Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/muhimu/claude-plan-lifecycle/pr-fixgit clone --depth 1 https://github.com/muhimu/claude-plan-lifecycleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/muhimu/claude-plan-lifecycle/pr-fix)<a href="https://agentmods.dev/commands/muhimu/claude-plan-lifecycle/pr-fix"><img src="https://agentmods.dev/badge/commands/muhimu/claude-plan-lifecycle/pr-fix.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.01258 |
| Opus 5 | $0.00014 | $0.00629 |
| Sonnet 5 | $0.00005 | $0.00252 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
pr-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Fix
Address review feedback on a pull request. You handle code changes and pushing commits; the user handles all GitHub replies and thread resolution.
Resolving the PR
If $ARGUMENTS contains a PR number, use it. Otherwise:
gh pr view --json number,headRefName,baseRefName,url
This auto-detects the PR for the currently checked-out branch. If there is no PR, stop and tell the user — do not create one.
Step 1 — Fetch review state
Get inline review comments with file/line anchors, top-level review comments, and the PR diff:
# Inline comments (the ones anchored to specific lines)
gh api "repos/{owner}/{repo}/pulls/<PR>/comments" --paginate > /tmp/pr-fix-inline.json
# Top-level reviews (overall approve/request-changes bodies)
gh pr view <PR> --json reviews,comments,headRefName,baseRefName,headRefOid
# Current diff for context
gh pr diff <PR>
Read all three. Filter out comments authored by the user themselves (gh api user --jq '.login') and any comments that are obviously already resolved (the line they point to no longer exists in HEAD).
Step 2 — Classify and plan
Sort each remaining comment into one bucket:
| Bucket | Meaning | Action |
|---|---|---|
| Actionable | Clear code change requested | Plan a code edit |
| Question | Reviewer asking for clarification, no code change | Draft a reply for the user |
| Suggestion | Reviewer's preference — requires judgment | Evaluate, then either Actionable or Pushback |
| Nit | Stylistic, low-stakes | Plan a code edit (cheap to address) |
| Pushback | Suggestion is wrong for this codebase | Draft a reply explaining why |
| Stale | Comment is on code that's since been changed | Skip, note it |
Before classifying, invoke the superpowers:receiving-code-review skill via the Skill tool. That skill owns the verify-before-implementing discipline, YAGNI checks, and pushback patterns — do not re-derive them here. If the skill is not available (superpowers plugin not installed), proceed without it and apply the same discipline yourself: verify each claim against the code before implementing, and push back with technical reasoning instead of performative agreement.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 117 lines · 27 tokens per session scan A 66a13762df8f
pr-fix is a command published in the GitHub repository muhimu/claude-plan-lifecycle (2 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 1,258 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.