contributing_workflow

A set of instructions for how contributors should communicate when discussing changes or suggestions.

In plain words
What is it for?
Use it when answering questions, proposing implementation choices, or guiding a discussion that needs the developer to choose an option.
Why use it?
It makes decisions easier to review by requiring alternatives, tradeoffs, and a recommendation before proceeding.

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/wiggitywhitney/mcp-commit-story/contributing_workflow
Clone the repo
git clone --depth 1 https://github.com/wiggitywhitney/mcp-commit-story

Made for: Cursor.

Per session 924 This file is loaded in full into every session.
When invoked 924 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 $0.00924 $0.00924
Opus 5 $0.00462 $0.00462
Sonnet 5 $0.00185 $0.00185
Haiku 4.5 $0.00092 $0.00092

Measured 2d ago against content hash 0c26a53e3e72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contributing_workflow 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/contributing_workflow.mdc · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributing Workflow Patterns

Essential Communication Pattern

ALWAYS provide options, tradeoffs, and recommendations when answering questions or making suggestions:

  • Options: Present 2-3 clear alternatives with descriptive names
  • Tradeoffs: Explain pros and cons for each option
  • Recommendations: State which option you recommend and why
  • Discussion: Wait for response before proceeding to next question

Example format:

Options:
- Option A: [Description] 
  - Tradeoff: [Pro vs Con]
- Option B: [Description]
  - Tradeoff: [Pro vs Con]

My recommendation: Option A because [reasoning]

What's your preference?

Communication Style Requirements

  • Ask ONE question at a time - never present multiple design decisions simultaneously
  • Provide options with tradeoffs - present 2-3 options with clear pros/cons analysis
  • Include recommendations - always state which option you recommend and why
  • Discuss before proceeding - wait for developer response and discussion before moving to next question
  • Be concise - avoid lengthy explanations, focus on essential information
  • Critical answers preferred - honest assessment over diplomatic responses
  • Direct communication - no unnecessary preamble or corporate speak
  • Concrete language - specific problems and solutions rather than abstract buzzwords

Two-Phase Task Creation Workflow

Phase 1: Create Parent Task

  • Create task file with complete header: ID, Title, Status, Dependencies, Priority, Description
  • Write clear Requirements section (what needs to be accomplished)
  • Add Notes section with any initial context or constraints
  • Include "Design Decisions for Future Consideration" section for open questions
  • Do NOT create subtasks yet - leave Subtasks section empty or with placeholder
  • Search codebase for similar implementations to understand existing patterns
  • Verify existing utilities before planning new functionality

Phase 2: Design Discussion and Subtask Creation

  • Discuss design decisions one question at a time
  • Update Notes section with "Design Decisions Made" as choices are finalized
  • Requirements may evolve during design discussions - update them as understanding improves
  • Convert Requirements section to checklist format once requirements are finalized
  • Create detailed subtasks only after design decisions are resolved
  • Add verification checklists to ALL subtasks using "[ ]" format (not "- [ ]")
  • Add "## Task Completion" section with "Final verification: [ ] All requirements above completed"

Read the full file on GitHub · 93 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 · 93 lines · 924 tokens per session scan A 0c26a53e3e72

Subscribe to this mod's changes

contributing_workflow is a cursor rule published in the GitHub repository wiggitywhitney/mcp-commit-story (15 stars, last pushed 1y ago), licensed MIT. It adds 924 tokens to every session, about $0.0046 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.