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.
git clone --depth 1 https://github.com/jcputney/agent-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/commands/jcputney/agent-peer-review/codex-peer-review)<a href="https://agentmods.dev/commands/jcputney/agent-peer-review/codex-peer-review"><img src="https://agentmods.dev/badge/commands/jcputney/agent-peer-review/codex-peer-review.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 | $0.00048 | $0.01454 |
| Opus 5 | $0.00024 | $0.00727 |
| Sonnet 5 | $0.00010 | $0.00291 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade B, and why
codex-peer-review 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 7d 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.
cat > ~/.codex/peer-review.config.toml <<'EOF' How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Peer Review Command
You have been explicitly asked to run peer review validation using OpenAI Codex CLI.
Parse Arguments
/codex-peer-review → ask for scope, run blind-debate (default)
/codex-peer-review --base <branch> → blind-debate vs branch
/codex-peer-review --uncommitted → blind-debate of staged/unstaged/untracked
/codex-peer-review --commit <SHA> → blind-debate of one commit
/codex-peer-review --mode classic [...] → legacy single-pass validation (deprecated)
/codex-peer-review --mode blind-debate [...] → explicit default
/codex-peer-review init → write peer-review profile files to ~/.codex/
/codex-peer-review <question> → blind-debate of an answer to a broad question
Modes:
blind-debate(default): symmetric blind pass + per-issue debate. Best signal. See thecodex-peer-reviewskill for full protocol.classic(deprecated): old behavior — Claude proposes, Codex validates, max 2 rounds. Cheaper but weaker. Will be removed in a future version. When this mode is invoked, warn the user once.
init subcommand
Codex CLI uses profile-v2 files: --profile <name> layers ~/.codex/<name>.config.toml on top of the base ~/.codex/config.toml. Profiles are NOT [profiles.*] tables inside config.toml (that was the pre-0.12 scheme). The plugin writes one standalone file per profile and never edits config.toml — that file holds unrelated user settings.
If the user runs /codex-peer-review init, do not dispatch the agent. Instead:
-
Check if the profile files already exist:
if [ -f ~/.codex/peer-review.config.toml ] && [ -f ~/.codex/peer-review-summarizer.config.toml ]; then echo "Profile files already exist. Nothing to do." exit 0 fi -
Write the profile files:
mkdir -p ~/.codex cat > ~/.codex/peer-review.config.toml <<'EOF' model = "gpt-5.4" model_reasoning_effort = "high" EOF cat > ~/.codex/peer-review-summarizer.config.toml <<'EOF' model = "gpt-5.4-mini" model_reasoning_effort = "low" EOF
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.
- 7d ago First seen · 146 lines · 48 tokens per session scan B d7e9ab170f9c
codex-peer-review is a command published in the GitHub repository jcputney/agent-peer-review (33 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,454 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.