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/kfnzero/mantis-mcp-server/archive-examplesgit clone --depth 1 https://github.com/kfnzero/mantis-mcp-serverWhat 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 | $0.01774 |
| Opus 5 | $0.00000 | $0.00887 |
| Sonnet 5 | $0.00000 | $0.00355 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
archive-examples 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive Format Examples
⚠️ CORRECT FORMAT EXAMPLES ⚠️
Example 1: Web Application Feature
## Task: Todo Application Implementation (v1.0)
Last Updated: 2023-04-15
### Implementation Results
- Created a React-based Todo application with the following features:
- Add new todo items
- Mark todos as complete
- Delete todos
- Filter by status (all, active, completed)
- Store todos in localStorage for persistence
- Responsive design for mobile and desktop
- Dark/light theme toggle
- Keyboard accessibility
### Completed Testing
- Manually tested all CRUD operations
- Verified persistence works across page reloads
- Tested UI responsiveness on mobile and desktop
- Confirmed filter functionality works as expected
- Verified keyboard navigation works properly
- Tested theme toggle functionality
- Checked accessibility with screen reader
### Lessons Learned
- React state management using useState was sufficient for this app
- localStorage offers simple persistence but has limitations for larger apps
- CSS Grid provided an efficient layout system
- Using unique IDs for todos simplified tracking and updates
- Controlled components provide better form handling
- Theme implementation with CSS variables is flexible
- Accessibility requires planning from the beginning
### Documentation Updates
- Updated projectbrief.md with completed requirements
- Updated progress.md with completion status
- Updated activeContext.md to focus on the next feature
- Updated systemPatterns.md with component architecture
- Updated techContext.md with React implementation details
- Updated tasks.md to mark task as completed
Example 2: Backend API Feature
## Task: RESTful API Implementation (v1.0)
Last Updated: 2023-05-20
### Implementation Results
- Created a Node.js/Express RESTful API with the following features:
- CRUD operations for products and categories
- Authentication using JWT
- Role-based authorization
- Input validation with Joi
- Error handling middleware
- MongoDB integration with Mongoose
- Rate limiting for public endpoints
- API documentation with Swagger
### Completed Testing
- Unit tests for validation logic
- Integration tests for all endpoints
- Authentication flow testing
- Authorization tests for different roles
- Error handling tests
- Performance testing with basic load
- Manual testing with Postman
- Cross-origin request testing
### Lessons Learned
- Middleware pattern in Express enhances code organization
- JWT implementation requires careful security considerations
- MongoDB schema design impacts query performance
- Input validation should happen early in the request lifecycle
- Consistent error response format improves client experience
- Documentation-first approach helps clarify API design
- Environment configuration management is critical for deployment
### Documentation Updates
- Updated projectbrief.md with API specifications
- Updated progress.md with API completion status
- Updated activeContext.md to focus on frontend integration
- Updated systemPatterns.md with API architecture
- Updated techContext.md with backend dependencies
- Updated tasks.md to mark API implementation as complete
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 · 276 lines · 1,774 tokens per session scan A 84a6bc57d555
archive-examples is a cursor rule published in the GitHub repository kfnzero/mantis-mcp-server (10 stars, last pushed 12mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,774 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 2026-08-31.
Other cursor rules, from other repositories
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
rules
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
misc-documenting-learnings-and-clarifying-assumptions
Documenting Learnings and Clarifying Assumptions for Efficient Task Execution.