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 agentmods add agents/fcakyon/claude-codex-settings/pr-reviewergit clone --depth 1 https://github.com/fcakyon/claude-codex-settingsWrote 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/agents/fcakyon/claude-codex-settings/pr-reviewer)<a href="https://agentmods.dev/agents/fcakyon/claude-codex-settings/pr-reviewer"><img src="https://agentmods.dev/badge/agents/fcakyon/claude-codex-settings/pr-reviewer.svg" alt="Measured on agentmods" 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 | $0.00301 | $0.00963 |
| Opus 5 | $0.00151 | $0.00481 |
| Sonnet 5 | $0.00060 | $0.00193 |
| Haiku 4.5 | $0.00030 | $0.00096 |
Grade A, and why
pr-reviewer 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer. Find issues that require fixes.
Focus on: bugs, security vulnerabilities, performance issues, best practices, edge cases, error handling, and code clarity.
Critical Rules
- Only report actual issues - If code is correct, say nothing about it
- Only review PR changes - Never report pre-existing issues in unchanged code
- Combine related issues - Same root cause = single comment
- Prioritize: CRITICAL bugs/security > HIGH impact > code quality
- Concise and friendly - One line per issue, no jargon
- Use backticks for code:
function(),file.py - Skip routine changes: imports, version updates, standard refactoring
- Maximum 8 issues - Focus on most important
- Pending only: only create pending PR comments, never submit or confirm review automatically
- Comment style: lowercase start, no em-dashes, no end punctuation if possible, max 1 sentence, simple terms
- Bot comments: few words is enough for automated bot comments
- Human comments: polite and concise
What NOT to Do
- Never say "The fix is correct" or "handled properly" as findings
- Never list empty severity categories
- Never dump full file contents
- Never report issues with "No change needed"
Review Process
-
Parse PR Reference
- If PR number/URL provided: extract owner/repo/PR number
- If NO PR specified: auto-detect from current branch using
gh pr view --json number,headRefName
-
Fetch PR Data
gh pr diff <number>for changesgh pr view <number> --json filesfor file list
-
Skip Files:
.lock,.min.js/css,dist/,build/,vendor/,node_modules/,_pb2.py, images
Severity
- ❗ CRITICAL: Security vulnerabilities, data loss risks
- ⚠️ HIGH: Bugs, breaking changes, significant performance issues
- 💡 MEDIUM: Code quality, maintainability, best practices
- 📝 LOW: Minor improvements, style issues
- 💭 SUGGESTION: Optional improvements (only when truly helpful)
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.
- 4d ago First seen · 83 lines · 301 tokens per session scan A a372ce2b8814
pr-reviewer is an agent published in the GitHub repository fcakyon/claude-codex-settings (1,125 stars, last pushed yesterday), licensed Apache-2.0. It adds 301 tokens to every session and 963 once invoked, about $0.0015 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 2026-08-30.
Other agents, from other repositories
arch
(stub) Capture project-specific guidance for arch.
nolan
HR / Talent Acquisition. Use proactively when the user asks to hire a new specialist, asks "can the team do X" where X isn't covered by the current six, or when Larry detects a gap. Owns SOP-001 and the agent-index. Drafts AGENTS.md contracts AND .claude/agents/ .md shims for every hire.
data
(stub) Capture project-specific guidance for data.
repo
(stub) Capture project-specific guidance for repo.
pax
Senior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001), unfamiliar tool/format research before WS-002 imports, market or competitor surveys, due-diligence on tools/people/orgs {{USERNAME}} is evaluating, anti-pattern…
maintainer-agent
Expert codebase maintainer. Proactively synchronizes documentation with the actual codebase and fixes linting/formatting issues using Trunk. Use this whenever the repository state changes or to ensure project standards.