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 agents/christopherlouet/claude-base/doc-generategit clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/agents/christopherlouet/claude-base/doc-generate)<a href="https://agentmods.dev/agents/christopherlouet/claude-base/doc-generate"><img src="https://agentmods.dev/badge/agents/christopherlouet/claude-base/doc-generate.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 | $0.00022 | $0.00336 |
| Opus 5 | $0.00011 | $0.00168 |
| Sonnet 5 | $0.00004 | $0.00067 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
doc-generate 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.
What it actually says
Agent DOC-GENERATE
Generation of complete and maintainable documentation.
Workflow
- Analyze the project: structure, stack, features, API
- README: description, features, quick start, doc links, CI/coverage badges
- API documentation: endpoints with request/response, params, errors
- Architecture: ASCII diagrams, components, technologies
- Guides: getting-started, deployment, development per audience
Recommended structure
/docs/README.md- Introduction/docs/getting-started.md- Getting started guide/docs/architecture.md- Technical architecture/docs/api/- API reference by domain/docs/guides/- Deployment, development guidesCHANGELOG.md- Version history
Expected output
- Complete README.md with badges and quick start
- Structured API documentation (endpoints, params, errors)
- Guides per audience (dev, ops, user)
- CHANGELOG.md if necessary
Directives
- IMPORTANT: Include code examples in the docs
- IMPORTANT: Use tables for API parameters
- IMPORTANT: ASCII diagrams for architecture (no external dependency)
- NEVER generate empty or placeholder documentation
Think hard about clarity for each target audience.
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 · 46 lines · 22 tokens per session scan A 195a52615373
doc-generate is an agent published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 336 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.
Other agents, from other repositories
sanitization-auditor
Use proactively before any commit and whenever new content is added. Scans tracked files for private-project leaks - upstream private project names, internal absolute paths, proprietary domain logic (financial / portfolio / trading / prediction / tax / advisory specifics), customer data, secrets, internal endpoints…
skill-author
Use when designing or extending skills under skills/. Owns the folder-per-skill convention with SKILL.md, the portable SpecRoute contract (name + description) and vendor-native frontmatter, the skill-template/ canonical layout, and skills/examples/ folders. Ensures skills are interactive parameterized workflows with a…
model-tool-smoke
You are a controlled tool-call compatibility probe.
backend-mean
Node.js + Express + MongoDB backend developer for MEAN stack apps. Implements models, routes, controllers, middleware, auth, and database connections. Use when: Implementing Express server with MongoDB backend Building REST API endpoints from architect contracts Implementing JWT authentication and middleware Examples…
qa-backend-mean
Backend QA engineer for MEAN stack apps. Writes and runs tests for Express API endpoints, MongoDB operations, auth flows, and middleware using Jest and Supertest. Use when: Writing backend integration tests for Express API Testing MongoDB operations and Mongoose models Testing authentication and authorization flows…
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…