claude-code-best-practices: Skill for Claude Code

.claude/skills/conventional-commits/SKILL.md

conventional-commits is a skill for Claude Code from awattar/claude-code-best-practices. It costs 53 tokens per session (358 once invoked), scanned A, original, MIT.

A commit-message guide for Git, the version-control tool used to track code changes. It applies this repository’s required format, including change type, optional GitHub issue reference, and one logical change per commit.

In plain words
What is it for?
Use it whenever you create a Git commit in this repository. It helps format single-line or multi-line messages correctly and separate unrelated changes into different commits.
Why use it?
It prevents inconsistent commit messages and makes the project history easier to understand. It also avoids extra author or generated-by lines that the repository does not allow.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is awattar/claude-code-best-practices's own configuration. It tells Claude Code how to work on claude-code-best-practices itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-best-practices configures →

Reuse

Borrowing it

Nothing to install: this file belongs to awattar/claude-code-best-practices. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/awattar/claude-code-best-practices/main/.claude/skills/conventional-commits/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/awattar/claude-code-best-practices

Made for: Claude Code.

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 conventional-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/awattar/claude-code-best-practices/conventional-commits.svg)](https://agentmods.dev/skills/awattar/claude-code-best-practices/conventional-commits)
Your own site
<a href="https://agentmods.dev/skills/awattar/claude-code-best-practices/conventional-commits"><img src="https://agentmods.dev/badge/skills/awattar/claude-code-best-practices/conventional-commits.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 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 $0.00053 $0.00358
Opus 5 $0.00026 $0.00179
Sonnet 5 $0.00011 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 8d ago against content hash 4de271cbe951, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

conventional-commits 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 8d 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.

.claude/skills/conventional-commits/SKILL.md · 43 lines

What it actually says

Conventional Commits

When creating any git commit in this repository, follow the project's commit convention. Unlike the /commit command (which the user invokes explicitly), this skill applies automatically whenever a commit message is being authored.

Format

Single-line, when a GitHub issue applies:

<type>: (#<issue_number>) <issue_name> - <description>.

Single-line, when no GitHub issue applies:

<type>: <description>.

Multiline, when the change spans multiple concerns:

<type>: (#<issue_number>) <issue_name>:
- <description_line_1>.
- <description_line_2>.

Rules

  • <type> is exactly one of: New feature, Fix issue, Other.
  • Single-line messages end with .; the first line of a multiline message ends with :.
  • Every bullet starts with - and ends with ..
  • Use present tense, imperative mood ("add feature", not "added feature").
  • Keep commits atomic — one logical concern per commit. Split unrelated changes into separate commits.
  • NEVER add trailers such as "Generated with Claude Code", author info, or co-author lines.

References

  • Full template with examples: .gitmessage
  • Commit-splitting guidance and workflow integration: .github/COMMIT_CONVENTION.md
  • For an interactive, guided commit flow, use the /commit command.
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. 8d ago First seen · 43 lines · 53 tokens per session scan A 4de271cbe951

Subscribe to this mod's changes

conventional-commits is a skill published in the GitHub repository awattar/claude-code-best-practices (251 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 358 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.