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/wiggitywhitney/mcp-commit-story/docstring_standardsgit clone --depth 1 https://github.com/wiggitywhitney/mcp-commit-storyWhat 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 | $0.00551 | $0.00551 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
docstring_standards 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docstring Standards
Core Principle
Write docstrings that are succinct and direct - avoid verbose explanations.
Docstring Requirements
- Succinct communication - Essential information only, no verbose explanations
- Direct language - Get to the point quickly
- Follow @documentation forbidden content rules:
- No task references or historical processes
- No abstract corporate speak
- No development journey narratives
- External reader accessible - Assume zero project knowledge but keep it brief
- Practical focus - What they need to know, not extensive examples
Structure Guidelines
- Brief description - One clear sentence about what the function does
- Essential args/returns - Key parameters and return values only
- Minimal examples - Only when necessary for clarity
- No extensive prerequisites - Basic requirements only
Examples
✅ Good Docstring
def generate_daily_summary(date: str) -> Optional[DailySummary]:
"""Generate a daily summary from journal entries.
Args:
date: Date string in YYYY-MM-DD format.
Returns:
DailySummary object or None if no entries found.
"""
❌ Avoid Verbose Docstrings
def generate_daily_summary(date: str) -> Optional[DailySummary]:
"""Generate a daily summary from journal entries.
This function orchestrates the complete workflow for generating daily summaries
from journal entries. It handles the entire process from loading configuration
to processing entries through AI and saving the final formatted results.
## Prerequisites
- Journal files must exist in the expected directory structure
- Configuration file must be properly set up with journal paths
- AI provider must be configured with valid API keys
## Usage Examples
```python
# Generate for today
summary = generate_daily_summary("2025-01-15")
# Handle the result
if summary:
print(f"Generated: {summary['summary']}")
else:
print("No entries found")
```
## Technical Context
This function was created to replace the MCP-based approach...
"""
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 · 76 lines · 551 tokens per session scan A e686e7d90508
docstring_standards is a cursor rule published in the GitHub repository wiggitywhitney/mcp-commit-story (15 stars, last pushed 1y ago), licensed MIT. It adds 551 tokens to every session, about $0.0028 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_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.
fastapi-production-architecture-cursorrules-prompt-file
Cursor rules for FastAPI services with router/service/repository boundaries, typed provider adapters, bulkhead isolation, idempotency, and domain exceptions.
dask
This guide provides opinionated, actionable best practices for writing performant, maintainable, and idiomatic Dask code, focusing on real-world scenarios and modern patterns.
django
Definitive guidelines for writing maintainable, performant, and secure Django applications, emphasizing modern best practices, clear code organization, and efficient patterns.
anyio
Definitive guidelines for writing robust, maintainable, and backend-agnostic asynchronous Python code using AnyIO. Prioritize structured concurrency and native AnyIO primitives.
sqlmodel
Satisfying the type checker when working with SQLModel.