codex-review

A review workflow that sends the latest project plan to Codex, an AI coding assistant, for an independent check. After explicit approval, it adds a marker that allows the session to finish.

In plain words
What is it for?
Use it in projects where a stop hook must check and approve the newest plan before the agent can end its work.
Why use it?
It prevents a project session from ending before its latest plan has passed the required review.

Skill for Claude CodeCodex

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 skills/barkaaa/codex-gate/codex-review
Any agent
npx skills add barkaaa/codex-gate --skill codex-review
Clone the repo
git clone --depth 1 https://github.com/barkaaa/codex-gate

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,742 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 $0.00079 $0.01742
Opus 5 $0.00039 $0.00871
Sonnet 5 $0.00016 $0.00348
Haiku 4.5 $0.00008 $0.00174

Measured 2d ago against content hash ce10599e647f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-review 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 2d 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.

.claude/skills/codex-review/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-review

Codex is a real, independent reviewer reached via the codex CLI. Do not fake this — actually run the commands below and read Codex's real output.

Plan directory

The plan directory is configurable per project via the CODEX_REVIEW_PLAN_DIR env var set in this project's .claude/settings.json Stop hook command (defaults to plans if unset — check that file to confirm the actual value for this project). All references to "the plan directory" below mean that directory, not necessarily a literal plans/.

Codex CLI facts (probed 2026-06-30, codex-cli 0.140.0)

  • Non-interactive entrypoint: codex exec. Without a subcommand it reads the prompt from the argument (or stdin if - / no arg given).
  • Always redirect stdin from /dev/null when scripting this — even with a prompt argument, codex still tries to read stdin and will hang forever if stdin is left attached to a pipe/terminal that never closes.
  • Always pass --skip-git-repo-check if the plan's directory isn't guaranteed to be a git repo.
  • -C <dir> sets the working root codex operates in — use the current project root ($CLAUDE_PROJECT_DIR), not the script's own directory.
  • --json streams JSONL events to stdout. The first line is {"type":"thread.started","thread_id":"<uuid>"}this uuid is the session id to save for resume.
  • -o <file> writes just the final agent message (clean text, no JSON) to <file>. Prefer this over parsing the JSONL stream for the "what did Codex actually say" content.
  • To continue the same session: codex exec resume <thread_id> -o <file> --json "<prompt>" < /dev/null. Verified: token usage grows across calls and Codex correctly recalls prior-turn content, so this is genuine context reuse, not a fresh thread.
  • codex exec resume does not accept -C — only the initial codex exec call takes -C <dir>. Passing -C to resume fails with error: unexpected argument '-C' found (exit code 2). The resumed thread already runs in whatever directory the session started in.

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 79 tokens per session scan A ce10599e647f

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository barkaaa/codex-gate (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 1,742 once invoked, about $0.0004 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 skills, from other repositories

decision-ledger

Maintain an append-only decision ledger (DECISIONS.md). Use when the user confirms a decision, reverses or changes a past decision, asks what was decided and why, or at session start to load standing decisions.

svy04/ballast · 48 tokens

webmcp-setup

Bootstraps webmcp-react into an existing React or Next.js app. Installs dependencies, adds WebMCPProvider, creates a first tool, and configures the MCP client bridge. Use when the user wants to set up WebMCP, add MCP tools to their app, integrate webmcp-react, or make their React app accessible to AI agents.

agentcathq/webmcp-react · 80 tokens

goal

Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.

svy04/ballast · 69 tokens

skill-forge

Promote a procedure that was worked out end-to-end and verified into a reusable skill file, so the next similar task starts from the solved path. Use when a hard-won procedure succeeds with evidence, when the same multi-step task appears a second time, or when the user says "make this repeatable".

svy04/ballast · 67 tokens

report

Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.

svy04/ballast · 49 tokens

config-manager

Skill that manages configuration.

ryo-ebata/cc-audit · 7 tokens