wb-commit

A commit workflow for AI-assisted development using Semantic Commits, a format that describes the type of change in each commit. It also defines a process for creating pull requests with GitHub CLI.

In plain words
What is it for?
Use it to prepare context-based commits, check commit formatting, and create pull requests through GitHub CLI.
Why use it?
It keeps commits grouped by code context and helps prevent accidental pushes directly to the `main` branch.

Command

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 commands/whitebeardit/.cursor/wb-commit
Clone the repo
git clone --depth 1 https://github.com/whitebeardit/.cursor
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,276 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 $0.00000 $0.02276
Opus 5 $0.00000 $0.01138
Sonnet 5 $0.00000 $0.00455
Haiku 4.5 $0.00000 $0.00228

Measured 2d ago against content hash 7eb189222b06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wb-commit 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.

commands/wb-commit.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wb-commit

Use the agent for AI-assisted commits

Para fluxo de commits assistido por IA, use o agent /agt-dev-commit. Ele aplica a skill .cursor/skills/shared/skill-conventional-commits/SKILL.md (formato, detecção de contexto, checklist, validação) e usa GitHub CLI (gh pr create) para criação de PRs — nunca git push origin main.

O conteúdo abaixo serve como referência (regra para colar em Cursor Rules, exemplos, troubleshooting) e complementa o agent e a skill.


Objective

Ensure that every commit follows the Semantic Commits pattern (compatible with semantic-release) and that commits are made by context (grouping by module/layer/folder). Also prohibit push to main branch without explicit authorization.


Rule summary (for Cursor / Rules)

Suggested rule name: commit-policy-semantic-context

For the full process (context detection, grouping, checklist, output format), use the agent /agt-dev-commit or read the skill .cursor/skills/shared/skill-conventional-commits/SKILL.md. Summary:

  1. Before committing: Read AGENTS.md if it exists; detect context from folder structure/namespaces; group changed files by context.
  2. Format: <type>(<scope>): <subject> — types: feat | fix | docs | style | refactor | perf | test | build | ci | chore | revert; scope = context/module; subject in English, imperative, no period.
  3. Context-based: One commit per context when possible; don't mix types in the same context; order by dependency (innermost first).
  4. Checklist: Validate format, scope, subject (English, imperative), same context; no accidental format/linter mix.
  5. Push/PR: Never push to main without explicit phrase AUTORIZO PUSH NA MAIN. Use feature branch + gh pr create for PRs.

When to use BREAKING CHANGE

If there's a contract/API break:

  • Use ! in the type: feat(api)!: rename endpoint for ...
  • And add footer:
    BREAKING CHANGE: <short explanation in English>
    

Read the full file on GitHub · 271 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 · 271 lines · 0 tokens per session scan A 7eb189222b06

Subscribe to this mod's changes

wb-commit is a command published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,276 tokens. 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.