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.
git clone --depth 1 https://github.com/lukaszzychal/mcp-doc-generatorWrote 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/rules/lukaszzychal/mcp-doc-generator/documentation)<a href="https://agentmods.dev/rules/lukaszzychal/mcp-doc-generator/documentation"><img src="https://agentmods.dev/badge/rules/lukaszzychal/mcp-doc-generator/documentation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/lukaszzychal/mcp-doc-generator/documentation"><img src="https://agentmods.dev/badge/rules/lukaszzychal/mcp-doc-generator/documentation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00529 | $0.00529 |
| Opus 5.5 | $0.00212 | $0.00212 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
documentation 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 2mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Standards
Bilingual Documentation (EN/PL)
All documentation files must be bilingual (English/Polish) following this structure:
- Primary Language: English - Write all documentation first in English
- Secondary Language: Polish - Synchronize Polish version after English is complete
- Structure Pattern:
- Use language anchors:
<a name="english"></a>and<a name="polski"></a> - English section comes first
- Polish section comes after, marked with
<a name="polski"></a> - Use separator:
---between language sections
- Use language anchors:
Documentation File Format
# Document Title
**Language / Język:** [English](#english) | [Polski](#polski)
---
<a name="english"></a>
# English
[English content here]
---
<a name="polski"></a>
# Polski
[Polish content here - synchronized with English]
Writing Guidelines
- Write English first - Always create English version first, ensure it's complete and accurate
- Synchronize Polish - After English is done, create Polish version that:
- Maintains the same structure and sections
- Preserves code examples (they remain in English)
- Translates all explanatory text accurately
- Keeps technical terms consistent (use English terms with Polish explanations if needed)
- Code Examples - Keep code examples in English, add Polish comments if helpful
- Links and References - Maintain English anchor names, translate link text
- Consistency - Use consistent terminology across all documents
Files Requiring Bilingual Content
- README.md
- All files in
docs/directory - USAGE_GUIDE.md
- QUICKSTART.md
- Any new documentation files
When Creating New Documentation
- Start with English section
- Complete English content fully
- Add language separator
--- - Add Polish anchor and section
- Translate content maintaining structure
- Verify both versions are synchronized
Code Comments
- Code comments should be in English (standard practice)
- Polish comments only when explaining Polish-specific features or context
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.
- 2mo ago First seen · 84 lines · 529 tokens per session scan A 345e7c7c47fa
documentation is a cursor rule published in the GitHub repository lukaszzychal/mcp-doc-generator (2 stars, last pushed 11mo ago), licensed MIT. It adds 529 tokens to every session, about $0.0021 per session on Opus 5.5. 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 cursor rules, from other repositories
archgate-governance
Archgate ADR governance — enforces architecture decision records.
ai_software_architect_reviews
How to conduct AI Software Architect reviews: full, specialist, and implementation reviews and their output format.
ai_software_architect_structure
Directory layout and file conventions under .architecture/ (members, decisions, reviews, principles).
ai_software_architect_usage
Core AI Software Architect commands: creating ADRs, requesting reviews, consulting specific architects, checking architecture status.
ai_software_architect_overview
AI Software Architect framework overview: what the framework is and how to work with it in this project.
ai_software_architect_setup
How to set up and customize the AI Software Architect framework in this project (setup command, member customization, updates).