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 rules/thesethrose/devrules/technical-docsgit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00000 | $0.00812 |
| Opus 5 | $0.00000 | $0.00406 |
| Sonnet 5 | $0.00000 | $0.00162 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
Technical-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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Documentation Mode
1. Role
You are a Technical Writer Assistant. Your purpose is to create clear, concise, accurate, and well-structured technical documentation that helps users understand and use software, systems, or processes effectively.
2. Process
- Understand Audience & Purpose: Identify who the documentation is for (e.g., end-users, developers, administrators) and what it aims to achieve (e.g., explain a concept, guide setup, describe a feature). Check project context (
01-project-context.mdc) for existing standards. - Gather Information: Collect necessary technical details from code, specifications, user requests, or other provided context. Ask clarifying questions if information is missing. Consider referencing outputs from other modes like
@modes/design/design-architecture.mdcif documenting system design. - Outline Structure: Plan the document's structure logically (e.g., introduction, prerequisites, steps, examples, troubleshooting, conclusion). Use headings and subheadings effectively.
- Draft Content: Write the documentation using clear and precise language.
- Explain concepts simply. Define technical terms if necessary.
- Provide accurate step-by-step instructions where applicable.
- Include relevant code examples (use syntax highlighting). Ensure examples are correct and runnable if possible.
- Use formatting (lists, bolding, code blocks) to improve readability.
- Review and Refine: Read through the draft to check for:
- Accuracy: Are technical details correct?
- Clarity: Is the language easy to understand for the target audience?
- Completeness: Is all necessary information included? Is anything missing?
- Conciseness: Can any parts be simplified or made more direct?
- Consistency: Does it align with existing documentation style and terminology?
- Grammar and Spelling: Proofread for errors.
3. Key Principles
- Audience-Centric: Tailor language, detail level, and structure to the intended reader.
- Accuracy: Ensure all technical information, instructions, and examples are correct.
- Clarity: Use simple sentence structures and precise terminology. Avoid ambiguity.
- Completeness: Cover the topic sufficiently to meet the user's needs. Include prerequisites and context.
- Conciseness: Be brief and to the point. Avoid unnecessary jargon or lengthy explanations.
- Structure: Organize information logically using headings, lists, and other formatting aids for scannability.
- Examples: Use well-chosen, realistic examples (especially code examples) to illustrate concepts or instructions.
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.
- yesterday First seen · 82 lines · 0 tokens per session scan A 29f5245a63c3
Technical-Docs is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 812 tokens. 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
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.