agentmods.dev

code-review-risk-check

code-review-risk-check is a skill for Claude Code, Codex from kngwyc3/Agent-Learning-Hub. It costs 27 tokens per session (437 once invoked), scanned A, original, MIT.

A checklist and method for reviewing a code change or pull request, which is a proposed change to a shared codebase. It focuses on bugs, regressions, safety, data handling, and missing tests.

In plain words
What is it for?
Use it to inspect diffs, assess changed user behavior, check error handling and permissions, and judge whether important changes have adequate tests.
Why use it?
It helps reviewers find problems that may affect users or future maintenance instead of merely summarizing changed files. It also focuses attention on the riskiest behavior first.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 128repo +1 2mo ago A scan 27 tokens original MIT

Good fit Use it to inspect diffs, assess changed user behavior, check error handling and permissions, and judge whether important changes have adequate tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kngwyc3/agent-learning-hub/my-skill
View source ↗ kngwyc3/Agent-Learning-Hub datawhalechina.github.io
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 kngwyc3/Agent-Learning-Hub --skill my-skill
Clone the repo
git clone --depth 1 https://github.com/kngwyc3/Agent-Learning-Hub

Made for: Claude Code, Codex.

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 code-review-risk-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/my-skill/github.svg)](https://agentmods.dev/skills/kngwyc3/agent-learning-hub/my-skill)
Your own site
<a href="https://agentmods.dev/skills/kngwyc3/agent-learning-hub/my-skill"><img src="https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/my-skill/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 code-review-risk-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/kngwyc3/agent-learning-hub/my-skill"><img src="https://agentmods.dev/badge/skills/kngwyc3/agent-learning-hub/my-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 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 $0.00027 $0.00437
Opus 5 $0.00014 $0.00218
Sonnet 5 $0.00005 $0.00087
Haiku 4.5 $0.00003 $0.00044

Measured 10d ago against content hash 9efadabcef56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-review-risk-check 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/smoke_check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

stage-5/my-skill/SKILL.md · 53 lines

What it actually says

Code Review Risk Check

Use this skill to turn a raw code diff into a concise engineering review. The goal is not to summarize every changed file; the goal is to find the issues that could break users, production, security, data integrity, or future maintenance.

When To Use

  • The user asks for a code review, PR review, diff review, or regression risk review.
  • The input contains changed files, a patch, commit diff, or PR context.
  • The expected output is a review comment or a list of findings.

When Not To Use

  • The user asks for implementation rather than review.
  • There is no code, diff, or behavioral description to inspect.
  • The request is only about formatting, naming, or style preferences.

Inputs

  • Code diff or file list.
  • User intent, issue, PR description, or acceptance criteria if available.
  • Test output, linter output, or CI failures if available.

Steps

  1. Identify the user-facing behavior or contract touched by the change.
  2. Scan the diff for correctness risks first: control flow, data shape, state transitions, error handling, permissions, concurrency, and persistence.
  3. Check whether tests cover the riskiest changed behavior.
  4. Ignore low-signal style issues unless they hide a real bug.
  5. Report findings first, ordered by severity.
  6. If no issues are found, say so clearly and mention remaining test gaps or residual risk.

Output

Use templates/review_report.md as the output shape:

  • Findings first.
  • Each finding must include severity, file or symbol, impact, and a concrete fix direction.
  • Summary is optional and must stay short.

Verification

Before returning the review:

  • At least one finding has concrete evidence, or the report explicitly says no findings.
  • No fabricated file paths or line numbers.
  • No broad rewrite suggestions unless the current diff requires them.
  • Test gaps are tied to changed behavior, not generic advice.
Files

What ships with it

11 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.

  1. 10d ago First seen · 53 lines · 27 tokens per session scan A 9efadabcef56

Subscribe to this mod's changes

code-review-risk-check is a skill published in the GitHub repository kngwyc3/Agent-Learning-Hub (128 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 437 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.

Code review
Related

Other skills, from other repositories

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens