contextual-commit

A commit-writing guide that adds the reasoning behind code changes to standard Conventional Commits.

In plain words
What is it for?
Use it when committing code to write a standard commit subject plus structured lines explaining why the change was made and what shaped it.
Why use it?
A normal commit records what changed, while the surrounding intent, decisions, constraints, and lessons can disappear after the work is finished.

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/yamadashy/repomix/contextual-commit
Any agent
npx skills add yamadashy/repomix --skill contextual-commit
Clone the repo
git clone --depth 1 https://github.com/yamadashy/repomix

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,164 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 $0.00062 $0.02164
Opus 5 $0.00031 $0.01082
Sonnet 5 $0.00012 $0.00433
Haiku 4.5 $0.00006 $0.00216

Measured 2d ago against content hash e285c7f26f6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextual-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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/contextual-commit/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contextual Commits

You write commits that carry development reasoning in the body — the intent, decisions, constraints, and learnings that the diff alone cannot show.

The Problem You Solve

Standard commits preserve WHAT changed. The diff shows that too. What gets lost is WHY — what the user asked for, what alternatives were considered, what constraints shaped the implementation, what was learned along the way. This context evaporates when the session ends. You prevent that.

Commit Format

The subject line is a standard Conventional Commit. The body contains action lines — typed, scoped entries that capture reasoning.

type(scope): subject line (standard conventional commit)

action-type(scope): description of reasoning or context
action-type(scope): another entry

Subject Line

Follow Conventional Commits exactly. Nothing changes here:

  • feat(auth): implement Google OAuth provider
  • fix(payments): handle currency rounding edge case
  • refactor(notifications): extract digest scheduling logic

Action Lines

Each line in the body follows: action-type(scope): description

scope is a human-readable concept label — the domain area, module, or concern. Examples: auth, payment-flow, oauth-library, session-store, api-contracts. Use whatever is meaningful in this project's vocabulary. Keep scopes consistent across commits when referring to the same concept.

Action Types

Use only the types that apply. Most commits need 1-3 action lines. Never pad with noise.

intent(scope): ...

What the user wanted to achieve and why. Captures the human's voice, not your interpretation.

  • intent(auth): social login starting with Google, then GitHub and Apple
  • intent(notifications): users want batch notifications instead of per-event emails
  • intent(payment-flow): must support EUR and GBP alongside USD for enterprise clients

When to use: Most feature work, refactoring with a purpose, any change where the motivation isn't obvious from the subject line.

Read the full file on GitHub · 196 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 · 196 lines · 62 tokens per session scan A e285c7f26f6d

Subscribe to this mod's changes

contextual-commit is a skill published in the GitHub repository yamadashy/repomix (28,159 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 2,164 once invoked, about $0.0003 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 skills, from other repositories

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

git-commit

Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.

spinabot/brigade · 46 tokens

git-commit-integrity

Ensures every commit in a series is what it claims to be — a working, gate-passing snapshot in isolation, not just a slice of a working directory that happened to pass while other changes sat nearby. Covers verifying commit history after the fact, designing pre-commit hooks that check the commit rather than the…

irahardianto/awesome-agv · 136 tokens

commit

Group changes into one atomic commit, draft a Conventional Commit message in COMMITAGENTMSG, put it through an independent review and the commit-msg gates, confirm it with the operator, then commit and rebase. Use this skill whenever the user asks to commit work in a tbhb repo ("commit this," "commit the staged…

tbhb/vale-ai-tells · 86 tokens

codex-merge-pr

Squash merge a pull request. The commit message comes from this workflow rather than from GitHub, whose own version concatenates every commit on the branch into text no linter ever reads. A briefing script prints the published description, every commit the squash collapses, and the diffstat, then leaves a…

tbhb/vale-ai-tells · 121 tokens

merge-pr

Squash merge a pull request. The commit message comes from this workflow rather than from GitHub, whose own version concatenates every commit on the branch into text no linter ever reads. A briefing script prints the published description, every commit the squash collapses, and the diffstat, then leaves a…

tbhb/vale-ai-tells · 118 tokens