datapages: Skill for Claude Code

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

git-commits is a skill for Claude Code from romshark/datapages. It costs 35 tokens per session (919 once invoked), scanned A, original, MIT.

A set of rules for writing commit messages in the Datapages project. It defines the title format, change types, breaking-change marker, description style, and line wrapping.

In plain words
What is it for?
Use it to write feature, fix, refactor, test, documentation, and other Git commit messages, including breaking changes.
Why use it?
It makes commit history consistent and tells maintainers when a change may break an application-facing API. It also avoids descriptions that merely repeat what the diff already shows.

Skill for Claude Code

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

This is romshark/datapages's own configuration. It tells Claude Code how to work on datapages 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 datapages configures →

Reuse

Borrowing it

Nothing to install: this file belongs to romshark/datapages. 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/romshark/datapages/main/.claude/skills/git-commits/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/romshark/datapages

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 git-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/romshark/datapages/git-commits/github.svg)](https://agentmods.dev/skills/romshark/datapages/git-commits)
Your own site
<a href="https://agentmods.dev/skills/romshark/datapages/git-commits"><img src="https://agentmods.dev/badge/skills/romshark/datapages/git-commits/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-commits

Your own site · 80×15
<a href="https://agentmods.dev/skills/romshark/datapages/git-commits"><img src="https://agentmods.dev/badge/skills/romshark/datapages/git-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 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 $0.00035 $0.00919
Opus 5.5 $0.00014 $0.00368
Sonnet 5.5 $0.00007 $0.00184
Haiku 4.5 $0.00003 $0.00092

Measured 25d ago against content hash b13064357934, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-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 25d 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/git-commits/SKILL.md · 67 lines

What it actually says

  • Respect writing.

  • Title: type: Summary, imperative, capitalized after the prefix, 50 characters or less, no trailing period.

  • Types: feat, fix, perf, refactor, test, chore, ci, docs. Suffix the type with ! for a breaking change.

  • Mark a change as breaking when it incompatibly changes an application-facing API. Changes to runtime/ APIs are not breaking: they are generator-facing, and datapages gen updates generated callers. Treat the root package, modules/ and generated APIs such as href and action as public APIs.

  • Wrap the description at 72 characters.

  • Imperative mood in the title, never past tense: Add cache, not Added cache or Adds cache. The description uses present tense and describes the code as it is now: Move foo to package buzz, not foo is now in package buzz. No first person, no we.

  • Don't paraphrase the code changes, the diff already shows them. The description is for what the diff can't show: why, scope, what was left out. Leave it empty when the title says everything.

  • Don't list the files touched, don't restate the title in longer words and don't close with a summary of the commit.

  • A commit that bundles several changes lists them as bullets, each with its own conventional prefix. List only the main changes. Tests, docs and call-site updates that come with a change are part of it, not separate bullets:

    feat: Add funcFoo <- keep, this is the change
    docs: Add docs for funcFoo <- drop
    test: Add tests for funcFoo <- drop
    refactor: Use funcFoo everywhere <- drop
    test: Add benchmark to test funcFoo against funcBar <- drop
    
  • A breaking change ends with a BREAKING: block. It is the migration instruction: name every removed or renamed symbol as old -> new, and say what the caller has to do, 1 step per line. A caller must be able to migrate from this block alone, without reading the diff. Say plainly when a step is automatic (datapages gen regenerates it) and when it is manual. Every line is a step the caller takes. Never list what did not change: href is unchanged is a step to do nothing. When a step could be read as reaching further than it does, narrow the step instead of adding a line: write EvSubjPref<Event> -> EvPrefix<Event>, the prefix constants only, not ... unchanged on a line of its own.

  • A perf: commit quotes the measurement as before -> after.

  • No tool attribution or Co-Authored-By trailers.

Bad:

feat: added caching to the generator and updated some files

This commit adds a cache to the generator so that it is faster. I changed
internal/gen/gen.go, internal/gen/cache.go and internal/cmd/gen.go to add the
cache and wire it up. The cache stores parsed packages in a map keyed by import
path. Overall this makes the generator faster and cleaner.

Co-Authored-By: Some Tool <[email protected]>

Good:

perf: Cache parsed packages in the generator

Every `datapages gen` run reparsed all dependencies. The cache keys on
import path and file mod time, which is safe because the loader already
rejects stale build artifacts.

Watch mode still reparses on every event: invalidation for edits inside
the module isn't implemented yet.

40ms -> 12ms on example/classifieds.

Good, breaking change:

refactor!: Move HTTP core to runtime packages

BREAKING:
- `datapages.NewCore` -> `runtime/httpserve.NewCore`.
- `datapages.CoreConfig` -> `runtime/httpserve.Config`.
- Generated code: run `datapages gen`, no hand edits needed.
- Hand-written callers: import `github.com/romshark/datapages/runtime/httpserve`
  and update the 2 names above.
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. 25d ago Changed b13064357934
  2. 1mo ago First seen · 67 lines · 35 tokens per session scan A 3dc239567f9f

Subscribe to this mod's changes

git-commits is a skill published in the GitHub repository romshark/datapages (119 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 919 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.

Related

git-commits compared with skills from other repositories

git-commits next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
git-commitsromshark/datapagesSkill1192d agoMITA35Claude Code
commit-msgjrswab/axeSkill90915d agoApache-2.0A0Claude Code, Codex
git-commit-integrityirahardianto/awesome-agvSkill15823d agoMITA136Claude Code, Codex
pixiv-cli-developFlanChanXwO/pixiv-cliSkill132yesterdayMITA49Codex
commit-stagedGoldziher/ai-rulezSkill167yesterdayMITA23Claude Code
squash-commitGoldziher/ai-rulezSkill167yesterdayMITA27Claude Code
test-then-commitGoldziher/ai-rulezSkill167yesterdayMITA28Claude Code