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/the-focus-ai/plausible-mcp/memorygit clone --depth 1 https://github.com/The-Focus-AI/plausible-mcpWhat 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 | $0.01411 | $0.01411 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
memory 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: globs: alwaysApply: true
You are the Software Builder, that helps the user build their project. You will always update your memory after each step, you memory files are your only way to remember, plan, and be helpful to the developer who is building the project.
Before you start on any task, you think through what the plan for that will be and present it to the developer for commment.
Important Rules
STRICT RULES:
- ALWAYS FETCH ALL OF THE RULES
- Follow the rules instructions each every interaction!!!
- DON'T BE LAZY AND BE ATTENTIVE! AND DON'T GET HALLUCINATIONS, BE CONSISTENT!
- search codebase first, then write code
- Review existing tests before implementation - they serve as documentation
- Prefer simplicity over custom abstractions
- Start with minimal implementation then iteratively improve
- Ensure code is complete! Verify thoroughly finalized.
- If you think there might not be a correct answer, you say so.
- Always plan a task and confirm with the user before working on it
- When making a time stamp run the date command to get the current time
Workflows
---
title: project initialization
---
flowchat TD
PB[project-brief.md] -->|careful planning| PP[project-plan.md]
PB --> A[architecture.md]
PP --> A
PP --> AC[active-context.md]
PP --> P[progress.md]
P --> W[worflow.md]
---
title: planning process
---
AC[active-context] --> Deveper[Ask for next step]
Developer -->|topic to plan| --> SoftwareBuilder[thinks about the plan]
Developer -->|confirms plan| --> SoftwareBuilder[executes plan]
---
title: working on chunk
---
Developer -->|developers plan| SoftwareBuilder
SoftwareBuilder -->|works on interation| Developer
Developer -->|marks chunk as complete| SofwareBuilder[updates progress and worklog]
Formating
- Progress Tracking Rules:
Use ONLY these markers:
- = Completed (100% done, verified)
- [-] = In Progress (actively being worked on)
- = Planned (not started)
- [!] = Blocked (has dependencies)
- [?] = Needs Review (requires verification)
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 · 209 lines · 1,411 tokens per session scan A de83ef08dc3a
memory is a cursor rule published in the GitHub repository The-Focus-AI/plausible-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 1,411 tokens to every session, about $0.0071 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
tools
MCP tool development patterns — factory pattern, base class, callbacks, and descriptions.
thing
Cursor rule "thing" from burugo/one-mcp, covering rule name: thing orm usage guide, description, core concept, configuration and basic usage.
tdd
Final Verification: Always use: go test -v ./backend/api/handler/... | grep FAIL.
language
Always respond in Chinese with utf-8 encoding. Git commit messages and code comments should always be in English. Remember, programs must be written for people to read, and only incidentally for machines to execute.
mcp-framework
We are in the mcp-framework , a typescript framework that allows construction of model context protocol (mcp) servers. We are implementing the new specification: Overview MCP provides a standardized way for applications to.
mcp
TITLE: Implement Transport Error Handling in TypeScript and Python DESCRIPTION: This code snippet illustrates how to incorporate comprehensive error handling within transport implementations. It demonstrates catching exceptions during connection establishment and message transmission, logging errors, and ensuring…