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-scangit 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-scan)<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-scan"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-scan/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-scan"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-scan.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 | $0.00059 | $0.01054 |
| Opus 5.5 | $0.00024 | $0.00422 |
| Sonnet 5.5 | $0.00012 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
ai-dev-os-scan 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Dev OS Full Project Scan
Execution Flow
1. Parse CLAUDE.md
Extract the list of guideline file paths from CLAUDE.md.
2. Discover Target Files
If the user provides a directory or glob pattern, use that as the scope. Otherwise, scan the entire project:
- Find all source files using
findorGlob(e.g.,**/*.{ts,tsx,js,jsx,py,go}) - Exclude common non-source directories:
node_modules/,.git/,dist/,build/,.next/,__pycache__/,.venv/,vendor/ - Exclude files listed in
.gitignore
3. Build Dynamic Mapping
Dynamically build the mapping between file patterns and guidelines.
Examples by tech stack:
- Python:
*.py→ code.md, naming.md, validation.md;*/router.py→ security.md, cors.md;*/models.py→ naming.md, validation.md;*/schemas.py→ validation.md;alembic/**→ naming.md - Next.js:
*.tsx→ ui.md, form.md, code.md, naming.md;app/**/page.tsx→ routing.md;app/**/action.ts→ server-actions.md - Go:
*.go→ code.md, naming.md, error-handling.md
4. Extract Check Items
Auto-detect check items from each guideline using the following keywords:
- "MUST", "MUST NOT", "PROHIBITED", "REQUIRED", etc.
- If frontmatter contains
checklist: [...], use that instead
If checklist templates exist in the plugin's checklist-templates/ directory for the detected tech stack, load them as a reference.
5. Run Checks (Batch Processing)
Process files in batches to manage context window:
- Group files by directory or module
- For each batch:
- Auto-check items detectable via static analysis (Grep/Glob)
- Flag items requiring judgment with ⚠️ for human review
- Track progress: "Scanning batch N/M..."
6. Aggregate Results
Combine results from all batches:
- Deduplicate violations
- Sort by severity (❌ violations first, then ⚠️ reviews)
- Group by guideline for pattern analysis
7. Report Output
Output in the following format:
## AI Dev OS Full Project Scan Report
### Summary
- Total files scanned: N
- ✅ Passed: N / ⚠️ Review: N / ❌ Violation: N
- Compliance rate: N%
### Violations by Guideline
| Guideline | Violations | Files Affected | Most Common Issue |
|-----------|-----------|----------------|-------------------|
### Top Violations
| # | File | Line | Rule | Guideline | Principle |
|---|------|------|------|-----------|-----------|
### Review Required
| File | Line | Item | Guideline |
|------|------|------|-----------|
### Hot Spots (Files with Most Violations)
| File | Violations | Reviews | Top Issues |
|------|-----------|---------|------------|
### Recommendations
1. [Priority: High] ...
2. [Priority: Medium] ...
### Why These Rules?
> Explains the rationale for the most frequent violations, tracing back to L2 principles → L1 philosophy
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 · 131 lines · 59 tokens per session scan A c2198797a8c5
ai-dev-os-scan 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 59 tokens to every session and 1,054 once invoked, about $0.0002 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
guideline-checker
Automatically check whether git diff contents comply with project guidelines after code changes. Run at coding completion or before committing.
memstack-development-code-reviewer
Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what's wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.
shard
Use when the user says 'shard this', 'split file', or when working with files over 1000 lines.
pr-review
Focused pull request review practices with severity-ranked, file-and-line-cited findings across four angles: security, performance, tests, and architecture. Use when asked to review a pull request, review a diff or set of changes, review "this PR," or provide a code review before merge.
eval-skills
Audit a project or library of skills for metadata, trigger boundaries, workflow completion criteria, local resource closure, instruction economy, tool scope, effort, and routing evidence. Use before shipping skills, after importing a skill collection, or when a skill triggers too often or not at all.
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.