review

review is a command for coding agents from wallneradam/cc-plugin-counterpoint. It costs 18 tokens per session (531 once invoked), scanned A, original, MIT.

A multi-round code review command for the current local Git changes or selected files and folders. It uses Codex to report findings and give an overall verdict.

In plain words
What is it for?
Use it before merging changes, or review specific files, folders, branches, or commits. You can focus the review on areas such as security, tests, performance, or correctness.
Why use it?
It helps find bugs or risks that a quick manual review may miss, while keeping findings across multiple review rounds. It can also distinguish problems introduced by the change from older problems nearby.

Command

Part of the counterpoint plugin — 1 skill, 7 commands, 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/wallneradam/cc-plugin-counterpoint/review
Clone the repo
git clone --depth 1 https://github.com/wallneradam/cc-plugin-counterpoint

Or install counterpoint, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/wallneradam/cc-plugin-counterpoint/review.svg)](https://agentmods.dev/commands/wallneradam/cc-plugin-counterpoint/review)
Your own site
<a href="https://agentmods.dev/commands/wallneradam/cc-plugin-counterpoint/review"><img src="https://agentmods.dev/badge/commands/wallneradam/cc-plugin-counterpoint/review.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 531 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 $0.00018 $0.00531
Opus 5 $0.00009 $0.00266
Sonnet 5 $0.00004 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 3d ago against content hash 086bf95cbb25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

plugin/commands/review.md · 22 lines

What it actually says

Run a Codex code review via the mcp__counterpoint__review MCP tool, following the review protocol in the counterpoint skill.

Argument handling:

  • If $ARGUMENTS contains --scope <value> or --base <ref>, pass them as the scope / base tool parameters.
  • Each --path <file-or-dir> goes into the paths array parameter — path-based review of the listed files/directories as they exist on disk, independent of git state (use this for already-committed code or whole modules). If the user names files or directories to review without flags, treat those as paths too.
  • Any remaining text in $ARGUMENTS is the focus parameter (optional review focus areas).

Protocol (see the counterpoint skill's "Review mode" section for the full rules):

  1. Call mcp__counterpoint__review with the parsed parameters.
  2. Parse the JSON findings from the response. Summarize them in chat — one line per finding (id severity file:line — title), plus the verdict. Mark findings whose origin is pre-existing (a real bug in the surrounding code that predates this change) — Codex reports these as full findings, and they are real bugs, not dismissable because they were already there. The user cannot see the raw MCP result.
  3. Verify each finding against the actual code before accepting it (Read/Grep the cited locations). Classify: real / false positive / uncertain — and say so in chat. A pre-existing finding is verified the same way; being pre-existing is not grounds to treat it as a false positive.
  4. This command is review-only: do NOT fix anything unless the user asks. If there are false positives or you have pushback, send a follow-up round via the reply parameter so Codex re-evaluates and updates finding statuses.
  5. If the user wants findings fixed automatically, point them to /counterpoint:review_loop.

Do NOT delegate to codex-rescue or any other Codex agent — the persistent thread is what makes multi-round review work.

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 · 22 lines · 18 tokens per session scan A 086bf95cbb25

Subscribe to this mod's changes

review is a command published in the GitHub repository wallneradam/cc-plugin-counterpoint (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 531 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.