codexa-review

codexa-review is a command for coding agents from mirnoorata/codexa. It costs 12 tokens per session (353 once invoked), scanned A, original, MIT.

A command that reviews current uncommitted changes against a previously saved change plan.

In plain words
What is it for?
Use it after edits to report missing verification, record tests or commands you ran, review invariants, and inspect specific files or symbols.
Why use it?
It identifies tests not yet accounted for, changes that drifted from the plan, and gaps in the review evidence.

Command

Part of the codexa plugin — 6 commands, 3 hooks, 1 MCP server 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 commands/mirnoorata/codexa/codexa-review
Clone the repo
git clone --depth 1 https://github.com/mirnoorata/codexa

Or install codexa, the plugin that ships this one along with the rest of its 6 commands, 3 hooks, 1 MCP server.

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 codexa-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/mirnoorata/codexa/codexa-review.svg)](https://agentmods.dev/commands/mirnoorata/codexa/codexa-review)
Your own site
<a href="https://agentmods.dev/commands/mirnoorata/codexa/codexa-review"><img src="https://agentmods.dev/badge/commands/mirnoorata/codexa/codexa-review.svg" alt="Measured on agentmods" height="20"></a>
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 353 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 $0.00012 $0.00353
Opus 5 $0.00006 $0.00177
Sonnet 5 $0.00002 $0.00071
Haiku 4.5 $0.00001 $0.00035

Measured 3d ago against content hash 965144508e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexa-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 3d 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.

integrations/claude-code/commands/codexa-review.md · 25 lines

What it actually says

Compare the current dirty tree against the saved Codexa change-plan snapshot. Reports tests still unaccounted for, drift signals, and known gaps. Saved planned tests now carry provenance; legacy, stale, or scope-mismatched snapshot tests are reported as degraded instead of silently trusted. Passing structured command reports lets Codexa account for verification and persist compact local outcomes for future visible ranking/test boosts.

Allowlisted flags (others are rejected): --change-type, --ran-test, --ran-command, --ran-command-report, --waive-check, --waiver, --invariant-review, --artifact-id, --file, --symbol, --budget, --limit, --snippets, --no-snippets, --auto-refresh, --no-auto-refresh, --task-id.

Common use:

/codexa-review --change-type style
/codexa-review --change-type behavior --ran-test tests/test_queue.py --ran-command "pytest tests/"
/codexa-review --task-id queue-safety --invariant-review '{"invariantId":"inv-...","status":"satisfied","evidence":["reviewed final diff"]}' --artifact-id va_...

!bash "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/review.sh" "$ARGUMENTS"

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. 3d ago First seen · 25 lines · 12 tokens per session scan A 965144508e79

Subscribe to this mod's changes

codexa-review is a command published in the GitHub repository mirnoorata/codexa (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 353 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.