git-conventions

Guidelines for creating commits and branches in a project’s Git repository.

In plain words
What is it for?
Choosing branch names, formatting commit messages, staging specific files, and avoiding force pushes, destructive commands, configuration changes, and secret files.
Why use it?
They reduce accidental data loss, inconsistent commit messages, unsafe branch operations, and the risk of committing secrets.

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/maless88/roadboard/git-conventions
Any agent
npx skills add Maless88/Roadboard --skill git-conventions
Clone the repo
git clone --depth 1 https://github.com/Maless88/Roadboard

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 315 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 $0.00042 $0.00315
Opus 5 $0.00021 $0.00158
Sonnet 5 $0.00008 $0.00063
Haiku 4.5 $0.00004 $0.00032

Measured 2d ago against content hash 09bffee706c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-conventions 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.

packages/agent-skills/git-conventions/SKILL.md · 28 lines

What it actually says

Git conventions

Commit only when the developer (or the task prompt) explicitly asks. Never on your own initiative.

Commit format

type(scope): description — types: feat, fix, docs, style, refactor, test, chore. Use a HEREDOC for multi-line messages so formatting stays clean.

Branches

  • main — stable, tagged releases
  • dev — default integration branch
  • feature/* — features · fix/* — bugfixes

Safety rules (non-negotiable)

  • Never update git config.
  • Never run destructive commands (push --force, reset --hard, checkout --, restore --, clean -f, branch -D) unless explicitly told.
  • Never use --no-verify or bypass commit signing.
  • Never force-push to main/master.
  • Create new commits — do not amend unless explicitly asked.
  • Stage specific files by name; avoid git add -A / git add ..
  • Never commit secrets (.env, credentials, any env/secrets.*).
  • Do NOT add Co-Authored-By: Claude or any Claude/Anthropic co-author trailer.
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 · 28 lines · 42 tokens per session scan A 09bffee706c0

Subscribe to this mod's changes

git-conventions is a skill published in the GitHub repository Maless88/Roadboard (2 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 315 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 2026-08-31.

Related

Other skills, from other repositories

speckit-git-commit

Auto-commit changes after a Spec Kit command completes.

UmarHassanKhan929/react-profiler-mcp · 18 tokens

speckit-git-initialize

Initialize a Git repository with an initial commit.

UmarHassanKhan929/react-profiler-mcp · 16 tokens

git-wrapup

Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts) and an annotated tag. Verify, commit, tag. Stops at "committed and tagged locally" — no push, no publish. The release-and-publish skill picks up from here. Distilled…

cyanheads/obsidian-mcp-server · 82 tokens

git-commit

Execute a git commit that follows semantic conventional-commits — type, optional scope, imperative subject in English under 70 chars, body explaining WHY. User-invoked via /git-commit or "/commit".

filipebraida/adonisjs-starter-kit · 47 tokens

french-commit-message

Génère un message de commit git en français au format Conventional Commits à partir des changements stagés. Récupère automatiquement le diff via git diff --staged. À utiliser quand l'utilisateur demande un commit message, message de commit, ou résumé de diff en français.

Swih/mistral-mcp · 57 tokens

commit-and-push

Stage, commit, and push changes without opening a PR. Use when the user says "commit and push", "commit these to a new branch", "push this branch", or wants a branch + commit summary but does not want PR creation. Distinct from yeet, which owns the commit + push + PR flow.

Kevin-Liu-01/Agent-Machines · 71 tokens