guideline-checker

guideline-checker is a skill for Claude Code from yunbow/ai-dev-os-rules-typescript. It costs 27 tokens per session (802 once invoked), scanned A, original, MIT.

A checker that reviews changed code against project-specific development guidelines. It selects guidelines based on the files that changed.

In plain words
What is it for?
Use it after coding or before committing to inspect the relevant files and check them against the applicable guidelines.
Why use it?
It helps catch departures from the project's coding, security, naming, validation, routing, or framework rules before a review or commit.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after coding or before committing to inspect the relevant files and check them against the applicable guidelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yunbow/ai-dev-os-rules-typescript/guideline-checker
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 yunbow/ai-dev-os-rules-typescript --skill guideline-checker
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-rules-typescript

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.

agentmods badge for guideline-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker/github.svg)](https://agentmods.dev/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker)
Your own site
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker/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 guideline-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-rules-typescript/guideline-checker.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 802 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 $0.00802
Opus 5 $0.00014 $0.00401
Sonnet 5 $0.00005 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 9d ago against content hash 35c79f03a1b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

guideline-checker 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 9d 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/nextjs/.claude/skills/guideline-checker/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guideline Compliance Checker

A skill that checks whether code changes comply with ai-dev-os guidelines.

When to Execute

  • When a review is requested after coding is complete
  • When verifying compliance before committing
  • When requested with "guideline check", "compliance check", etc.

Execution Steps

1. Get Changed Files

git diff --name-only

If there are no changes, check staged or last commit changes with git diff HEAD~1 --name-only.

2. Identify Relevant Guidelines

Based on the paths of changed files, identify which guidelines to check:

Changed File Pattern Guidelines to Check
*.ts, *.tsx common/code.md, common/naming.md
*/server/*.ts, *-actions.ts frameworks/nextjs/api.md, common/security.md, common/error-handling.md
*/schema/*.ts common/validation.md
*/components/*.tsx frameworks/nextjs/ui.md, frameworks/nextjs/form.md
*/hooks/*.ts frameworks/nextjs/state.md
prisma/schema.prisma frameworks/nextjs/database.md, common/naming.md
app/**/page.tsx, app/**/layout.tsx frameworks/nextjs/routing.md
app/api/** frameworks/nextjs/api.md, common/security.md
.env* common/env.md
*.test.ts, *.spec.ts common/testing.md

3. Check Items by Guideline

common/security.md (Security)
  • Are authentication checks (auth()) performed in Server Actions?
  • Is input validated with Zod?
  • Are there IDOR protections (resource ownership checks)?
  • Is sensitive information excluded from logs?
common/code.md (Coding Conventions)
  • Is the any type not used? (unknown should be used instead)
  • Are function arguments and return types explicitly typed?
  • Are Union Literals used instead of Enums?
  • Are reasons documented in comments when disabling ESLint rules?
common/error-handling.md (Error Handling)
  • Are error responses in a unified format (ActionResult, etc.)?
  • Are internal errors not directly exposed to users?
  • Are appropriate log levels (ERROR/WARN/INFO) used?

Read the full file on GitHub · 100 lines

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. 9d ago First seen · 100 lines · 27 tokens per session scan A 35c79f03a1b6

Subscribe to this mod's changes

guideline-checker is a skill published in the GitHub repository yunbow/ai-dev-os-rules-typescript (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 802 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

ai-dev-os-check

Checks code changes against AI Dev OS guidelines and automatically fixes violations. Based on benchmark Test 011: check+fix achieves +9.9 improvement vs report-only (+0.8). Supports git diff (default), branch comparison, and staged changes. Use --dry-run for report-only mode (no fixes applied).

yunbow/ai-dev-os-plugin-claude-code · 68 tokens

ai-dev-os-scan

Scans ALL source files in the project against AI Dev OS guidelines. Unlike /ai-dev-os-check (which only checks git diff), this performs a full project-wide compliance scan. Use for initial audits, periodic full reviews, or after introducing new guidelines.

yunbow/ai-dev-os-plugin-claude-code · 59 tokens

ai-dev-os-review

Performs a comprehensive self-review before creating a PR. Combines guideline compliance checking (L3) with design-level review (L2) and philosophical alignment (L1). Unlike /ai-dev-os-check which only checks rules, this also evaluates architecture decisions and code design quality.

yunbow/ai-dev-os-plugin-claude-code · 64 tokens

ai-dev-os-extract

Extracts rules from the gap between AI-generated code and ideal code. Used after code review to add new rules to AI Dev OS guidelines. A Rule Harvesting approach to rule discovery.

yunbow/ai-dev-os-plugin-claude-code · 43 tokens

ai-dev-os-evolve

Supports the spiral evolution of AI Dev OS. Analyzes recent AI coding practices (commit history, review records) and generates update proposals for L1 philosophy and L2 principles. Used in monthly retrospectives or quarterly reviews.

yunbow/ai-dev-os-plugin-claude-code · 50 tokens

spotpatch

A development workflow for React that connects a selected page element to its JSX or TSX source code and gathers context for review.

huanglvjing/spotpatch · 93 tokens