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/steipete/agent-rulesWrote 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/steipete/agent-rules/update-docs)<a href="https://agentmods.dev/rules/steipete/agent-rules/update-docs"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/update-docs/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/steipete/agent-rules/update-docs"><img src="https://agentmods.dev/badge/rules/steipete/agent-rules/update-docs.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 | $0.01833 | $0.01833 |
| Opus 5.5 | $0.00733 | $0.00733 |
| Sonnet 5.5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
update-docs 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 1mo 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Documentation
You will generate LLM-optimized documentation with concrete file references and flexible formatting.
Your Task
Create documentation that allows humans and LLMs to:
- Understand project purpose - what the project does and why
- Get architecture overview - how the system is organized
- Build on all platforms - build instructions with file references
- Add features/subsystems - following established patterns with examples
- Debug applications - troubleshoot issues with specific file locations
- Test and add tests - run existing tests and create new ones
- Deploy and distribute - package and deploy the software
Required Documentation Structure
Each document MUST include:
- Timestamp Header - Hidden comment with last update timestamp
- Brief Overview (2-3 paragraphs max)
- Key Files & Examples - Concrete file references for each major topic
- Common Workflows - Practical guidance with file locations
- Reference Information - Quick lookup tables with file paths
Timestamp Format
Each generated file MUST start with:
<!-- Generated: YYYY-MM-DD HH:MM:SS UTC -->
Process
You will:
- Analyze the codebase systematically across 7 key areas (merging development+patterns)
- Create or update docs in
docs/*.mdwith concrete file references - Synthesize final documentation into a minimal, LLM-friendly README.md
- Eliminate all duplication across files
Analysis Methodology
For each area, agents should:
- Examine key files: Look for build configs, test files, deployment scripts, main source files
- Extract file references: Note specific files, line numbers, and examples
- Identify patterns: Find repeated structures, naming conventions, common workflows
- Make content LLM-friendly: Token-efficient, reference-heavy, practical examples
Specific File Requirements
Issue the following Task calls in parallel:
Project Overview (docs/project-overview.md):
STRUCTURE:
- Overview: What the project is, core purpose, key value proposition (2-3 paragraphs)
- Key Files: Main entry points and core configuration files
- Technology Stack: Core technologies with specific file examples
- Platform Support: Requirements with platform-specific file locations
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.
- 1mo ago First seen · 198 lines · 1,833 tokens per session scan A c27f72c68377
update-docs is a cursor rule published in the GitHub repository steipete/agent-rules (5,675 stars, last pushed 5mo ago), licensed MIT. It adds 1,833 tokens to every session, about $0.0073 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 2026-08-30.
Other cursor rules, from other repositories
paperfit
PaperFit project rule for LaTeX visual typesetting optimization.
turborepo
Turbo task-graph rationale, query graph primitives, and signed remote-cache key provisioning.
react
React 19 SPA - client-only, layout and #/ imports, no fetch in useEffect, Compiler memo policy, providers, splitting, React Doctor.
previews
Cloudflare Worker Previews pipeline - credential-free Preview build then cf previews deploy, cf previews delete, Wrangler-only secrets, Access before arming, agent loop.
workers-cache
Workers Cache - Cache-Control, gateway exports cache off, RPC vs fetch.
boundaries
Package dependency boundaries - tag map and enforced invariants.