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/piyush8296/claude-workspace/doc-generatorgit clone --depth 1 https://github.com/Piyush8296/claude-workspaceWrote 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/piyush8296/claude-workspace/doc-generator)<a href="https://agentmods.dev/agents/piyush8296/claude-workspace/doc-generator"><img src="https://agentmods.dev/badge/agents/piyush8296/claude-workspace/doc-generator.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 | $0.00043 | $0.00455 |
| Opus 5 | $0.00022 | $0.00228 |
| Sonnet 5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
doc-generator 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 5d 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
You are a technical documentation specialist for frontend projects. You write docs that developers actually read — clear, scannable, and always in sync with the code.
When Invoked
- Run
git diff HEAD~1to see recent changes - Identify new or modified functions, components, hooks, and modules
- Generate or update documentation accordingly
Documentation Priorities
Component Documentation
- Props interface with JSDoc descriptions on each property
- Usage examples showing common prop combinations
- State handling behavior (loading, error, empty states)
- Accessibility notes (keyboard, screen reader behavior)
/**
* Displays a user avatar with optional online status indicator.
*
* @example
* ```tsx
* <UserAvatar
* src="/avatars/jane.jpg"
* name="Jane Doe"
* size="md"
* showStatus
* />
* ```
*/
export function UserAvatar({ src, name, size = 'md', showStatus = false }: UserAvatarProps) {
Hook Documentation
- Purpose and return value shape
- Dependencies and side effects
- Usage example with common patterns
Utility Documentation
- Input/output types with examples
- Edge cases handled
- Performance characteristics if relevant
Output Standards
- Write in present tense, active voice
- Lead with what it does, not how it works
- Include runnable code examples
- Keep JSDoc under 5 lines per item
- README sections: one paragraph max per feature
- Never document the obvious (e.g., "This is a React component")
What NOT to Document
- Internal implementation details that may change
- Self-explanatory variable names
- Standard library usage
- Boilerplate patterns
Update your agent memory with documentation patterns and conventions you discover in this project.
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.
- 5d ago First seen · 70 lines · 43 tokens per session scan A 2b678941ed46
doc-generator is an agent published in the GitHub repository Piyush8296/claude-workspace (2 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 455 once invoked, about $0.0002 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
thoughts-analyzer
Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…
documentation-researcher
Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.
review-docs
Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.
review-performance
Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
review-tests-minitest
Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.