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 travisjneuman/.claude --skill codebase-documentergit clone --depth 1 https://github.com/travisjneuman/.claudeWrote 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/travisjneuman/.claude/codebase-documenter)<a href="https://agentmods.dev/skills/travisjneuman/.claude/codebase-documenter"><img src="https://agentmods.dev/badge/skills/travisjneuman/.claude/codebase-documenter.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01074 |
| Opus 5 | $0.00041 | $0.00537 |
| Sonnet 5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
codebase-documenter 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 3d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Documenter
Create comprehensive, beginner-friendly documentation for any codebase.
When to Use
Use for:
- Writing or updating README files
- Creating architecture documentation
- Adding meaningful code comments
- Documenting APIs and endpoints
- Creating getting-started guides
- Explaining project structure
Don't use when:
- Code review → use
generic-code-reviewer - UX design decisions → use
generic-ux-designer - Adding code features → use
generic-feature-developer
Core Principles
- Start with "Why" - Explain purpose before implementation
- Progressive Disclosure - Simple to complex
- Provide Context - Why code exists, not just what it does
- Include Examples - Concrete usage for every concept
- Assume No Prior Knowledge - Define terms, avoid jargon
- Visual Aids - Diagrams, file trees, flowcharts
- Quick Wins - Get something running in 5 minutes
Documentation Workflow
- Analyze - Entry points, dependencies, core concepts, configuration
- Choose Type - README → Architecture → API → Comments
- Generate - Use templates, customize for project
- Verify - Read as beginner, test examples
Documentation Types
README (Project Entry Point)
# Project Name
## What This Does
[1-2 sentence explanation]
## Quick Start
[< 5 minute setup]
## Project Structure
[Visual file tree]
## Key Concepts
[Core abstractions]
## Common Tasks
[Step-by-step guides]
Architecture Documentation
# Architecture Overview
## System Design
[High-level diagram]
## Data Flow
[How data moves through system]
## Key Design Decisions
[Why certain choices were made]
## Extension Points
[Where to add new features]
Code Comments
// ✅ GOOD - Explains WHY and context
// IndexedDB quota check: Prevents silent failures when storage is full.
// Without this, writes fail with cryptic QuotaExceededError.
if (quota.percentUsed > 80) showStorageWarning();
// ❌ BAD - Just repeats what code does
// Check if quota is over 80
What ships with it
8 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.
- assets/templates/API.template.md 14 KB
- assets/templates/ARCHITECTURE.template.md 13 KB
- assets/templates/CODE_COMMENTS.template.md 15 KB
- assets/templates/README.template.md 5.4 KB
- index.js 263 B runs code
- package.json 229 B
- references/documentation_guidelines.md 14 KB
- references/visual_aids_guide.md 25 KB
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.
- 3d ago First seen · 200 lines · 81 tokens per session scan A 0c96baadbe03
codebase-documenter is a skill published in the GitHub repository travisjneuman/.claude (95 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,074 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
obsidian-vault
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
notion-sdk
Control Notion via Python SDK. TRIGGERS - Notion API, create page, query database, add blocks.
asciinema-converter
Convert .cast recordings to .txt for analysis. TRIGGERS - convert cast, cast to txt, strip ANSI, batch convert.
post-session
Complete post-session workflow - finalize orphaned recordings, convert, and AI summarize. TRIGGERS - post session, analyze recording, session review.
documentation-standards
Apply markdown documentation standards optimized for both LLM consumption and Pandoc PDF generation. Use whenever the user is writing or.
pandoc-pdf-generation
PDF generation from markdown via Pandoc/XeLaTeX. TRIGGERS - markdown for PDF, print document, pandoc.