A skill for checking an open GitHub issue or pull request against the current code and deciding whether to implement it, leave it open, or close it. GitHub is a service for hosting code, issues, and proposed changes for review.

Use it to inspect issue or pull-request details, verify claims in the repository, review related changes, and report a factual decision.

It replaces guesswork with a code-based check of whether the reported problem still exists and whether a proposed change is still relevant.

triage — Skill for Claude Code by bengous

Install

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.

Any agent

npx skills add bengous/claude-code-plugins --skill triage

Clone the repo

git clone --depth 1 https://github.com/bengous/claude-code-plugins

Made for: Claude Code.

Or install git-tools, the plugin that ships this one along with the rest of its 6 skills, 2 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bengous/claude-code-plugins/triage.svg)](https://agentmods.dev/skills/bengous/claude-code-plugins/triage)

Your own site

<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/triage"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/triage.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 884 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00059	$0.00884
Opus 5	$0.00030	$0.00442
Sonnet 5	$0.00012	$0.00177
Haiku 4.5	$0.00006	$0.00088

Measured 4d ago against content hash befe693e30fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

triage 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.

git-tools/skills/triage/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage

Decide the fate of one issue or PR from the current code. Never state something about code you did not read this session.

Target

$ARGUMENTS

A URL with /pull/ is a PR, with /issues/ an issue.
A bare number: gh issue view <n> --json url; a /pull/ URL means it is a PR.
Empty: run gh issue list --limit 30 and gh pr list --limit 30, show both lists, ask which one to triage.

Protocol

Fetch.
- Issue: gh issue view <n> --json title,body,state,labels,comments,url
- PR: gh pr view <n> --json title,body,state,baseRefName,headRefName,mergeable,reviewDecision,statusCheckRollup,comments,url,additions,deletions and gh pr diff <n> --stat
Closed already: report it and stop.
Extract the claims. The problem, every file, symbol, or error named, expected versus actual, the reproduction if given, the open questions in the comments.
Verify each claim. Glob and Grep to locate, Read to confirm. git log --oneline -20 -- <file> finds a fix that landed without a link. For a PR, also check: does it apply to the current base (mergeable), do the checks pass, does the code it changes still exist on the base, has a competing change landed since.

Verdict. One word, with the proof next to it.

Issue	PR
`valid`: confirmed in the code, root cause named	`mergeable`: applies, checks pass, still wanted
`fixed`: name the commit	`needs-rebase`: conflicts or stale base
`outdated`: the code it describes is gone or changed	`superseded`: name the commit or PR that landed instead
`duplicate`: of #N	`stale`: an open question with no answer, give the date
`unclear`: what is missing to verify	`unclear`: what is missing to verify

Report in this shape, then ask.
```
## #<n> <title>
Verdict: <word>
Proof: <anchor or commit>, <anchor or commit>
Recommendation: <implement | keep | close as <reason>>
```
AskUserQuestion with the options that fit the verdict, and put the exact comment text inside the option that would post it:

Read the full file on GitHub · 71 lines

Changes

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 · 71 lines · 59 tokens per session scan A befe693e30fe

Subscribe to this mod's changes

triage is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 884 once invoked, about $0.0003 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 2026-09-03.

Claude Code Code review Debugging automation developer-tools workflow

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens

create-issue

Transitional alias — prefer /prflow:specs, which runs the same issue-drafting pipeline. Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue rather than built right now. This command name is retained so existing /prflow:create-issue…

The01Geek/prflow · 89 tokens

docs-release-notes

Use when a change needs a user-visible release-note, changelog, or changeset entry — "add a release note", "add a changeset for this", "what goes in the changelog?", "write up what shipped", "note this for the next release" — or when finalizing a branch whose customer-visible features, bug fixes, or UI changes should…

The01Geek/prflow · 106 tokens

retrospective-audit

Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…

The01Geek/prflow · 91 tokens

ag-avaliar-arquitetura

Maquina autonoma de saude arquitetural. 5D (STRUCTURE/COUPLING/DEBT/PATTERNS/SCALE), imports circulares, tech debt, consistencia. AQS >= 80.

andregusman-raiz/a-gusman-claude · 55 tokens

Receiving Code Review

Guidelines for analyzing and applying peer code review feedback objectively.

ankur-gaurav161418/omniforge · 16 tokens