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/paddyalton/gotask-mcp/tool-use-rulegit clone --depth 1 https://github.com/PaddyAlton/gotask-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/paddyalton/gotask-mcp/tool-use-rule)<a href="https://agentmods.dev/rules/paddyalton/gotask-mcp/tool-use-rule"><img src="https://agentmods.dev/badge/rules/paddyalton/gotask-mcp/tool-use-rule.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00316 |
| Opus 5 | $0.00000 | $0.00158 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
tool-use-rule 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 5d 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
As an expert-level Python developer, you understand that
- adhering to common coding standards is extremely important
- testing code properly is important: unit tests are essential and higher-order tests (functional and integration tests) may often be valuable
- careful type annotations and static type analysis can be extremely beneficial, ensuring that the greater freedom provided by dynamic typing doesn't cause problems
- automated tasks can help with all of the above
A tool will be provided to you that allows you to request a list of available automated tasks in the working project. You should run this tool before writing code, if you have not done so yet, being sure to pass the full path of the working project (obtained from user_data) as an argument.
You should then evaluate the list of rules and use the descriptions to decide contextually when to run specific tools. Some guidelines are provided below.
Important common rules
- after writing or editing code, you must run the 'fix' rule if it is available
- before signing off on changes, you must run the 'check' rule if it is available
These tools provide feedback. If they detect problems, you will resolve these problems and then run the tools again (iterating as needed).
These are top-level tools that run a number of sub-tools in sequence. It may be useful to run individual tools from time to time, for example the tools that run unit tests or static type checks.
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.
- 5d ago First seen · 25 lines · 316 tokens per session scan A ce3bbb162585
tool-use-rule is a cursor rule published in the GitHub repository PaddyAlton/gotask-mcp (4 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 316 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
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
python-llm-ml-workflow-cursorrules-prompt-file
Cursor rules for Python LLM & ML development with workflow integration.
python
Python best practices and patterns for modern software development with Flask and SQLite.
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
rich
Definitive guidelines for building robust, maintainable, and visually appealing Python CLI applications using the rich library.