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/inakianduaga/clockify-mcp/implementgit clone --depth 1 https://github.com/inakianduaga/clockify-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 | $0.00012 | $0.01378 |
| Opus 5 | $0.00006 | $0.00689 |
| Sonnet 5 | $0.00002 | $0.00276 |
| Haiku 4.5 | $0.00001 | $0.00138 |
Grade A, and why
implement 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Include these rules while IMPLEMENTATION/Coding. globs: alwaysApply: true
Before every code implementation/change ALWAYS do 2 things:
a. Read and understand the documentation in docs/ and tasks/
a. Get required code context from src and other codes at other places.
IMPLEMENTATION (ACT MODE/Code MODE):
[Step: 2]
- If needed initiate process.
- Use to Outline a detailed plan including component dependencies, architectural considerations before coding. Use to Explain all code changes, what each part does, and how it affects other areas.
- Provide a proposal that specifies: 1) what files, functions, or lines of code are being changed; 2) why the change is necessary (i.e. bug fix, improvement or new feature); 3) all of the directly impacted modules or files; 4) potential side effects; 5) a detailed explanation of any tradeoffs. </STRUCTURED PROPOSALS> </PLAN CODE>
[Step: 3]
- Document Current State in files specified by @memory.mdc
- What’s currently working?
- What’s the current error/issue?
- Which files will be affected?
- Plan Single Logical Change at a Time
- One logical feature at a time
- But fully resolve this one change by accomodating appropriate changes in other parts of the code.
- Adjust all existing dependencies and issues created by this change.
- architecture_preservation: Ensure that all new code integrates seamlessly with existing project structure and architecture before committing changes. Do not make changes that disrupt existing code organization or files. </INCREMENTAL ROLLOUTS>
- Simulation Testing
- Simulate user interactions and behaviors by performing dry runs, trace calls, or other appropriate methods to rigorously analyze the impact of proposed changes on both expected and edge-case scenarios.
- Generate feedback on all potential side effects. </SIMULATION ANALYSIS>
- Do not propose a change unless the simulation passes and verifies that all existing functionality is preserved, and if a simulation breaks, provide fixes immediately before proceeding. </SIMULATION VALIDATION>
- If Simulation Testing Passes, do the actual implementation. </MAKE CHANGES>
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 · 127 lines · 12 tokens per session scan A 03afe79d77a9
implement is a cursor rule published in the GitHub repository inakianduaga/clockify-mcp (14 stars, last pushed 1y ago), licensed MIT. It adds 12 tokens to every session and 1,378 once invoked, about $0.0001 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.