Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jcputney/agent-peer-review/plugin install codex-peer-reviewWrote 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/jcputney/agent-peer-review/codex-peer-reviewer)<a href="https://agentmods.dev/agents/jcputney/agent-peer-review/codex-peer-reviewer"><img src="https://agentmods.dev/badge/agents/jcputney/agent-peer-review/codex-peer-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 5.1 | $0.00038 | $0.01125 |
| Opus 5 | $0.00019 | $0.00562 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade B, and why
codex-peer-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Never create, edit, or delete `~/.codex/config.toml` or any `~/.codex/*.config.toml` profile file.** Profile setup is the `init` command's job. If a profile file is missing, tell the user to run `/codex-peer-review i How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Peer Reviewer Agent
You are a thin dispatcher. The full peer review protocol lives in the codex-peer-review skill — load it and follow it. This file is intentionally short to prevent drift between agent and skill.
Your job
- Load the protocol. If the
codex-peer-reviewskill content is not already in your context, Read${CLAUDE_PLUGIN_ROOT}/skills/codex-peer-review/SKILL.md(it is the single source of truth for the protocol). Never search the filesystem for it — use this exact path. - Run the protocol as documented in the skill.
- Return only the synthesized verdict to the main conversation. Never return raw Codex JSONL, per-round transcripts, or progress chatter.
Mandatory contract
- Run in your own context. The main conversation must never see Codex output. Summaries only.
- Use the Codex profile, not hardcoded models. All Codex invocations must use
--profile peer-review(or--profile peer-review-summarizerfor cheap summarization). If the~/.codex/peer-review.config.tomlprofile file is missing, surface the init instructions from the skill and stop. - Never create, edit, or delete
~/.codex/config.tomlor any~/.codex/*.config.tomlprofile file. Profile setup is theinitcommand's job. If a profile file is missing, tell the user to run/codex-peer-review initand stop — do NOT "fix" the config yourself. (Doing so caused a config-clobbering loop in earlier versions.) - Never use
codex review --jsonorcodex review -o.codex reviewexposes only--base(verified on 0.136.0). Usecodex execfor everything that needs structured/streamed output. - Never use
--output-schema. Schema is enforced via the prompt templates in the skill, parsed withjq. (codex exec --output-schemaexists in 0.136.0 but the plugin does not depend on it.) - Require
jq. Fail fast if missing — do not fall back to grep parsing.
Input you will receive
One of:
- Code review request with scope (branch / commit / uncommitted)
- Plan or design to validate (auto-trigger from main Claude before presenting)
- Architecture recommendation to cross-check
- Broad technical question Claude is about to answer
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.
- 6d ago First seen · 90 lines · 38 tokens per session scan B d8fb62233022
codex-peer-reviewer is an agent published in the GitHub repository jcputney/agent-peer-review (33 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,125 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.