review

review is a command for coding agents from AcKeskin/contexture. It costs 28 tokens per session (375 once invoked), scanned A, original, MIT.

A command that checks code against the project’s architectural rules and reports specific places where the implementation has drifted from them.

In plain words
What is it for?
Use it to review a whole project, folder, file, or changes since a Git reference, then accept, skip, or edit proposed fixes.
Why use it?
It finds structural problems such as dead code, oversized files, or misplaced responsibilities, while requiring confirmation before applying fixes.

Command

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/ackeskin/contexture/review
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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/ackeskin/contexture/review.svg)](https://agentmods.dev/commands/ackeskin/contexture/review)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/review"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 375 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 5.1 $0.00028 $0.00375
Opus 5 $0.00014 $0.00187
Sonnet 5 $0.00006 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured yesterday against content hash 66d57693c31d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 yesterday.

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 · 27 lines

What it actually says

Run the review skill.

Forms:

  • /review — entire current project.
  • /review <path> — directory (recursive) or a single file.
  • /review --since <ref> — only files changed since the given git ref.

Examples:

  • /review — scan the whole project for drift.
  • /review src/auth/ — scan just the auth module.
  • /review src/auth/middleware.ts — scan a single file.
  • /review --since main — scan files changed on the current branch.

The skill resolves scope, loads architectural rules via skills/discover/SKILL.md (kind: "architectural-rule", relevance_phases: ["always", "during-review"], render_bodies: true), reads .claude/architecture.md if present, and scans each file in scope for drift across six categories: dead code, monolithic files, SoC violations, missing pattern usage, principle violations, comment drift. Findings come with specific fixes — not "consider refactoring." Each fix is propose-confirm-commit (apply / skip / edit / view-detail) — no silent changes.

At the end of every run, the skill asks "did this catch what you wanted?" A "no" opens the feedback loop: sharpen an existing rule, add a new rule, retag a rule, or adjust a threshold — each routed through /capture so the system improves from the correction.

Does not auto-fire. Not a linter replacement, not a security audit, not a test coverage report.

See ~/.claude/skills/review/SKILL.md for the full procedure.

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. yesterday First seen · 27 lines · 28 tokens per session scan A 66d57693c31d

Subscribe to this mod's changes

review is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 375 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 2026-09-03.