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.
npx skills add yunbow/ai-dev-os-plugin-claude-code --skill ai-dev-os-checkgit clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-claude-codeWrote 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.
[](https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-check)<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-check"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-check/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.
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-check"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.01091 |
| Opus 5.5 | $0.00027 | $0.00436 |
| Sonnet 5.5 | $0.00014 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
ai-dev-os-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Dev OS Guideline Check & Fix
Design Principle: Report-only checks have near-zero impact on code quality. Check + Fix in a single session achieves +9.9 improvement (benchmark Test 011).
Execution Flow
1. Determine Scope & Mode
Parse the argument to determine the check scope and mode:
Scope:
- No argument: Check unstaged changes (
git diff --name-only) --staged: Check staged changes (git diff --cached --name-only)[branch](e.g.,main,develop): Check all changes vs. the specified branch (git diff [branch]...HEAD --name-only) — ideal for PR review
Mode:
- Default: Check & Fix — find violations and fix them automatically
--dry-run: Report only — list violations without modifying code
2. Parse CLAUDE.md
Extract the list of guideline file paths from CLAUDE.md.
3. Get Changed Files
Retrieve changed files based on the determined scope. If no files are changed, report "No changes to check" and exit.
4. Select Checklist
Auto-detect the tech stack from the project and load the appropriate checklist template:
checklist-templates/nextjs.md— for Next.js / React projectschecklist-templates/python.md— for Python / FastAPI projectschecklist-templates/go.md— for Go projects
Also load relevant guideline files from CLAUDE.md to extract additional MUST/MUST NOT rules.
5. Check — Systematic Violation Scan
Review ALL changed files against the checklist items systematically:
- Read each changed file
- Check each checklist item against the actual code
- Record violations with: file, line number, rule ID, description
Important: Check ALL items, not just obvious ones. Security and naming rules are easy to miss.
6. Fix — Auto-Correct Violations
Skip this step if --dry-run is specified.
For each violation found:
- Fix the violation directly in the code using Edit/Write tools
- Verify the fix doesn't break surrounding code
- Mark the item as fixed
Fix principles:
What ships with it
3 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.
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.
- 1mo ago First seen · 144 lines · 68 tokens per session scan A bcd890d492f7
ai-dev-os-check is a skill published in the GitHub repository yunbow/ai-dev-os-plugin-claude-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 68 tokens to every session and 1,091 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…
pr-autofix
When the user has PR review feedback to address, CI failures to fix, or wants to automatically resolve common PR issues. Use when the user says "fix the PR," "address review comments," "CI is failing," "fix the build," "autofix," "pr feedback," "resolve comments," "fix merge conflicts," or when a PR needs updates…