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 antropos17/Aegis --skill pr-monitorgit clone --depth 1 https://github.com/antropos17/AegisWrote 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/antropos17/aegis/pr-monitor)<a href="https://agentmods.dev/skills/antropos17/aegis/pr-monitor"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/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/antropos17/aegis/pr-monitor"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/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 | $0.00025 | $0.00435 |
| Opus 5.5 | $0.00010 | $0.00174 |
| Sonnet 5.5 | $0.00005 | $0.00087 |
| Haiku 4.5 | $0.00003 | $0.00044 |
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 today.
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
Review and monitor AEGIS PRs
Resolve the repository from the supplied PR or configured remote. Use explicit PR numbers and record the head revision so concurrent pushes cannot be mistaken for the reviewed change.
gh pr list --repo <owner/repo> --state open
gh pr view <number> --repo <owner/repo> --json title,author,body,files,additions,deletions,headRefOid,url
gh pr diff <number> --repo <owner/repo> --name-only
gh pr diff <number> --repo <owner/repo>
gh pr checks <number> --repo <owner/repo>
gh pr diff has no --stat flag. Use the files/additions/deletions fields for scope and the patch for review. Use ci-monitor to interpret unfinished checks and bind results to the current revision.
Review changed behavior, contracts and evidence:
- Main-process changes preserve CommonJS, platform boundaries and stamped identity.
- Renderer changes follow the actual Vite entrypoint and Svelte conventions; consider frontend/observatory/ as well as src/renderer/.
- Rule changes match the applicable schema and runtime consumer.
- Dependency changes are assessed using the relevant manifest/lockfile diff and audit scope; npm audit is not a per-package command.
- Run tests relevant to the changed behavior, including when the PR changes implementation without changing a test file.
A file exceeding 300 lines is context for maintainability, not an automatic defect. Do not reject a change solely by file length or changed-line count.
Report the PR/revision, scope, actual check state and actionable findings. Recommendation text is not a posted review or a merge. Reading/reviewing a PR does not authorize publishing comments, labels or review decisions to other people. Follow the session's explicit authorization for such actions.
For requested recurring monitoring, use the current host's scheduler and notify on meaningful changes; a one-time review does not set up /loop or an automation.
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.
- today First seen · 30 lines · 25 tokens per session scan A 9256c5937d81
pr-monitor is a skill published in the GitHub repository antropos17/Aegis (157 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 435 once invoked, about $0.0001 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 2026-10-17.
Other skills, from other repositories
update-pr
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
repo-conventions
Use before committing, pushing, or opening a PR in ANY repo. Universal pre-push checklist plus how to discover each repo's own conventions (AGENTS.md/CLAUDE.md/CONTRIBUTING.md/.claude/skills) — repo-specific rules are NOT encoded here, they live in the repo itself.
open-code-review
Use Alibaba Open Code Review (ocr) to review git diffs, staged changes, branches, or scan a workspace, then summarize findings and optionally fix high-confidence issues.
Release Readiness
Review a change against release gates, rollback safety, validation evidence, and operational risk.
github-pr-workflow
Pull request lifecycle: create, review, merge, manage (gh CLI).
github-code-review
Review PRs: diffs, inline comments via gh or REST.