review

review is a command for Claude Code from adamjgmiller/adamsreview. It costs 22 tokens per session (1,388 once invoked), scanned A, original, MIT.

A command that performs a deep code review and creates JSON and Markdown review reports. In pull-request mode, it can also post a review comment on the pull request.

In plain words
What is it for?
Use it to inspect a code change, produce a review artifact, or review a pull request. The `--full` option forces a complete review when the normal configuration would skip trivial changes.
Why use it?
It organizes review work into several stages and leaves a reusable record of the findings. An optional ensemble mode combines additional external reviews, at higher cost.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

Part of the adamsreview plugin — 6 commands, 1 hook shipped together

Good fit Use it to inspect a code change, produce a review artifact, or review a pull request. The --full option forces a complete review when the normal configuration would skip trivial changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/adamjgmiller/adamsreview/review
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.

Clone the repo
git clone --depth 1 https://github.com/adamjgmiller/adamsreview

Made for: Claude Code.

Or install adamsreview, the plugin that ships this one along with the rest of its 6 commands, 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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/review/github.svg)](https://agentmods.dev/commands/adamjgmiller/adamsreview/review)
Your own site
<a href="https://agentmods.dev/commands/adamjgmiller/adamsreview/review"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/adamjgmiller/adamsreview/review"><img src="https://agentmods.dev/badge/commands/adamjgmiller/adamsreview/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.01388
Opus 5 $0.00011 $0.00694
Sonnet 5 $0.00004 $0.00278
Haiku 4.5 $0.00002 $0.00139

Measured 12d ago against content hash d2103efd26eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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/review.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flags (optional):

  • --ensemble adds Phase 1.5 external-reviewer dispatch (Codex CLI + GitHub PR bot-comment scrape, followed by a unified normalizer). Off by default — enable for a richer review at higher cost.
  • --full forces trivial_mode=false for this run (overrides the doc/config-PR early-exit).

Read fragments/_prelude-shared.md before proceeding — it lists rules that apply to every phase below (sub-agent return handling, helper-script error-as-prompt).

Execution overview

This command orchestrates Phases 0–6 in order. Each phase is defined in a fragment under fragments/NN-<name>.md. At each phase boundary below, read the named fragment with the Read tool and execute the instructions inside before proceeding to the next phase.

Before you start, build a TaskList that mirrors the phases below (one task per phase, plus one for argument parsing). Mark each in_progress when you start it and completed when you finish.

Under --ensemble, Phase 1 and Phase 1.5 dispatch as a joint fan-out in one orchestrator turn. The TaskList can still carry two tasks — mark both in_progress when you fire the dispatch turn, and both completed after the join step at 01-detection.md 1.5 commits the pooled findings.

If a phase genuinely cannot run, mark the task completed with a one-line trace.md note and move on. Phase 6 (finalize) runs unconditionally — a partial review is still worth rendering and publishing so the user can inspect what did succeed.

Sub-agent failures (non-zero, unparseable output, timeouts) get logged to trace.md and drop that candidate from the run — they don't abort the whole command.

Sub-agent dispatch pattern

Every Agent tool-use specifies:

  • subagent_type: general-purpose. (The Codex CLI under --ensemble runs as a background Bash invocation of codex-companion.mjs, not an Agent dispatch — see fragments/02-ensemble-adapter.md.)
  • model: explicitly — haiku, sonnet, or opus per the fragment's instructions.

Read the full file on GitHub · 120 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. 12d ago First seen · 120 lines · 22 tokens per session scan A d2103efd26eb

Subscribe to this mod's changes

review is a command published in the GitHub repository adamjgmiller/adamsreview (243 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,388 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.