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/mtwn105/decipher-research-agent/main-rulegit clone --depth 1 https://github.com/mtwn105/decipher-research-agentWhat 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 | $0.00336 | $0.00336 |
| Opus 5 | $0.00168 | $0.00168 |
| Sonnet 5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
main-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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cursorrules — 98% identical, 5 lines differ
What it actually says
You are an expert in Python, FastAPI, and scalable API development.
Here are some best practices and rules you must follow:
-
Python Version: Python 3.12
-
Frameworks and Tools:
pydanticfastapisqlalchemyuvfor dependency managementlogurufor logging
Coding Standards
- Use Meaningful Names: Choose descriptive variable, function, and class names.
- Follow PEP 8: Adhere to the Python Enhancement Proposal 8 style guide for formatting.
- Use Docstrings: Document functions and classes with docstrings to explain their purpose.
- Keep It Simple: Write simple and clear code; avoid unnecessary complexity.
- Use List Comprehensions: Prefer list comprehensions for creating lists over traditional loops when appropriate.
- Handle Exceptions: Use try-except blocks to handle exceptions gracefully.
- Use Type Hints: Utilize type hints for better code clarity and type checking.
- Avoid Global Variables: Limit the use of global variables to reduce side effects.
- Write Minimal Code: Only write the minimum code necessary to achieve the goal. Avoid overengineering.
- Don't Modify Other Files Without Permission: Do not make changes in files you weren’t explicitly asked to edit.
Important: Do not write any code until you're at least 95% confident in the requirement. Ask for clarification if needed.
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.
- 3d ago First seen · 34 lines · 336 tokens per session scan A ded3188a36c4
main-rule is a cursor rule published in the GitHub repository mtwn105/decipher-research-agent (152 stars, last pushed 1y ago), licensed MIT. It adds 336 tokens to every session, about $0.0017 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
python-agent-api
Python conventions for agent/ and api/.
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
010-python-tooling
Python tooling and dependency conventions for plugin-eval and tools/.
type_layer_rules
Type layer rules for TypeScript type definitions and interfaces.
english_comments
Enforce English-only comments and docstrings across the codebase.
python
when writing python.