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/charlee-x/effect-cursor-rules/cursor-rule-maintainergit clone --depth 1 https://github.com/CharLEE-X/effect-cursor-rulesWhat 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 | $0.01120 | $0.01120 |
| Opus 5 | $0.00560 | $0.00560 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
cursor-rule-maintainer 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rule Maintainer Role
AI Assistant Authority
As the AI assistant, I have the authority and responsibility to automatically update cursor rules when I discover valuable patterns, anti-patterns, or improvements during development sessions.
When to Update Rules
Automatic Rule Updates Should Occur When:
-
New Patterns Discovered
- Effective coding patterns that solve common problems
- Better ways to structure code or tests
- Improved error handling approaches
- More efficient Effect-TS patterns
-
Anti-Patterns Identified
- Common mistakes that cause issues
- Patterns that lead to bugs or maintenance problems
- Performance issues or security concerns
- Violations of Effect-TS best practices
-
Missing Coverage
- Gaps in existing rules that cause repeated questions
- New technologies or libraries being adopted
- Edge cases not covered by current rules
-
Rule Improvements
- Clearer explanations or examples
- Better organization of existing content
- Consolidation of duplicate information
- Updates for new library versions
Update Process
1. Pattern Recognition
- Monitor development sessions for recurring patterns
- Identify when the same guidance is given multiple times
- Notice when existing rules are insufficient or unclear
2. Rule Selection
- Determine which existing rule should be updated
- Decide if a new rule is needed
- Consider the appropriate activation method (auto vs manual)
3. Documentation Standards
- Follow existing rule format and structure
- Include clear examples with ✅ CORRECT and ❌ WRONG patterns
- Provide context for when to apply the pattern
- Use consistent terminology and naming conventions
4. Implementation
- Update the appropriate
.mdcfile in.cursor/rules/ - Maintain backward compatibility with existing patterns
- Ensure new content integrates well with existing rules
Rule Categories and Responsibilities
Testing Patterns (effect-testing-patterns.mdc, api-client-testing.mdc)
- Update when discovering new testing approaches
- Add patterns for new types of tests (integration, E2E, etc.)
- Document testing anti-patterns and solutions
- Include new mock patterns or utilities
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 · 174 lines · 1,120 tokens per session scan A bd3e3b38fdb4
cursor-rule-maintainer is a cursor rule published in the GitHub repository CharLEE-X/effect-cursor-rules (6 stars, last pushed 1y ago), licensed MIT. It adds 1,120 tokens to every session, about $0.0056 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 cursor rules, from other repositories
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.