Borrowing it
Nothing to install: this file belongs to cardstack/boxel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cardstack/boxel/main/.claude/skills/pr-monitor/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/pr-monitor)<a href="https://agentmods.dev/skills/cardstack/boxel/pr-monitor"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-monitor/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/cardstack/boxel/pr-monitor"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-monitor.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 | $0.00097 | $0.03910 |
| Opus 5.5 | $0.00039 | $0.01564 |
| Sonnet 5.5 | $0.00019 | $0.00782 |
| Haiku 4.5 | $0.00010 | $0.00391 |
Grade A, and why
pr-monitor 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 5d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Monitor
After a PR is opened, arm a persistent Monitor that polls GitHub and emits one event per new review comment, per CI check turning red, and each time the PR gains or loses a merge conflict with its base. Each emitted line becomes a notification, so the agent can react to feedback, failures and conflicts as they land rather than waiting for the whole CI run or for someone to notice the PR can't merge.
gh pr create is not the end of that thread of work — the end state is "PR filed AND monitor armed." Arm it as the next step after opening the PR.
Pick a form — and read this first
Two kinds of behavior are bundled in the full form: (a) keeping the PR mergeable — reacting to CI failures and to merge conflicts — and (b) drafting replies to human reviewers' comments. Behavior (b) is the judgment call. The replies are posted through the PR author's GitHub account, but each one begins with the [Claude Code 🤖] prefix (see the pr-comment-attribution skill), so reviewers can see at a glance that the agent wrote it — not the author. The concern is therefore social, not mistaken identity: a teammate may simply not want an agent taking a first pass at reviewers' feedback before they've engaged with it themselves. Respect that.
- Full form — watches review comments + reviews + CI + merge conflicts, and the agent drafts a per-thread reply to each (prefixed per the
pr-comment-attributionskill so reviewers know it's the agent). Use when the PR author is comfortable with the agent taking a first pass at review feedback. - Reduced form — watches only CI checks turning red and merge conflicts; review comments are left entirely to the human author. Use this when anyone is uncomfortable with the agent replying on their behalf. It still gives you the tight fix-CI-fast loop, and keeps the branch mergeable, without touching the social surface.
When in doubt, default to the reduced form and let the author opt up.
Reduced form (CI + conflicts)
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.
- 5d ago First seen · 180 lines · 97 tokens per session scan A c41d4c940106
pr-monitor is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 3,910 once invoked, about $0.0004 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 2026-10-21.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
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.
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.
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…