create-commit-message

A rule for writing Git commit messages in the Conventional Commits format. That format labels changes with types such as feature, bug fix, documentation, or testing.

In plain words
What is it for?
Use it when creating or suggesting a commit message, including the change type, optional area, and a short imperative description.
Why use it?
It makes commit history consistent and easier to understand, filter, and use in automated release workflows.

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/zackiles/cursor-config/create-commit-message
Clone the repo
git clone --depth 1 https://github.com/zackiles/cursor-config

Made for: Cursor.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 863 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00005 $0.00863
Opus 5 $0.00003 $0.00432
Sonnet 5 $0.00001 $0.00173
Haiku 4.5 $0.00001 $0.00086

Measured 2d ago against content hash 7114a3a95420, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-commit-message 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/global/create-commit-message.mdc · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Commit Messages With Convention Commit

All commit messages follow Conventional Commits standard when generating or suggesting commit messages.

Format

<type>(<scope>): <description>
  • Type: Defines the nature of the change.
  • Scope: Prefer domain- or module-level identifiers, not file names. Reflects logical grouping or feature boundary, not precise file paths.
  • Description: Written in imperative mood. One sentence.

Types

  • feat: A new feature.
  • fix: A bug fix.
  • docs: Documentation changes only.
  • style: Code formatting, no logic change.
  • refactor: Code restructuring, no behavior change.
  • perf: Performance improvements.
  • test: Adding or improving tests.
  • chore: Build process, dependencies, or auxiliary tools.
  • ci: CI/CD config or script changes.
  • build: Affects the build system or external dependencies

Examples

Example A (Change History)

Staged Changes:

  • Created a new file named src/auth/login.ts
  • Imported src/auth/login.ts into src/users/account.ts
  • Added a modal component class named 'loginForm'
  • Tracked a new test file named test/login.test.ts
  • Git dif of the documentation shows a new section named "# Logging In"

Output 1 (GOOD):

feat(users-account): add user authentication

Output 2 (BAD):

// No past tense. No periods at the end of the message. No file names for scope
feat(users-account.ts): added user authentication.

Example B (Change History)

Staged Changes:

  • Created validation schema in src/validation/product-schema.ts using Zod
  • Integrated schema into product API endpoint in src/routes/products.ts
  • Added unit tests in test/validation/product-schema.test.ts

Output 4 (GOOD):

feat(product-schema): add zod schema validation for product input

Output 4 (BAD):

// Avoid PascalCase. Avoid file extensions. Avoid stating the file path or using vague verbs.
feat(ProductSchema.ts): created validation for product input

Read the full file on GitHub · 114 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 · 114 lines · 5 tokens per session scan A 7114a3a95420

Subscribe to this mod's changes

create-commit-message is a cursor rule published in the GitHub repository zackiles/cursor-config (17 stars, last pushed 1y ago), licensed MIT. It adds 5 tokens to every session and 863 once invoked, about $0.0000 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.

Related

Other cursor rules, from other repositories

react-floating-ui

React 19 + Floating UI 0.27 conventions and pitfalls for floating/anchored components (tooltips, popovers, context menus, dialogs, selects).

docs-plus/docs.plus · 0 tokens

agent-rules-and-memory

Where this repo's agent rules and durable memory live, and the order to read them. Applies to every task.

docs-plus/docs.plus · 977 tokens

design-system

Authoritative source: .cursor/docs/design-system.md. Read it before any UI/theme/styling work; the design-system skill in .cursor/skills/ is the working protocol. Behavioral invariants (pad geometry, motion wiring, scrims, sheet systems) live in apps/webapp/CLAUDE.md, which loads automatically under apps/webapp/.…

docs-plus/docs.plus · 0 tokens

miro-best-practices

MCP server for controlling Miro whiteboards with AI assistants.

olgasafonova/miro-mcp-server · 197 tokens

rule-generating-agent

This rule is essential for maintaining consistency and quality in rule creation across the codebase. It must be followed whenever: (1) A user requests a new rule to be created, (2) An existing rule needs modification, (3) The user asks to remember certain behaviors or patterns, or (4) Future behavior changes are…

appboypov/pew-pew-cli · 1,197 tokens

testing-mocks-spies-stubs-agent

Apply when writing unit tests that involve functions or modules with side effects (e.g., file system access, network requests, database interactions, timers, complex dependencies). Guides the use of test doubles like mocks, spies, and stubs (using frameworks like Jest) to isolate the unit under test and control its…

appboypov/pew-pew-cli · 71 tokens