rogee/superpowers
1
0
Fork 0
mirror of https://github.com/obra/superpowers.git synced 2026-07-17 23:44:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(sdd): lifecycle restructure with resume-based fix loop, five-round breaker, and rationalization table

Browse Source
This commit is contained in:
Jesse Vincent
2026-07-15 11:53:32 -07:00
parent 236077326b
commit 1f97eda0fc
1 changed files with 281 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

454
skills/subagent-driven-development/SKILL.md
View File

@@ -51,41 +51,85 @@ digraph process {
subgraph cluster_per_task { subgraph cluster_per_task {
label="Per Task"; label="Per Task";
"Dispatch implementer subagent (./implementer-prompt.md)" [shape=box]; "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
"Implementer subagent asks questions?" [shape=diamond]; "Implementer asks questions?" [shape=diamond];
"Answer questions, provide context" [shape=box]; "Answer questions, provide context" [shape=box];
"Implementer subagent implements, tests, commits, self-reviews" [shape=box]; "Implementer implements, tests, commits, self-reviews" [shape=box];
"Write diff file, dispatch task reviewer subagent (./task-reviewer-prompt.md)" [shape=box]; "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" [shape=box];
"Task reviewer reports spec ✅ and quality approved?" [shape=diamond]; "Spec ✅ and quality approved?" [shape=diamond];
"Dispatch fix subagent for Critical/Important findings" [shape=box]; "Finding conflicts with plan text?" [shape=diamond];
"Mark task complete in todo list and progress ledger" [shape=box]; "Ask human partner which governs" [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];
"STOP: report BLOCKED to human partner" [shape=box];
"Park findings in ledger with rulings" [shape=box];
"Append completion to ledger, mark todo complete" [shape=box];
} }
"Read plan, note context and global constraints, create todos" [shape=box]; "Setup: worktree, ledger check, read plan, pre-flight review" [shape=box];
"More tasks remain?" [shape=diamond]; "More tasks remain?" [shape=diamond];
"Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [shape=box]; "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];
"Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen]; "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
"Read plan, note context and global constraints, create todos" -> "Dispatch implementer subagent (./implementer-prompt.md)"; "Setup: worktree, ledger check, read plan, pre-flight review" -> "Dispatch implementer subagent (./implementer-prompt.md)";
"Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?"; "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer asks questions?";
"Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"]; "Implementer asks questions?" -> "Answer questions, provide context" [label="yes"];
"Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)"; "Answer questions, provide context" -> "Implementer implements, tests, commits, self-reviews";
"Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"]; "Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
"Implementer subagent implements, tests, commits, self-reviews" -> "Write diff file, dispatch task reviewer subagent (./task-reviewer-prompt.md)"; "Implementer implements, tests, commits, self-reviews" -> "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)";
"Write diff file, dispatch task reviewer subagent (./task-reviewer-prompt.md)" -> "Task reviewer reports spec ✅ and quality approved?"; "Generate review package, dispatch task reviewer (./task-reviewer-prompt.md)" -> "Spec ✅ and quality approved?";
"Task reviewer reports spec ✅ and quality approved?" -> "Dispatch fix subagent for Critical/Important findings" [label="no"]; "Spec ✅ and quality approved?" -> "Append completion to ledger, mark todo complete" [label="yes"];
"Dispatch fix subagent for Critical/Important findings" -> "Write diff file, dispatch task reviewer subagent (./task-reviewer-prompt.md)" [label="re-review"]; "Spec ✅ and quality approved?" -> "Finding conflicts with plan text?" [label="no"];
"Task reviewer reports spec ✅ and quality approved?" -> "Mark task complete in todo list and progress ledger" [label="yes"]; "Finding conflicts with plan text?" -> "Ask human partner which governs" [label="yes"];
"Mark task complete in todo list and progress ledger" -> "More tasks remain?"; "Ask human partner which governs" -> "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?" -> "STOP: report BLOCKED to human partner" [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 implementer subagent (./implementer-prompt.md)" [label="yes"];
"More tasks remain?" -> "Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" [label="no"]; "More tasks remain?" -> "Dispatch final code reviewer (../requesting-code-review/code-reviewer.md)" [label="no"];
"Dispatch final code reviewer subagent (../requesting-code-review/code-reviewer.md)" -> "Use superpowers:finishing-a-development-branch"; "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" -> "Use superpowers:finishing-a-development-branch";
} }
``` ```
## Pre-Flight Plan Review ## Setup
Ensure the work happens in an isolated workspace: use Ensure the work happens in an isolated workspace: use
superpowers:using-git-worktrees to create one or verify the existing one. 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.
- At skill start, check for a ledger:
`cat "$(git rev-parse --show-toplevel)/.superpowers/sdd/progress.md"`. 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.
- 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 ledger (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.
Before dispatching Task 1, scan the plan once for conflicts: Before dispatching Task 1, scan the plan once for conflicts:
@@ -113,7 +157,11 @@ capable available model, not the session default.
**Review tasks**: choose the model with the same judgment, scaled to the **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 diff's size, complexity, and risk. A small mechanical diff does not need the
most capable model; a subtle concurrency change does. 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 **Always specify the model explicitly when dispatching a subagent.** An
omitted model inherits your session's model — often the most capable and omitted model inherits your session's model — often the most capable and
@@ -132,7 +180,47 @@ that implementer. Single-file mechanical fixes also take the cheapest tier.
- Touches multiple files with integration concerns → standard model - Touches multiple files with integration concerns → standard model
- Requires design judgment or broad codebase understanding → most capable model - Requires design judgment or broad codebase understanding → most capable model
## Handling Implementer Status ## The Task Loop
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.
### 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.
- 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: Implementer subagents report one of four statuses. Handle each appropriately:
@@ -150,20 +238,37 @@ Implementer subagents report one of four statuses. Handle each appropriately:
**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change. **Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
## Handling Reviewer ⚠️ Items 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.
The task reviewer may report "⚠️ Cannot verify from diff" items — requirements ### 3. Review the task
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 — send it back to the implementer and re-review.
## Constructing Reviewer Prompts
Per-task reviews are task-scoped gates. The broad review happens once, at the Per-task reviews are task-scoped gates. The broad review happens once, at the
final whole-branch review. When you fill a reviewer template: 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 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 - Do not add open-ended directives like "check all uses" or "run race tests
if useful" without a concrete, task-specific reason if useful" without a concrete, task-specific reason
- Do not ask a reviewer to re-run tests the implementer already ran on the - Do not ask a reviewer to re-run tests the implementer already ran on the
@@ -174,111 +279,153 @@ final whole-branch review. When you fill a reviewer template:
loop. If the prompt you are writing contains "do not flag," "don't treat X 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 as a defect," "at most Minor," or "the plan chose" — stop: you are
pre-judging, usually to spare yourself a review loop. pre-judging, usually to spare yourself a review loop.
- The global-constraints block you hand the reviewer is its attention
lens. Copy the binding requirements verbatim from the plan's Global The task reviewer may report "⚠️ Cannot verify from diff" items — requirements
Constraints section or the spec: exact values, exact formats, and the that live in unchanged code or span tasks. These do not block the rest of the
stated relationships between components ("same layout as X", "matches review, but you must resolve each one yourself before marking the task
Y"). The reviewer's template already carries the process rules (YAGNI, complete: you hold the plan and cross-task context the reviewer
test hygiene, review method) — the constraints block is for what THIS lacks. If you confirm an item is a real gap, treat it as a failed spec
project's spec demands. review — it enters the fix loop with the other findings.
- Hand the reviewer its diff as a file: run this skill's
`scripts/review-package BASE HEAD` and pass the reviewer the file path Template: [task-reviewer-prompt.md](task-reviewer-prompt.md)
it prints (or, without bash: `git log --oneline`, `git diff --stat`,
and `git diff -U10` for the range, redirected to one uniquely named ### 4. The fix loop
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 The loop triggers when the review reports spec ❌, any Critical or Important
call. Use the BASE you recorded before dispatching the implementer — finding, or a ⚠️ item you confirmed as a real gap.
never `HEAD~1`, which silently truncates multi-commit tasks.
- A dispatch prompt describes one task, not the session's history. Do not Before the loop starts, two routes leave it immediately:
paste accumulated prior-task summaries ("state after Tasks 1-3") into
later dispatches — a real session's dispatch hit 42k chars of which 99% - Record Minor findings in the progress ledger as you go
was pasted history. A fresh subagent needs its task, the interfaces it (`Task <N>: minor (deferred): <one-liner>`), and point the final
touches, and the global constraints. Nothing else.
- Dispatch fix subagents for Critical and Important findings. Record Minor
findings in the progress ledger as you go, and point the final
whole-branch review at that list so it can triage which must be fixed 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. 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 - A finding labeled plan-mandated — or any finding that conflicts with
what the plan's text requires — is the human's decision, like any plan what the plan's text requires — is the human's decision, like any plan
contradiction: present the finding and the plan text, ask which governs. contradiction: present the finding and the plan text, ask which governs.
Do not dismiss the finding because the plan mandates it, and do not Do not dismiss the finding because the plan mandates it, and do not
dispatch a fix that contradicts the plan without asking. dispatch a fix that contradicts the plan without asking.
- The final whole-branch review gets a package too: run
`scripts/review-package 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.
- Every fix dispatch carries the implementer contract: the fix subagent
re-runs the tests covering its change and reports the results. Name the
covering test files in the dispatch — a one-line fix does not need the
whole suite. 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.
- 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.
## File Handoffs Everything else enters the loop. A fix round is one fix dispatch plus one
scoped re-review. Five rounds maximum per task:
Everything you paste into a dispatch prompt — and everything a subagent **Rounds 1-3 — resume the original implementer.** Send it the open findings
prints back — stays resident in your context for the rest of the session verbatim. Its context is intact: it knows the task, the code, and its own
and is re-read on every later turn. Hand artifacts over as files: 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.
- **Task brief:** before dispatching an implementer, run this skill's **Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
`scripts/task-brief PLAN_FILE N` — it extracts the task's full text to a Model Selection), with the brief path, the report-file path, the open
uniquely named file and prints the path. Compose the dispatch so the findings, and this framing: "A prior implementer attempted this task
brief stays the single source of requirements. Your dispatch should [N] times; you own it now. Read the report file for what was tried." A loop
contain: (1) one line on where this task fits in the project; (2) the that survives three resumes usually means the implementer cannot see its
brief path, introduced as "read this first — it is your requirements, own problem — fresh eyes and a capability bump in one move.
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.
- **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.
- **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.
- Fix dispatches append their fix report (with test results) to the same
report file and return a short summary; re-reviews read the updated file.
## Durable Progress **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.
Conversation memory does not survive compaction. In real sessions, **The re-review is scoped.** Run `scripts/review-package FIX_BASE HEAD`
controllers that lost their place have re-dispatched entire completed task where FIX_BASE is the head the previous review saw, and dispatch
sequences — the single most expensive failure observed. Track progress in [re-review-prompt.md](re-review-prompt.md) with the findings list, the
a ledger file, not only in todos. 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.
- At skill start, check for a ledger: **After each round,** append to the ledger:
`cat "$(git rev-parse --show-toplevel)/.superpowers/sdd/progress.md"`. Tasks listed there `Task <N>: fix round <R>/5 (<X> addressed, <Y> open — <finding one-liners>; commits <a7>..<b7>)`
as complete are DONE — do not re-dispatch them; resume at the first task
not marked complete.
- When a task's review comes back clean, append one line to the ledger in
the same message as your other bookkeeping:
`Task N: complete (commits <base7>..<head7>, review clean)`.
- 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 ledger (it's git-ignored scratch); if
that happens, recover from `git log`.
## Prompt Templates Never fix findings yourself in the controller session — your context stays
clean for coordination, and controller fixes skip review.
- [implementer-prompt.md](implementer-prompt.md) - Dispatch implementer subagent **The breaker.** When round 5's re-review still leaves findings open, stop
- [task-reviewer-prompt.md](task-reviewer-prompt.md) - Dispatch task reviewer subagent (spec compliance + code quality) dispatching. Adjudicate each open finding yourself — you hold the plan and
- Final whole-branch review: use superpowers:requesting-code-review's [code-reviewer.md](../requesting-code-review/code-reviewer.md) 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: STOP. Append `Task <N>: BLOCKED — <reason>` and report to
your human partner with the finding, the plan text it collides with, and
the fix history. Parking a structural failure lets every dependent task
build on it and hands the final review a problem it cannot fix either.
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 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` 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 stop on load-bearing ones. There is no second fix wave —
residual load-bearing findings surface to your human partner when
finishing-a-development-branch presents the options.
## Finish
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. |
## Example Workflow ## Example Workflow
``` ```
You: I'm using Subagent-Driven Development to execute this plan. You: I'm using Subagent-Driven Development to execute this plan.
[Read plan file once: docs/superpowers/plans/feature-plan.md] [Setup: worktree verified, no ledger found, read plan, created todos]
[Create todos for all tasks]
Task 1: Hook installation script Task 1: Hook installation script
@@ -288,8 +435,7 @@ Implementer: "Before I begin - should the hook be installed at user or system le
You: "User level (~/.config/superpowers/hooks/)" You: "User level (~/.config/superpowers/hooks/)"
Implementer: "Got it. Implementing now..." Implementer: [Later]
[Later] Implementer:
- Implemented install-hook command - Implemented install-hook command
- Added tests, 5/5 passing - Added tests, 5/5 passing
- Self-review: Found I missed --force flag, added it - Self-review: Found I missed --force flag, added it
@@ -299,77 +445,39 @@ Implementer: "Got it. Implementing now..."
Task reviewer: Spec ✅ - all requirements met, nothing extra. Task reviewer: Spec ✅ - all requirements met, nothing extra.
Strengths: Good test coverage, clean. Issues: None. Task quality: Approved. Strengths: Good test coverage, clean. Issues: None. Task quality: Approved.
[Mark Task 1 complete] [Ledger: Task 1: complete (commits a1b2c3d..d4e5f6a, review clean)]
Task 2: Recovery modes Task 2: Recovery modes
[Run task-brief for Task 2; dispatch implementer with brief + report paths + context] [Run task-brief for Task 2; dispatch implementer with brief + report paths + context]
Implementer: [No questions, proceeds] Implementer: [No questions]
Implementer:
- Added verify/repair modes - Added verify/repair modes
- 8/8 tests passing - 8/8 tests passing
- Self-review: All good
- Committed - Committed
[Run review-package, dispatch task reviewer with the printed path] [Run review-package, dispatch task reviewer with the printed path]
Task reviewer: Spec ❌: Task reviewer: Spec ❌:
- Missing: Progress reporting (spec says "report every 100 items") - Missing: Progress reporting (spec says "report every 100 items")
- Extra: Added --json flag (not requested)
Issues (Important): Magic number (100) Issues (Important): Magic number (100)
[Dispatch fix subagent with all findings] [Fix round 1: resume the implementer with both findings]
Fixer: Removed --json flag, added progress reporting, extracted PROGRESS_INTERVAL constant Implementer: Added progress reporting, extracted PROGRESS_INTERVAL constant.
Re-ran test/recovery.test.js — 10/10 passing. Fix report appended.
[Task reviewer reviews again] [Run review-package FIX_BASE HEAD; dispatch scoped re-review]
Task reviewer: Spec ✅. Task quality: Approved. Re-reviewer: Missing progress reporting — ADDRESSED (src/recovery.js:41).
Magic number — ADDRESSED (src/recovery.js:7). New breakage: none.
Verdict: all findings addressed.
[Mark Task 2 complete] [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] [After all tasks]
[Dispatch final code-reviewer] [Run review-package MERGE_BASE HEAD; dispatch final code-reviewer, most capable model]
Final reviewer: All requirements met, ready to merge Final reviewer: All requirements met. Deferred minors triaged: none block merge.
Done! Done! Using superpowers:finishing-a-development-branch.
``` ```
## Red Flags
**Never:**
- Start implementation on main/master branch without explicit user consent
- Skip task review, or accept a report missing either verdict (spec compliance AND task quality are both required)
- Proceed with unfixed issues
- Dispatch multiple implementation subagents in parallel (conflicts)
- Make a subagent read the whole plan file (hand it its task brief —
`scripts/task-brief` — instead)
- Skip scene-setting context (subagent needs to understand where task fits)
- Ignore subagent questions (answer before letting them proceed)
- Accept "close enough" on spec compliance (reviewer found spec issues = not done)
- Skip review loops (reviewer found issues = implementer fixes = review again)
- Let implementer self-review replace actual review (both are needed)
- Tell a reviewer what not to flag, or pre-rate a finding's severity in the
dispatch prompt ("treat it as Minor at most") — the plan's example code is
a starting point, not evidence that its weaknesses were chosen
- Dispatch a task reviewer without a diff file — generate it first
(`scripts/review-package BASE HEAD`) and name the printed path in the
prompt
- Move to next task while the review has open Critical/Important issues
- Re-dispatch a task the progress ledger already marks complete — check
the ledger (and `git log`) after any compaction or resume
**If subagent asks questions:**
- Answer clearly and completely
- Provide additional context if needed
- Don't rush them into implementation
**If reviewer finds issues:**
- Implementer (same subagent) fixes them
- Reviewer reviews again
- Repeat until approved
- Don't skip the re-review
**If subagent fails task:**
- Dispatch fix subagent with specific instructions
- Don't try to fix manually (context pollution)