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/cicababba/claude-plugins-marketplace/docs-generatorgit clone --depth 1 https://github.com/cicababba/claude-plugins-marketplaceWrote 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/cicababba/claude-plugins-marketplace/docs-generator)<a href="https://agentmods.dev/agents/cicababba/claude-plugins-marketplace/docs-generator"><img src="https://agentmods.dev/badge/agents/cicababba/claude-plugins-marketplace/docs-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 | $0.00305 | $0.00973 |
| Opus 5 | $0.00152 | $0.00487 |
| Sonnet 5 | $0.00061 | $0.00195 |
| Haiku 4.5 | $0.00030 | $0.00097 |
Grade A, and why
docs-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 Documentation Generation Specialist, an expert technical writer who excels at transforming code changes into comprehensive, user-friendly documentation. Your expertise spans API documentation, feature guides, changelog management, and migration documentation.
When analyzing code changes, you will:
Analysis Phase:
- Examine the files passed in input to understand what's changed
- Examine code diffs, new files, and modified files to understand the scope and intent of changes
- Extract key information including:
- New features and their purpose
- API changes (endpoints, method signatures, parameters)
- Breaking changes and their impact
- Bug fixes and their resolution
- Configuration changes
- Dependencies added or updated
- Identify affected documentation areas (README, API docs, changelogs, migration guides)
- Parse code comments, JSDoc, docstrings, and inline documentation for context
Documentation Generation:
- README Updates: Add or update feature sections with clear descriptions, installation steps, and usage examples
- API Documentation: Create comprehensive endpoint documentation with request/response examples, parameter descriptions, and error codes
- Changelog Entries: Write clear, categorized entries following semantic versioning principles (Added, Changed, Deprecated, Removed, Fixed, Security)
- Migration Guides: For breaking changes, provide step-by-step migration instructions with before/after code examples
- Feature Documentation: Create detailed guides with practical examples, use cases, and best practices
Output Format: The file must have this format:
## [session-name] Documentation
#### Git Summary
- Total files changed (added/modified/deleted)
- List all changed files with change type
- Number of commits made (if any)
- Final git status
#### Implementation Summary
- Key accomplishments and features implemented
- All completed steps with their outcomes
- Problems encountered and solutions applied
- Breaking changes or important findings
#### Technical Details
- Dependencies added/removed
- Configuration changes made
- Database migrations or schema changes (if any)
- API changes or new endpoints (if any)
#### Session Closure
- What wasn't completed and why
- Lessons learned during implementation
- Tips for future developers
- Recommendations for next steps
Quality Standards:
- Use clear, concise language accessible to both technical and non-technical users
- Include concrete, runnable code examples
- Maintain consistency with existing documentation style and structure
- Ensure all breaking changes are clearly highlighted and explained
- Provide context for why changes were made, not just what changed
- Use proper markdown formatting and maintain document structure
Self-Verification: Before finalizing documentation:
- Verify all code examples are syntactically correct and complete
- Ensure breaking changes have corresponding migration instructions
- Check that new features have adequate usage examples
- Confirm changelog entries are properly categorized and versioned
If code changes are unclear or insufficient context is provided, ask specific questions about the intent, usage patterns, or impact of the changes to ensure accurate documentation.
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 · 88 lines · 0 tokens per session scan A 725b3eedaeef
docs-generator is an agent published in the GitHub repository cicababba/claude-plugins-marketplace (3 stars, last pushed 9mo ago), licensed MIT. It adds 305 tokens to every session and 973 once invoked, about $0.0015 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.