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 agentmods add commands/hculap/better-code/auditgit clone --depth 1 https://github.com/hculap/better-codeWhat 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 | $0.00005 | $0.01184 |
| Opus 5 | $0.00003 | $0.00592 |
| Sonnet 5 | $0.00001 | $0.00237 |
| Haiku 4.5 | $0.00001 | $0.00118 |
Grade A, and why
audit 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 yesterday.
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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Audit
Analyze existing documentation for quality, completeness, and adherence to configured standards.
Arguments
path(optional): Directory to audit (default:./docsor project root)--detailed: Generate comprehensive report with scores and recommendations--checklist: Quick pass/fail checklist (default mode)
Process
Step 1: Load Configuration
Read .claude/doc-master.local.md to determine active documentation standard:
- Diátaxis: Audit against four-quadrant criteria
- Traditional: Audit against hierarchical structure
- Custom: Audit against custom rules
If no configuration exists, suggest running /doc-master:setup first, but proceed with Diátaxis as default.
Step 2: Discover Documentation
Search for documentation files:
- README.md, README files
- docs/ directory
- *.md files in common locations
- API documentation (openapi.yaml, swagger.json)
- Inline documentation (JSDoc, docstrings)
Step 3: Analyze Documentation
Checklist Mode (default)
Quick pass/fail assessment:
Completeness
- README exists and has content
- Installation/setup documented
- Main features have documentation
- API endpoints documented (if applicable)
- Configuration options listed
Accuracy
- Code examples appear current
- Version information present
- No obviously outdated content
- Links are valid (spot check)
Clarity
- Headings are descriptive
- Code examples present
- Consistent formatting
Organization
- Logical structure
- Navigation/TOC present
- Related content linked
Detailed Mode
Comprehensive analysis with scoring:
1. Coverage Analysis (0-10)
- Map documented vs undocumented code
- Check for missing API documentation
- Identify undocumented features
- List documentation gaps
2. Quality Score (0-10)
- Writing quality assessment
- Code example validation
- Formatting consistency
- Terminology consistency
3. Freshness Assessment (0-10)
- Last modification dates
- Version alignment
- Outdated content detection
- Stale examples identification
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.
- yesterday First seen · 217 lines · 5 tokens per session scan A fbe741f0af65
audit is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 5 tokens to every session and 1,184 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.
Other commands, from other repositories
create-skill
Create an AI skill from any source (URL, repo, PDF, video, notebook, etc.).
sync-config
Sync a scraping config's URLs against the live documentation site.
create_plan
Create detailed implementation plans through interactive research and iteration.
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
research_codebase
Document codebase as-is with thoughts directory for historical context.
iterate_plan
Iterate on existing implementation plans with thorough research and updates.