git-conventions

git-conventions is a skill for Claude Code, Codex from lossless-group/lossless-agent-skills. It costs 75 tokens per session (3,116 once invoked), scanned A, original, MIT.

A set of rules for writing Git commit messages, which are notes that describe changes made to a code project. It defines a consistent header format, action words, effort groupings, and explanatory message bodies.

In plain words
What is it for?
Use it when writing or reviewing commits, teaching collaborators how to describe changes, or deciding how to group several related updates in one message.
Why use it?
Inconsistent commit messages make project history hard to search and understand. These rules help developers quickly see what changed and why.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it when writing or reviewing commits, teaching collaborators how to describe changes, or deciding how to group several related updates in one message.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lossless-group/lossless-agent-skills/git-conventions
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.

Any agent
npx skills add lossless-group/lossless-agent-skills --skill git-conventions
Clone the repo
git clone --depth 1 https://github.com/lossless-group/lossless-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for git-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/git-conventions/github.svg)](https://agentmods.dev/skills/lossless-group/lossless-agent-skills/git-conventions)
Your own site
<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/git-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/git-conventions/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for git-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/git-conventions"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/git-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.03116
Opus 5 $0.00037 $0.01558
Sonnet 5 $0.00015 $0.00623
Haiku 4.5 $0.00007 $0.00312

Measured 9d ago against content hash 27e1a6be1d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

git-conventions/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Conventions

The Lossless Group's conventions for git commit messages — making history readable, searchable, and useful for future-you.

Status: Initial scaffold (May 2026) — documenting observed patterns from lossless-monorepo.

When to use this skill

  • Writing commit messages (any repo)
  • Reviewing commits before push
  • Teaching commit conventions to collaborators
  • User asks "how should I format this commit?"
  • User mentions "commit message", "git conventions", "effort grouping"

Core Patterns

1. Header Syntax

Two accepted patterns:

Pattern A: Single effort grouping

{action}({effort-grouping}): {narrative description}

Pattern B: Multiple effort groupings or chained actions

{action}({effort-1}, {effort-2}): {narrative description}
{action}({effort-1}), {action}({effort-2}): {narrative description}

Examples:

feat(theme-system): Add vibrant mode verification checklist
fix(mode-switcher, theme.css): Vibrant mode now dark-based with neon effects
doc(README), skill(astro-knots): Update vibrant mode guidance

2. Common Action Verbs

Action When to use
feat New feature, new capability
fix Bug fix, correction
doc Documentation changes
refactor Code restructure without behavior change
style Formatting, whitespace (no logic change)
test Adding/updating tests
chore Maintenance, deps, tooling
skill Skill file changes (lossless-skills repo)
changelog Changelog entry added/updated

3. Effort Groupings

What is an effort grouping? The part of the codebase this commit touches — a package, a site, a system, a concern.

Examples:

  • skill(theme-system) — changes to theme-system skill
  • feat(reach-edu-hub) — new feature in reach-edu-hub site
  • fix(mode-switcher, theme.css) — bug fix touching both files/systems
  • doc(README, CANDIDATES) — documentation changes in both files

Guideline: Use the most specific grouping that makes sense. If a commit touches multiple unrelated areas, consider splitting into multiple commits.

Read the full file on GitHub · 327 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 327 lines · 75 tokens per session scan A 27e1a6be1d76

Subscribe to this mod's changes

git-conventions is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 16d ago), licensed MIT. It adds 75 tokens to every session and 3,116 once invoked, about $0.0004 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.