Borrowing it
Nothing to install: this file belongs to sageox/ox. 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/sageox/ox/main/.claude/skills/monitor-pr/SKILL.mdgit clone --depth 1 https://github.com/sageox/oxWrote 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/sageox/ox/monitor-pr)<a href="https://agentmods.dev/skills/sageox/ox/monitor-pr"><img src="https://agentmods.dev/badge/skills/sageox/ox/monitor-pr/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/sageox/ox/monitor-pr"><img src="https://agentmods.dev/badge/skills/sageox/ox/monitor-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.02579 |
| Opus 5.5 | $0.00048 | $0.01032 |
| Sonnet 5.5 | $0.00024 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
monitor-pr 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
monitor-pr
Drives a pull request to green by streaming its state through the
Monitor tool and reacting the moment a check fails or a new review
comment lands. Designed for CodeRabbit-reviewed PRs but works for human
reviewers too.
Architecture: use the Monitor tool, not a sleep loop
This is load-bearing — do not substitute a Bash sleep loop. A loop
in a single Bash call blocks the agent until it exits, so the agent
can't react to events concurrently and misses interleaved work.
Monitor streams each stdout line as a notification into the
conversation, so the agent keeps full agency between events.
Start exactly one monitor at the top of the task with:
persistent: true— PR reviews can take hours; don't let a timeout kill the watch mid-review.description— specific, e.g."PR #493 state changes", because it appears in every notification.- The polling script below as
command.
Stop the monitor with TaskStop only when the exit condition is met or
the user cancels.
The polling script
Resolve PR metadata first (once, before starting the monitor):
gh pr view --json number,url,headRepository,headRepositoryOwner,baseRepository
Then start the Monitor with this command (substitute PR, OWNER,
REPO). It emits one line only when state changes — a quiet PR
produces zero events, an eventful PR produces one event per transition.
PR=<number>; OWNER=<owner>; REPO=<repo>
last=""
while true; do
checks=$(gh pr checks "$PR" --json bucket 2>/dev/null || echo '[]')
failing=$(jq '[.[] | select(.bucket=="fail" or .bucket=="cancel")] | length' <<<"$checks")
pending=$(jq '[.[] | select(.bucket=="pending")] | length' <<<"$checks")
unresolved=$(gh api graphql --paginate -f query='
query($o:String!,$r:String!,$n:Int!,$endCursor:String){
repository(owner:$o,name:$r){
pullRequest(number:$n){
reviewThreads(first:100, after:$endCursor){
nodes{ isResolved }
pageInfo{ hasNextPage endCursor }
}
}
}
}' -f o="$OWNER" -f r="$REPO" -F n="$PR" 2>/dev/null \
| jq -s '[.[].data.repository.pullRequest.reviewThreads.nodes[]
| select(.isResolved==false)] | length')
state="fail=${failing:-?} pending=${pending:-?} unresolved=${unresolved:-?}"
if [ "$state" != "$last" ]; then
if [ "$failing" = "0" ] && [ "$pending" = "0" ] && [ "$unresolved" = "0" ]; then
echo "clean: all checks pass, none pending, zero unresolved threads"
else
echo "change: $state — triage needed"
fi
last="$state"
fi
sleep 60 || exit 0
done
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 Changed · +33 lines 9d5e3c14682d
- 1mo ago First seen · 231 lines · 120 tokens per session scan A bcba72ddc777
monitor-pr is a skill published in the GitHub repository sageox/ox (65 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 2,579 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
intuitive-port-worktree
Port commits or patches between worktrees when explicitly requested; preserve the target branch and unrelated edits.
intuitive-squash
Safely rewrite noisy local history into reviewable commits, with aggressive or moderate plan choices, when the user explicitly asks to squash.
intuitive-tests
Audit or improve test-suite structure and signal when the user asks about redundancy, pruning, layout, fixtures, or parameterization.
exploit-xss
Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site scripting, script injection, or needs to test JavaScript injection in parameters, forms, headers, or DOM sources.
chinese-git-workflow
A Git workflow guide tailored to Chinese-hosted platforms such as Gitee, Coding.net, and GitLab, including their code-review and build systems.
chinese-commit-conventions
A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.