commit

A workflow for staging current changes and creating a Git commit with a conventional message. Conventional commits use labels such as feat, fix or docs to make project history easier to understand.

In plain words
What is it for?
Use it to create a feature branch when needed, stage selected files explicitly and commit changes without pushing them.
Why use it?
It standardises commits and helps avoid accidentally including sensitive files or pushing changes when only a local commit is wanted.

Skill for Claude CodeCodex

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 skills/afx-team/hebb-mind/commit
Any agent
npx skills add afx-team/hebb-mind --skill commit
Clone the repo
git clone --depth 1 https://github.com/afx-team/hebb-mind

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,739 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 $0.00030 $0.02739
Opus 5 $0.00015 $0.01370
Sonnet 5 $0.00006 $0.00548
Haiku 4.5 $0.00003 $0.00274

Measured yesterday against content hash cb13fc4e4781, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

.claude/skills/commit/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Current Changes

Stage and commit pending changes with a conventional-commits message. Does not push. For push + PR, use /push-to-github after.

This repo follows conventional-commits for a consistent history that maps cleanly onto the manually-maintained CHANGELOG.md sections (Added / Fixed / Performance / Changed / Documentation). Releases are manual — versioning and the changelog are bumped by hand on release (the release-please automation was removed).


Hard rules (MUST)

  • MUST use conventional-commits format. Type is one of: feat, fix, refactor, perf, docs, chore, test, build, ci, style, revert.
  • MUST NOT git commit --amend, git reset, git push, git config, git rebase -i, git commit --no-verify.
  • MUST NOT commit files matching: .env*, *.key, *.pem, id_rsa*, credentials*, secrets*, *.db (incl. hebb.db), .claude/scheduled_tasks.lock, any file with secret / password / token in the name. If git status shows any, abort and ask the user.
  • MUST stage explicitly by path (git add <paths>) — never bare git add . / git add -A. List what will be staged first.
  • MUST create a new feature branch when current branch is main (or master). MUST NOT commit directly to main.
  • MUST show the generated commit message to the user and get confirmation before running git commit.
  • MUST follow the project's CLAUDE.md — but this skill only ships code that's already in the working tree; it does not author new code.

Pre-flight (run in parallel)

git rev-parse --git-dir                    # in a git repo?
git rev-parse --abbrev-ref HEAD            # current branch
git status --porcelain                     # working tree state
git log -5 --pretty=format:'%s'            # recent commit style reference

If not a git repo → exit.


Workflow

Step 1 — Classify state

From git status --porcelain:

  • If output is empty → nothing to commit. Print "working tree clean" and exit.
  • Otherwise → continue to Step 2.

Read the full file on GitHub · 289 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. yesterday First seen · 289 lines · 30 tokens per session scan A cb13fc4e4781

Subscribe to this mod's changes

commit is a skill published in the GitHub repository afx-team/hebb-mind (50 stars, last pushed 29d ago), licensed MIT. It adds 30 tokens to every session and 2,739 once invoked, about $0.0002 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.