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 Smirnov-Labs/claude-skills --skill reading-bot-pr-reviewsgit clone --depth 1 https://github.com/Smirnov-Labs/claude-skillsWrote 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/smirnov-labs/claude-skills/reading-bot-pr-reviews)<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/reading-bot-pr-reviews"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/reading-bot-pr-reviews/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/smirnov-labs/claude-skills/reading-bot-pr-reviews"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/reading-bot-pr-reviews.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 | $0.00114 | $0.01825 |
| Opus 5 | $0.00057 | $0.00912 |
| Sonnet 5 | $0.00023 | $0.00365 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
reading-bot-pr-reviews 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 12d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Bot PR Reviews
Overview
Two automated reviewers post PR feedback through channels the default gh query misses. Codex (chatgpt-codex-connector[bot]) posts to three endpoints; an Architecture-Review action posts a System Architecture Review (SAR) as a fourth. This skill fetches all four streams, filters on exact bot logins, classifies findings by severity, and reports a merge verdict.
Read-only. It reads and reports. It never commits or pushes — for an autonomous fix loop use /pr-fix.
Core principle: gh pr view --json comments misses both bots. A clean Codex verdict AND the SAR both live in issue comments, not inline. Filtering author logins by substring (codex, architect) misses both — the SAR posts as the generic github-actions[bot]. Use exact [bot] logins.
When to Use
- "What did the bots say on PR #N?" — before merging, or before declaring a PR done
- A Codex finding or a clean "no issues" verdict seems missing (the inline endpoint is empty)
- Confirming both reviewers passed before merge
Not for: auto-committing fixes to PR feedback (→ /pr-fix); sending a plan to Codex for review (→ codex-plan-review, the reverse direction).
The Four Streams
| # | Stream | Endpoint | Filter login | What lives here |
|---|---|---|---|---|
| 1 | Codex inline findings | pulls/<PR>/comments |
chatgpt-codex-connector[bot] |
Per-line findings with P1/P2/P3 severity badges |
| 2 | Codex formal review | pulls/<PR>/reviews |
chatgpt-codex-connector[bot] |
Top-level summary + review state (e.g. CHANGES_REQUESTED) |
| 3 | Codex run summary | issues/<PR>/comments |
chatgpt-codex-connector[bot] |
Clean "Didn't find any major issues" verdict lives ONLY here |
| 4 | Architecture SAR | issues/<PR>/comments |
github-actions[bot] |
System Architecture Review — severity rating + blocker list |
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.
- 12d ago First seen · 122 lines · 114 tokens per session scan A c88f2518bcea
reading-bot-pr-reviews is a skill published in the GitHub repository Smirnov-Labs/claude-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 1,825 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…