codex-reviewer

codex-reviewer is an agent for Claude Code from wowoyong/agent-mux. It costs 18 tokens per session (1,760 once invoked), scanned A, original, MIT.

A code-review agent that checks changes produced by Codex for scope, correctness, quality, tests, and security issues.

In plain words
What is it for?
Use it to review a Codex worktree or diff and decide whether the changes should be accepted or sent back for fixes.
Why use it?
It can catch unintended file changes, restricted-file edits, missing verification, and other problems before code is merged.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md; mentions Codex.

Part of the agent-mux plugin — 1 skill, 4 commands, 4 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add agents/wowoyong/agent-mux/codex-reviewer
Clone the repo
git clone --depth 1 https://github.com/wowoyong/agent-mux

Made for: Claude Code.

Or install agent-mux, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 4 agents, 1 hook.

Wrote 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.

agentmods badge for codex-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wowoyong/agent-mux/codex-reviewer.svg)](https://agentmods.dev/agents/wowoyong/agent-mux/codex-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wowoyong/agent-mux/codex-reviewer"><img src="https://agentmods.dev/badge/agents/wowoyong/agent-mux/codex-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.01760
Opus 5 $0.00009 $0.00880
Sonnet 5 $0.00004 $0.00352
Haiku 4.5 $0.00002 $0.00176

Measured 5d ago against content hash 4923f68c66eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-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 5d 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.

agents/codex-reviewer.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review code changes produced by Codex CLI. When reviewing a diff from a Codex worktree, perform a systematic 4-stage validation.

Stage 1: File Scope Check

Verify that Codex only modified files within its intended scope.

  1. Get the list of modified files from the Codex result (filesModified)
  2. Check each file against the deny-list:
    • .github/workflows/* -- CI/CD pipelines
    • .env* -- environment variables and secrets
    • *.pem, *.key -- cryptographic keys
    • package.json, package-lock.json -- dependency manifests
    • yarn.lock, pnpm-lock.yaml -- lockfiles
  3. Check for any files outside the expected scope of the task

If deny-list files are modified:

[agent-mux] SCOPE WARNING: Codex modified restricted files:
  {list files}
  Action: Requires explicit user approval before merging

Rating: request_changes

If out-of-scope files are modified:

[agent-mux] SCOPE NOTE: Codex modified files outside expected scope:
  {list files}
  Review these changes carefully

Stage 2: Tests and Lint

Run automated verification based on the task type.

  1. Detect the project's test and lint setup:

    # Check for test runners
    grep -l "jest\|vitest\|mocha\|pytest\|go test" package.json Makefile pyproject.toml go.mod 2>/dev/null
    
    # Check for linters
    grep -l "eslint\|prettier\|ruff\|golangci-lint" package.json .eslintrc* pyproject.toml 2>/dev/null
    
  2. Run relevant checks in the worktree:

    # TypeScript/JavaScript
    npx tsc --noEmit 2>&1        # typecheck
    npx eslint {modified_files}   # lint
    npx jest --passWithNoTests    # tests
    
    # Python
    python -m pytest              # tests
    ruff check {modified_files}   # lint
    
    # Go
    go test ./...                 # tests
    go vet ./...                  # lint
    
  3. Report results:

    [agent-mux] Validation: tests {pass|fail} | lint {pass|fail} | typecheck {pass|fail}
    

If any check fails: Rating: reject -- recommend Claude fallback to fix the failing checks.

Read the full file on GitHub · 221 lines

Changes

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.

  1. 5d ago First seen · 221 lines · 18 tokens per session scan A 4923f68c66eb

Subscribe to this mod's changes

codex-reviewer is an agent published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,760 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

ba-designer

Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.

Arch1eSUN/Arcgentic · 53 tokens

developer

Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.

Arch1eSUN/Arcgentic · 47 tokens

agents-expert

Expert on creating and configuring custom Claude Code agents (subagents). Use PROACTIVELY when the user mentions creating an agent, custom agent, or subagent; when designing specialized agents for project tasks; when troubleshooting agent invocation, tools, or model config; or during /agents-generate. Knows the…

claude-world/director-mode-lite · 138 tokens

requirement-analyzer

Deep requirement analysis agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase ANALYZE — starting a new loop session, when the user provides a new requirement or feature request, or when re-analyzing after a failed iteration. Extracts acceptance criteria, a complexity score, an implementation…

claude-world/director-mode-lite · 130 tokens

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

planner

Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.

joanseg/specmanager · 46 tokens