frequent-commit-strategy

A rule that divides software implementation into a sequence of small commits, with tests and documentation for each stage. A commit is a saved group of code changes.

In plain words
What is it for?
Planning commits for project setup, core logic, integration, error handling, and final checks using conventional commit labels.
Why use it?
Small, testable steps make it easier to check progress and identify which change caused a problem.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/seanlf/weather-mcp/frequent-commit-strategy
Clone the repo
git clone --depth 1 https://github.com/SeanLF/weather-mcp

Made for: Cursor.

Per session 891 This file is loaded in full into every session.
When invoked 891 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00891 $0.00891
Opus 5 $0.00445 $0.00445
Sonnet 5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 2d ago against content hash 2db2efdce73a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frequent-commit-strategy 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.

.cursor/rules/frequent-commit-strategy.mdc · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

filters:

  • type: event pattern: "implementation_plan"
  • type: content pattern: "(?i)(implement|develop|create|build)"

actions:

  • type: transform pattern: "^.*$" replacement: |

    Implementation Plan

    Conventional Commit Sequence

    {original_content}

    Commit Structure

    1. feat: add initial project structure

      • Tests: Basic smoke tests
      • Testable state: Can verify structure is correct
      • Format: feat(module): add initial project structure
    2. feat: implement core business logic

      • Tests: Unit tests for core algorithms
      • Testable state: Core functions work in isolation
      • Format: feat(core): implement [feature] business logic
    3. feat: integrate component connections

      • Tests: Integration tests for component interaction
      • Testable state: Components work together
      • Format: feat(integration): connect [componentA] with [componentB]
    4. fix: add comprehensive error handling

      • Tests: Error condition tests
      • Testable state: System handles failures gracefully
      • Format: fix(error-handling): add validation for [scenario]
    5. chore: finalize implementation

      • Tests: Performance tests, documentation validation
      • Testable state: Ready for production
      • Format: chore(release): finalize documentation and optimization
  • type: suggest message: | For effective implementation planning:

    1. Break work into small, testable commits
    2. Use conventional commit format: type(scope): description
    3. Choose the right type: feat, fix, docs, style, refactor, perf, test, chore
    4. Define a testable state for each commit
    5. Write tests before or alongside code

examples:

  • input: | Implement a new user authentication system. output: |

    Implementation Plan

    Conventional Commit Sequence

    1. feat(user): add user model with authentication fields
    2. feat(auth): implement password hashing and validation
    3. feat(auth): create authentication service with login/logout
    4. feat(session): add session management functionality
    5. feat(middleware): implement authentication middleware
    6. feat(api): create login/logout endpoints
    7. fix(auth): add comprehensive error handling
    8. feat(security): implement rate limiting protection
    9. docs(auth): add documentation and integration examples

    Commit Structure

    1. feat(user): add user model with authentication fields

      • Tests: Schema validation tests
      • Testable state: Can create users with auth fields
      • Format: feat(user): add user model with authentication fields
    2. feat(auth): implement password utilities

      • Tests: Hash generation and verification tests
      • Testable state: Can hash and verify passwords
      • Format: feat(auth): implement password hashing and validation
    3. feat(auth): create authentication service

      • Tests: Authentication flow tests with mocks
      • Testable state: Service correctly authenticates valid credentials
      • Format: feat(auth): create login/logout authentication service
    4. feat(session): add session management

      • Tests: Session creation, validation, expiration tests
      • Testable state: Sessions work properly with timeouts
      • Format: feat(session): add user session handling with timeouts
    5. feat(middleware): implement auth middleware

      • Tests: Middleware correctly authenticates/rejects requests
      • Testable state: Protected routes require authentication
      • Format: feat(middleware): implement route authentication

Read the full file on GitHub · 113 lines

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.

  1. 2d ago First seen · 113 lines · 891 tokens per session scan A 2db2efdce73a

Subscribe to this mod's changes

frequent-commit-strategy is a cursor rule published in the GitHub repository SeanLF/weather-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 891 tokens to every session, about $0.0045 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.