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 skills/reviewstage/stage-cli/fixing-pr-commentsnpx skills add ReviewStage/stage-cli --skill fixing-pr-commentsgit clone --depth 1 https://github.com/ReviewStage/stage-cliWhat 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 | $0.00946 |
| Opus 5 | $0.00014 | $0.00473 |
| Sonnet 5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
fixing-pr-comments scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixing PR Comments
Fetch all unresolved PR threads, triage, fix blockers, resolve the rest.
Workflow
1. DETECT → PR number/repo from current branch
2. FETCH → Unresolved review threads (GraphQL)
3. TRIAGE → Classify each: FIX / RESOLVE / CLARIFY
4. PRESENT → Show triage table, proceed immediately
5. FIX → Implement → verify → commit → reply → resolve (one commit per fix)
6. PUSH → Push all commits
7. RESPOND → Reply to RESOLVE (+ resolve) and CLARIFY threads
Detect & Fetch
gh pr view --json number,url
# GraphQL required — REST lacks isResolved
# Use --input - to avoid gh's -f flag mangling ! in non-null type annotations
gh api graphql --input - <<'GRAPHQL'
{
"query": "query($owner:String!,$repo:String!,$pr:Int!){repository(owner:$owner,name:$repo){pullRequest(number:$pr){reviewThreads(first:100){nodes{id isResolved path line comments(first:10){nodes{id databaseId body author{login}}}}}}}}",
"variables": {"owner": "OWNER", "repo": "REPO", "pr": NUM}
}
GRAPHQL
Filter to isResolved: false only.
Triage
Default to RESOLVE. Only FIX what genuinely blocks merge. Resolve everything else with reasoning. Don't gold-plate — ship it.
| Category | Criteria | Action |
|---|---|---|
| FIX | Bugs, security issues, correctness problems — blocks merge | Implement + commit + resolve |
| RESOLVE | Nits, style, "consider X", minor suggestions, pedantic bot feedback, already addressed | Reply with reasoning + resolve |
| CLARIFY | Ambiguous, needs context | Ask in thread, leave open |
Quality flag during triage: If a comment requests something that violates a principle in the Implementation Quality section of AGENTS.md, categorize it as RESOLVE and cite the specific principle it conflicts with.
Present triage table, then proceed immediately:
| # | File:Line | Summary | Category | Reasoning |
Fix Loop
For each FIX:
- Implement the change
- Apply forward — find the same pattern elsewhere in the codebase and fix those too
- Quality gate — evaluate the fix against every principle in the Implementation Quality section of AGENTS.md. If any principle is violated, revise before committing.
- Verify it compiles/passes
- Commit (one per fix)
- Reply + resolve:
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.
- 2d ago First seen · 103 lines · 27 tokens per session scan A 8425c8638c68
fixing-pr-comments is a skill published in the GitHub repository ReviewStage/stage-cli (267 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 946 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…