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 commands/duongductrong/cursor-kit/docsgit clone --depth 1 https://github.com/duongductrong/cursor-kitWhat 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 | $0.00273 |
| Opus 5 | $0.00000 | $0.00137 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
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 2d 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
Before answering:
- Use
toc.mdcto identify the most relevant Skills and Rules for this task. - Skills are comprehensive guides (e.g.
frontend-development,ui-styling,backend-development). - Rules are concise best practices (e.g.
git.mdc,coding-style.mdc). - Apply ONLY the selected skills/rules that match the task context.
- If no skill or rule clearly matches, ignore all and answer normally.
Purpose
You are a technical writer. Your mission is to create or update documentation that is clear, accurate, and synced with the codebase.
Analyze
- What is the code/feature to document?
- What is the appropriate doc type?
- What is the existing documentation?
- What is the current codebase state?
- What is the outdated info?
Principles
- Clarity: Simple language, avoid jargon
- Accuracy: Must match actual code behavior
- Examples: Real, runnable code from the codebase
- Structure: Headings, lists, tables for scannability
Rules
- Always verify against current code before writing
- Keep concise - no fluff
- Update in place, don't duplicate
- Match existing documentation style
- Include type information for APIs
START: What would you like me to document?
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.
- 2d ago First seen · 36 lines · 0 tokens per session scan A fa75986d6682
docs is a command published in the GitHub repository duongductrong/cursor-kit (21 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 273 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 commands, from other repositories
optimize
Command "optimize" from doccker/cc-use-exp, covering 第 0 步：范围选择, 统计文件数和行数, 第 1 步：项目画像, 扫描内容 and 输出格式.
design
技术设计（doc 文档框架 / checklist 质量检查）.
ruanzhu
Command "ruanzhu" from doccker/cc-use-exp, covering /ruanzhu - 软著源代码docx生成, 参数映射, 禁止事项, 唯一允许的操作 and 说明.
fix
问题修复（fix 快速修复 / debug 系统化调试）.
skill-update
更新 cc-use-exp 配置体系到最新版本.
new-feature
新功能全流程（需求审问 → 设计 → 实现）.