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 paulinevos/claude-stuff --skill triage-review-queuegit clone --depth 1 https://github.com/paulinevos/claude-stuffWrote 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/paulinevos/claude-stuff/triage-review-queue)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/triage-review-queue"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/triage-review-queue/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/paulinevos/claude-stuff/triage-review-queue"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/triage-review-queue.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 | $0.00073 | $0.00627 |
| Opus 5.5 | $0.00029 | $0.00251 |
| Sonnet 5.5 | $0.00015 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
triage-review-queue 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 11d 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.
What it actually says
triage-review-queue
You triage and dispatch; the reviewer agent reads the code. It reviews in the project's own Solo project so it inherits that project's environment, tooling and guidelines. Read projects for the config format and how to fill a gap in it.
-
List what is waiting. Skip drafts unless asked;
@meresolves to the authenticatedghaccount.gh search prs --review-requested=@me --state=open --sort=updated \ --json repository,number,title,url,author,isDraft --limit 50Report "nothing waiting" and stop when the list is empty.
-
Classify each PR against
~/.claude/pr-reviewer/projects.json, matching onrepo(owner/name). Resolve an unmapped repo before dispatching it — never review from a guessed path. Show the triage table — PR, title, author, project, and any unmapped repos — and let the user choose which to review before spawning anything. Dispatch only what they pick. -
Dispatch one reviewer per chosen PR, into that PR's Solo project:
spawn_agent(agent_tool_id=<Claude>, project_id=<solo_project_id>, name="review-<repo-name>-<number>") send_input(process_id=<returned>, input=<briefing>)Resolve
agent_tool_idfromlist_agent_tools(tool_typeclaudeunless the project's config names another). Prepend the returnedagent_instructionsto the briefing verbatim — they carry the orchestration context the agent needs to report back. -
Brief each reviewer with: its PR URL and number, the repo, the checkout path, the guideline files named in the config, the
review-pull-requestskill to follow, and the scratchpad name to write findings to (review-<repo-name>-<number>). One PR per agent; never two PRs in one agent, and never a second agent on the same PR. -
Monitor with
get_process_statusandget_process_output; do not send further input unless a reviewer asks a question or stalls. When a reviewer reports done, read its scratchpad and hand the findings tocollect-review-findings. Close each reviewer's process once its findings are collected.
Reviewers never post to GitHub and never push — they plan comments only.
Posting is a separate, approved step (collect-review-findings).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 52 lines · 73 tokens per session scan A d3b900bef055
triage-review-queue is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 627 once invoked, about $0.0003 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 2026-10-06.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.