A code-review checklist that runs a project's required checks and compares recent changes with its coding rules and technical specification.

Use it to review changed code, run applicable build, test, lint, and type checks, and check API contracts, data models, edge cases, and test coverage.

It helps catch build, test, style, security, error-handling, and specification problems before changes are accepted or released.

review — Skill for Claude Code by ashtonian

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 ashtonian/llm-init --skill review

Clone the repo

git clone --depth 1 https://github.com/ashtonian/llm-init

Made for: Claude Code.

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/ashtonian/llm-init/review.svg)](https://agentmods.dev/skills/ashtonian/llm-init/review)

Your own site

<a href="https://agentmods.dev/skills/ashtonian/llm-init/review"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/review.svg" alt="Measured on agentmods" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 516 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	$0.00009	$0.00516
Opus 5	$0.00005	$0.00258
Sonnet 5	$0.00002	$0.00103
Haiku 4.5	$0.00001	$0.00052

Measured 6d ago against content hash 0cb16380c020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

templates/.claude/skills/review/SKILL.md · 46 lines

What it actually says

Run quality gates and review current work.

Instructions

Read .claude/rules/agent-guide.md for project-specific quality gate commands and the Production Code Quality Checklist.
Read docs/spec/.llm/PROGRESS.md for known patterns and conventions.
Run quality gates from the agent guide rules (build, test, lint, type-check as applicable).
Check conventions:
- Code follows rules in .claude/rules/ (go-patterns, typescript-patterns, etc.)
- New files have appropriate structure and documentation
- No hardcoded credentials, secrets, or environment-specific values
- Error handling follows project patterns
- Implementation matches technical spec (if one exists): data models, API contracts, error codes
Spec compliance (if a technical spec exists for the changed feature):
- Every data model field matches the spec (types, constraints, nullability)
- Every API endpoint matches the spec (path, method, request/response shape, status codes)
- Every error code in the spec is handled in the implementation
- Edge cases documented in the spec have corresponding code paths and tests
Code quality audit:
- All error paths are tested, not just happy paths
- Input validation exists at system boundaries (handlers, CLI, config parsing)
- No swallowed errors (_ = err without justification)
- Functions are < 60 lines; complex logic is commented with WHY
- New public packages have doc.go with usage examples
- README updated if new user-facing functionality was added
Security check:
- No secrets, tokens, or passwords in code or config files
- User input is validated and sanitized before use
- SQL queries use parameterized statements (no string concatenation)
- File paths from user input are sanitized
Report results in a structured format:
- Quality gates: pass/fail with details
- Spec compliance: field-by-field match (or N/A if no spec)
- Code quality: issues found with file:line references
- Security: issues found or clean
- Convention issues: list with file and line
- Recommendations: what to fix and how (prioritized)

$ARGUMENTS

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.

6d ago First seen · 46 lines · 9 tokens per session scan A 0cb16380c020

Subscribe to this mod's changes

review is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 516 once invoked, about $0.0000 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.

Code review Testing

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

semgrep-rule-variant-creator

Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.

waybarrios/opencode-power-pack · 50 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

include-test-files-that-assert-on-behavior-being-changed-in-decl

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens

qa-frontend

Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence. Do not use for generic code review, PR review…

PostHog/posthog · 142 tokens