A command that reviews a coding plan and writes a response for each review finding.

Starting or reviewing a plan, choosing a plan or workflow file, and responding to every finding from the review.

It gives a current Claude workflow a structured review and records whether each issue is accepted, rejected, or deferred.

plan — Command by boyand

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 commands/boyand/codex-review/plan

Clone the repo

git clone --depth 1 https://github.com/boyand/codex-review

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 595 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00595
Opus 5	$0.00006	$0.00298
Sonnet 5	$0.00002	$0.00119
Haiku 4.5	$0.00001	$0.00060

Measured 2d ago against content hash 558fe6ff90b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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.

commands/plan.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/codex-review:plan

Run a plan review round immediately. If the current Claude thread has no active workflow, this command creates one.

The user may pass:

focus text
--plan <path> to override the current Claude plan file
--workflow <id> to target a specific workflow

Default plan resolution:

infer the plan file from the current Claude session transcript
snapshot that source once into workflow artifacts/plan.md
after workflow creation, treat artifacts/plan.md as the plan under review; only --plan should replace it
if the plan exists only as inline chat text and not as a file, the engine should fail and Claude should ask for --plan <path> rather than guessing from another plan file

Required behavior

Run the engine:

"${CLAUDE_PLUGIN_ROOT}/.bin/codex-review" plan $ARGUMENTS

Do not pass hidden runtime flags like --session-pid or --session-id; the wrapper injects them automatically.

If the engine reports a review file, read it completely.
Write findings responses automatically to the reported Findings file:

respond to every finding ID
use ACCEPT, REJECT, or DEFER
be concrete, not generic

After writing findings:

run:

"${CLAUDE_PLUGIN_ROOT}/.bin/codex-review" summary

present that summary output as the approval summary for the round
in this same command response only, ask the user inline what they want to do next:
- move to implementation
- run another review round
- stop and keep this review
do not re-offer these choices on unrelated later turns

if the user chooses to move to implementation, run:

"${CLAUDE_PLUGIN_ROOT}/.bin/codex-review" __approve

if the user chooses another review round, run:

"${CLAUDE_PLUGIN_ROOT}/.bin/codex-review" __repeat

if the user chooses to stop and keep this review, run:
```
"${CLAUDE_PLUGIN_ROOT}/.bin/codex-review" __done
```
do not require the user to type separate slash commands for those transitions

Read the full file on GitHub · 66 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.

2d ago First seen · 66 lines · 12 tokens per session scan A 558fe6ff90b6

Subscribe to this mod's changes

plan is a command published in the GitHub repository boyand/codex-review (16 stars, last pushed 16d ago), licensed MIT. It adds 12 tokens to every session and 595 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 2026-08-30.

Code review Planning Productivity

plan

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/codex-review:plan

Required behavior

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement