A read-only diff review skill that checks code quality, behavior against the plan, and whether the changes belong in the project. A diff is the set of changes between two versions.

Use it to review a completed change and produce a written verdict covering code quality, feature behavior, and relevance.

It finds implementation, scope, and requirement problems before a change is shipped without modifying the reviewed files.

05-review — Skill for Claude Code by ai-driven-dev

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.

Any agent

npx skills add ai-driven-dev/framework --skill 05-review

Clone the repo

git clone --depth 1 https://github.com/ai-driven-dev/framework

Made for: Claude Code.

Or install aidd-dev, the plugin that ships this one along with the rest of its 11 skills, 2 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-driven-dev/framework/05-review.svg)](https://agentmods.dev/skills/ai-driven-dev/framework/05-review)

Your own site

<a href="https://agentmods.dev/skills/ai-driven-dev/framework/05-review"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/05-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 677 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00677
Opus 5	$0.00022	$0.00338
Sonnet 5	$0.00009	$0.00135
Haiku 4.5	$0.00004	$0.00068

Measured 3d ago against content hash 9a81cfc17d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

05-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.

plugins/aidd-dev/skills/05-review/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: review

Read-only review of a diff along three axes, code quality, feature behavior, and relevancy, composed into one report.

Actions

#	Action	Axis
01	`review-code`	Clean-code quality on the changed lines
02	`review-functional`	The diff against the plan's phases and their acceptance criteria
03	`review-relevancy`	Does the change belong: fit to the need, rule conformance, no rot

Run all three by default, composing one report. Run a single axis only when the caller names it; if it is unclear whether they want all or one, ask. Before running an action, read its file in actions/, not only the table or assets.

Transversal rules

Read-only: surface each finding with its fix described, never patch.
Output: always write review.md to disk; the file is the deliverable, never an inline-only verdict.
Folder: write into the reviewed work's feature folder (aidd_docs/tasks/<yyyy_mm>/<yyyy_mm_dd>_<slug>/, beside plan.md), or one resolved from the change when it has none.
Report: fill review.md from assets/review-template.md. One shared Findings table for every axis: functional writes the Phases boxes and the Verification table, and appends a functional row to Findings for each unmet criterion tagged fix; code and relevancy append rows to Findings under their Kind. Tables and boxes, no prose, no per-axis sections. The Phase column ties a finding to the plan when one is in scope, - otherwise.
Sections: the report has exactly the sections in assets/review-validator.yml. Before returning, verify against it and remove any section not listed.
Not run: every required section always exists. The header Axes run lists which axes ran, so a skipped code or relevancy axis is visible even though Findings is shared. An axis that did not run marks the sections it owns "Not run" (functional owns Phases and Verification); it never leaves a placeholder or invents data.
Re-run: overwrite review.md with the current review. It is a snapshot of the current diff, not a history; a later review of the same work replaces the earlier one.
Verdict: one overall verdict, the strictest across the axes run, per references/review-rubric.md.

Read the full file on GitHub · 41 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 41 lines · 44 tokens per session scan A 9a81cfc17d5a

Subscribe to this mod's changes

05-review is a skill published in the GitHub repository ai-driven-dev/framework (455 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 677 once invoked, about $0.0002 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.

Code review Git and workflow agent agentic ai ai-driven-development commands context-engineering

contribute-to-eliza

Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…

elizaOS/eliza · 68 tokens

github

Manage the full GitHub workflow from the terminal — auth, issues, pull request lifecycle (branch/commit/open/CI/merge), code review, and repo management. Uses the gh CLI when present, with a git + REST API fallback. Use when asked to "open a PR", "create an issue", "review this PR", "check CI", "list issues".

diillson/chatcli · 78 tokens

05-review