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 skills add bendrucker/claude --skill github-triagegit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/skills/bendrucker/claude/github-triage)<a href="https://agentmods.dev/skills/bendrucker/claude/github-triage"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/github-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bendrucker/claude/github-triage"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/github-triage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00050 | $0.01181 |
| Opus 5.5 | $0.00020 | $0.00472 |
| Sonnet 5.5 | $0.00010 | $0.00236 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
github-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 1mo 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Triage
Clear bot and Dependabot noise from the notification inbox, leave threads from real humans. --dry-run classifies and prints the plan without acting.
Inbox
!gh api "notifications?all=true&per_page=100" --paginate | jq -r '.[] | [.id, .reason, .subject.type, .repository.full_name, (.subject.url | sub(".*/pulls/";"#") | sub(".*/issues/";"issue#")), .subject.title] | @tsv' | column -t -s $'\t'
Triage against all=true. The default call returns only unread; the app Inbox also shows read-but-not-done threads, where most stale noise sits. First column is the thread id, which is also the mark-done key.
Gather
Resolve your own login once: gh api user --jq .login. For each open PullRequest thread:
gh api repos/<r>/pulls/<n> --jq '{author:.user.login, state, merged:(.merged_at!=null)}'. Any closed/merged PR is settled: mark done, skip the rest.gh pr view <n> --repo <r> --json mergeStateStatus. Merge gate, per the table below. It computes async, so re-fetch once onUNKNOWN.gh api repos/<r> --jq .permissions.push.truemeans you can merge.- Latest actor, only for a your-own-PR-in-your-own-repo thread:
gh api <subject.latest_comment_url> --jq '{login:.user.login, type:.user.type}'.
mergeStateStatus |
Meaning | Action |
|---|---|---|
CLEAN |
green, no conflict, current | mergeable |
BLOCKED |
needs review or a required check | leave, never force |
BEHIND |
base moved | leave, Dependabot rebases |
UNSTABLE / DIRTY |
check failed or conflict | classify by importance |
UNKNOWN |
not computed | re-fetch once |
Classify
First match wins.
- Closed or merged PR → done, whatever the author or reason. Largest category: every merge and every landed bump leaves a read-but-not-done thread.
- Bot or self activity on your own PR → done. PR author is you, repo owner is you, and the latest actor is you or a bot (
typeBot): your own automation (Worktrunk, Greptile, CI) and replies on your own work. Exception: a different human as latest actor is real feedback, leave it. Personal namespace only, not shared orgs. - Open human thread (
reasonmention/comment, or a person authored) → leave. - Open non-Dependabot bot (e.g.
github-actions[bot]generated content) → leave; the diff is real. - Open Dependabot,
CLEAN, you have push → merge, then done. - Open Dependabot, not mergeable, low-importance → done, leave PR open. Low-importance:
deps-devtooling (eslint, prettier, globals, ncc,@types/*) and routine CI-action bumps (actions/checkout,actions/cache,goreleaser-action). - Open Dependabot, not mergeable, runtime/prod dep → leave. Shipped deps, Go modules, security bumps (
golang.org/x/*,through2,undici) are a real call. - Non-PR:
Release→ done;RepositoryAdvisory→ leave (security).
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.
- 1mo ago First seen · 68 lines · 50 tokens per session scan A 50df19ff6d48
github-triage is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,181 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
update-pr
Update an existing pull request with new changes. Use when the user wants to update a PR, push follow-up changes to a PR, refresh a PR description, or sync a PR with latest commits. Triggers on: update pr, update-pr, update the pr, push to pr, refresh pr, sync pr, update pull request.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — no skill executes…
merge-prep
Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep.
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.
pr-comment
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).
update
Safe cc10x upgrade through the Claude Code plugin CLI. Lists every installed scope, refreshes the marketplace, updates each scope, and optionally carries local patches over to the new install. Use this skill when: updating cc10x, upgrading, pulling latest cc10x, syncing plugin, refreshing cache, or checking for new…