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 kellykampen/agent-skills --skill cmux-pr-qc-agentgit clone --depth 1 https://github.com/kellykampen/agent-skillsWrote 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/kellykampen/agent-skills/cmux-pr-qc-agent)<a href="https://agentmods.dev/skills/kellykampen/agent-skills/cmux-pr-qc-agent"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/cmux-pr-qc-agent/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/kellykampen/agent-skills/cmux-pr-qc-agent"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/cmux-pr-qc-agent.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 | $0.00187 | $0.02735 |
| Opus 5 | $0.00093 | $0.01367 |
| Sonnet 5 | $0.00037 | $0.00547 |
| Haiku 4.5 | $0.00019 | $0.00274 |
Grade A, and why
cmux-pr-qc-agent 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR QC Bot
What this is
A delegated, long-running PR shepherd. The orchestrator (you) spawns a separate Claude Code instance in its own cmux pane and hands it one PR. That instance — the bot — owns the PR: it watches for review comments and CI results, fixes what's needed (tests first), replies to each comment, and keeps looping until the PR is green and every thread is answered, then reports back.
Why a separate instance rather than doing it inline: a PR review cycle is bursty and slow — CodeRabbit and humans drop comments minutes or hours apart, CI takes a while, and each round is mechanical. Tying up your main session to poll a PR is wasteful; a dedicated instance can sit on it, react as things arrive, and ping you only when it's done or genuinely stuck. It's also cleanly independent — a fresh agent re-reads each comment without your authoring bias.
This skill pairs with linear-ac-verification
(verify acceptance criteria) — same delegation pattern, different target.
Don't reinvent the cmux plumbing
This machine has the cmux skill suite. Invoke the installed cmux-workspace
skill for everything about creating the pane and talking to the bot — reading
the caller context ($CMUX_WORKSPACE_ID / $CMUX_SURFACE_ID), cmux new-pane … --focus false, the two-step cmux send + cmux send-key … enter, reading the
pane back, and its non-interfering focus rules. Use cmux for topology/surface
discovery. Don't hardcode socket paths or surface IDs. This skill only adds the
PR-watching layer on top.
Spawning the bot
Via cmux-workspace: capture your own surface ($CMUX_SURFACE_ID — the bot
reports back here), create a helper pane to the right with --focus false so
your focus is undisturbed, and start Claude Code in it (ccc by convention; fall
back to claude if ccc isn't on PATH — check with command -v ccc). Wait for
the prompt, then send the brief (text, then Enter as a separate send-key, since
an agent stages input until Enter arrives). The brief tells the bot to run this
skill on the PR — you don't decompose the work yourself; the bot does.
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 · 186 lines · 187 tokens per session scan A 5832787a6878
cmux-pr-qc-agent is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 2,735 once invoked, about $0.0009 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 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.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.