Borrowing it
Nothing to install: this file belongs to cesarnml/son-of-anton. 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/cesarnml/son-of-anton/main/.agents/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/cesarnml/son-of-antonWrote 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/cesarnml/son-of-anton/pr-review)<a href="https://agentmods.dev/skills/cesarnml/son-of-anton/pr-review"><img src="https://agentmods.dev/badge/skills/cesarnml/son-of-anton/pr-review/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/cesarnml/son-of-anton/pr-review"><img src="https://agentmods.dev/badge/skills/cesarnml/son-of-anton/pr-review.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 | $0.00044 | $0.00641 |
| Opus 5.5 | $0.00018 | $0.00256 |
| Sonnet 5.5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
soa-pr-review 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 2mo 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Code Review
Supported external review agents: coderabbit, qodo, greptile, sonarqube. Other vendors are unsupported unless repo policy adds them.
Boundary
The orchestrator owns polling cadence, state transitions, artifact persistence, and auto-recording clean on the final check. After record-review, it also git-commits the updated review JSON artifacts when running in a normal git checkout so the triage file is not left dirty on disk.
This skill owns: fetching review data with gh, detection logic, normalizing comments into structured artifacts, and triage judgment.
Contract:
- fetcher outputs:
detected,agents,reviewed_head_sha,vendors,comments - triager outputs:
outcome(clean|needs_patch|patched),note,action_summary,non_action_summary,vendors
When triager returns needs_patch, follow-up must conclude as patched or operator_input_needed — not stop permanently at needs_patch.
Workflow
- Resolve PR number with
gh pr viewif not provided. - Fetch with
.agents/skills/pr-review/scripts/fetch_pr_review_comments.sh <pr-number>. - If orchestrator already saved
review.fetch.json, use that as the source of truth for vendor attribution and comment shape. - Detection policy: supported vendor identities, explicit vendor wording in comment body, check-run annotations. Human drive-by comments do not count. Preserve head SHA, inline resolution/outdated state, and native thread identity.
- Return fetcher contract when inside
poll-review:detected=false→ keep polling or auto-clean;detected=true→ orchestrator inspects agent state and decides. - Triage each detected comment: actionable, stale, wrong, over-scoped, or out of scope.
- Treat AI review as advisory, not authoritative.
- Push back on stale, over-scoped, unnecessary, or policy-conflicting suggestions.
- When running as triager hook, return the triager contract and let the agent environment decide whether to patch or stop.
- If user approves a patch: apply it, run the smallest relevant verification, commit, push. If the finding came from a native GitHub inline thread still resolvable, mark it resolved.
What ships with it
2 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.
- 2mo ago First seen · 46 lines · 44 tokens per session scan A 939f328c2dd4
soa-pr-review is a skill published in the GitHub repository cesarnml/son-of-anton (2 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 641 once invoked, about $0.0002 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 2026-08-31.
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…