Borrowing it
Nothing to install: this file belongs to sageox/agent-toolkit. 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/agent-toolkit/main/.agents/skills/monitor-pr/SKILL.mdgit clone --depth 1 https://github.com/sageox/agent-toolkitWrote 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/agent-toolkit/monitor-pr)<a href="https://agentmods.dev/skills/sageox/agent-toolkit/monitor-pr"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/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/agent-toolkit/monitor-pr"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/monitor-pr.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 | $0.00102 | $0.01809 |
| Opus 5 | $0.00051 | $0.00905 |
| Sonnet 5 | $0.00020 | $0.00362 |
| Haiku 4.5 | $0.00010 | $0.00181 |
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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor PR
Own the selected pull request from its current state through a clean review result. Continue monitoring, fixing, testing, committing, pushing, replying, and resolving without an arbitrary iteration limit. Do not merge unless the user explicitly asks.
Read references/github-review-operations.md before the
first GitHub mutation. Use scripts/pr-review-state.sh for every full
review snapshot so inline threads and edited summary comments are never omitted.
Non-negotiable contract
- Keep working while a safe, in-scope action can make progress.
- Evaluate every finding on its merits. Never blanket-dismiss bot comments, nitpicks, or outdated threads.
- Treat an outdated thread as unresolved until its claim has been checked against the current code.
- Preserve unrelated user changes and repository conventions. Never force-push or rewrite history unless explicitly authorized.
- Fail closed: an unreadable or partial GitHub response is unknown state, never a clean result.
- Require only signals configured for this repository or named by the user. Do not require a particular review vendor merely because this skill knows about it.
- Prove every completion condition against the same current remote head SHA.
1. Preflight and create or find the PR
- Read repository instructions. Inspect
git status, the current branch, remotes, and the complete diff from the intended base. For an existing PR, use its actualbaseRefName; otherwise use the user-specified or repository-default branch. - Do not create a PR from its target branch or detached HEAD. Request input only when selecting a safe feature branch would change the user's intent.
- Run the repository's relevant tests and review the full diff. Commit only task-related changes with a repository-conforming message. Leave unrelated changes untouched.
- Verify GitHub authentication, push normally, then find the PR for the branch and create one if absent. Include a concise summary and test evidence.
- Record the PR number, URL, base, branch, and head SHA. Continue on the same PR for every round.
What ships with it
3 files 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.
- yesterday First seen · 146 lines · 102 tokens per session scan A 1a7ea114ede0
monitor-pr is a skill published in the GitHub repository sageox/agent-toolkit (10 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 1,809 once invoked, about $0.0005 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 2026-09-10.
Other skills, from other repositories
pr-review
Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first.
pr-triage
First-touch triage for external pull requests - verdict, label, and a welcoming comment within minutes of open.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.
inbox-triage
Daily GitHub notification inbox triage - surfaces aging vuln PR replies, security advisories, review requests, and mentions that need action.
git-workflow
Git operations: commits, branches, PRs, and conflict resolution.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.