review

A read-only method for reviewing a code change against its request or specification. It checks correctness, security, regressions, scope, and missing tests.

In plain words
What is it for?
Reviewing Git diffs, checking relevant files and requirements, and reporting actionable issues without editing the code.
Why use it?
It focuses attention on problems that could affect behavior, safety, compatibility, or completion of the requested work.

Skill for Claude CodeCodex

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 skills/bnet47/codexicon/review
Any agent
npx skills add bnet47/codexicon --skill review
Clone the repo
git clone --depth 1 https://github.com/bnet47/codexicon

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 383 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 $0.00029 $0.00383
Opus 5 $0.00015 $0.00192
Sonnet 5 $0.00006 $0.00077
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash bd87428f8f61, 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 2d 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.

.agents/skills/review/SKILL.md · 49 lines

What it actually says

Review

Review evidence, not intent. Do not modify files.

Establish the comparison

Inspect git status, unstaged and staged diffs, and—when available—the branch diff from its merge base. Read the request or linked spec/plan plus relevant conventions. If no Git repository exists, review the explicitly supplied files and state the limitation.

For a broad or high-risk diff, delegate independent read-only passes to the reviewer profile (for example correctness, security, and test coverage), then deduplicate and verify the findings yourself.

When the diff came from an engineering loop, review the combined result after integration. Do not treat a passing subagent report as final evidence; inspect the actual diff and canonical checks.

Findings threshold

Report only issues that can cause:

  • unmet acceptance criteria;
  • incorrect behavior or a regression;
  • security, privacy, authorization, or data-integrity exposure;
  • unsafe migration or compatibility behavior;
  • meaningful missing verification;
  • accidental scope drift that raises risk.

Do not report style preferences, speculative future improvements, or items already enforced by a passing formatter unless they affect behavior.

Output

Order findings by severity:

## Findings

### [P1] [Short title]
`path/to/file:line` — [Concrete impact, triggering condition, and violated requirement.]

## Verification gaps
- [Missing or untrustworthy evidence.]

## Verdict
READY | NEEDS WORK — [one sentence]

Severity: P0 blocks all use; P1 high-impact and likely; P2 material but limited; P3 low-impact and concrete. Use the tightest line reference possible. If no actionable issue exists, return READY — no actionable gaps found.

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. 2d ago First seen · 49 lines · 29 tokens per session scan A bd87428f8f61

Subscribe to this mod's changes

review is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 383 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.

Related

Other skills, from other repositories

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

pdf

当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.

agentscope-ai/QwenPaw · 95 tokens

make_plan

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

agentscope-ai/QwenPaw · 51 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

mateaix/mateclaw · 16 tokens