted until it is fixed: incorrect
    or fragile behavior, a missed requirement, or maintainability damage you
    would block a merge over — verbatim duplication of a logic block,
    swallowed errors, tests that assert nothing. "Coverage could be broader"
    and polish suggestions are Minor.
    If the plan or brief explicitly mandates something this rubric calls a
    defect (a test that asserts nothing, verbatim duplication of a logic
    block), that IS a finding — report it as Important, labeled
    plan-mandated. The plan's authorship does not grade its own work; the
    human decides.
    Acknowledge what was done well before listing issues — accurate praise
    helps the implementer trust the rest of the feedback.

    ## Output Format

    ### Spec Compliance

    - ✅ Spec compliant | ❌ Issues found: [what's missing/extra/misunderstood,
      with file:line references]
    - ⚠️ Cannot verify from diff: [requirements you could not verify from the
      diff alone, and what the controller should check — report alongside the
      ✅/❌ verdict for everything you could verify]

    ### Strengths
    [What's well done? Be specific.]

    ### Issues

    #### Critical (Must Fix)
    #### Important (Should Fix)
    #### Minor (Nice to Have)

    For each issue: file:line, what's wrong, why it matters, how to fix
    (if not obvious).

    ### Assessment

    **Task quality:** [Approved | Needs fixes]

    **Reasoning:** [1-2 sentence technical assessment]
```

**Placeholders:**
- `[MODEL]` — REQUIRED: reviewer model per SKILL.md Model Selection
- `[BRIEF_FILE]` — REQUIRED: the task brief file (`scripts/task-brief PLAN N`
  prints the path; same file the implementer worked from)
- `[GLOBAL_CONSTRAINTS]` — the binding requirements copied verbatim from
  the plan's Global Constraints section or the spec: exact values, formats,
  and stated relationships between components (not process rules — those
  are already in this template)
- `[REPORT_FILE]` — REQUIRED: the file the implementer wrote its detailed
  report to
- `[BASE_SHA]` — commit before this task
- `[HEAD_SHA]` — current commit
- `[DIFF_FILE]` — REQUIRED: the path the controller wrote the review
  package to (`scripts/review-package PLAN_FILE BASE HEAD` prints the unique
  path it wrote; the package never enters the controller's context)

**Reviewer returns:** Spec Compliance verdict (✅/❌/⚠️), Strengths, Issues
(Critical/Important/Minor), Task quality verdict