A set of rules for recording code changes with Git, a tool for tracking versions of files and collaborating on code. It covers branch names, commit messages, pull-request review, and related safeguards.

It helps create branches, write commits using Conventional Commits, open or review pull requests, and record breaking changes.

It prevents inconsistent change records and unsafe repository practices, such as pushing directly to the main branch or using unclear commit messages.

How techtankto/techtank-site configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to techtankto/techtank-site. 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/techtankto/techtank-site/main/.agents/skills/git/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/techtankto/techtank-site

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/techtankto/techtank-site/git/github.svg)](https://agentmods.dev/skills/techtankto/techtank-site/git)

Your own site

<a href="https://agentmods.dev/skills/techtankto/techtank-site/git"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/git/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/techtankto/techtank-site/git"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/git.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 738 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00738
Opus 5.5	$0.00000	$0.00295
Sonnet 5.5	$0.00000	$0.00148
Haiku 4.5	$0.00000	$0.00074

Measured 1mo ago against content hash e58aa0eddbce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git 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 1mo 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.

.agents/skills/git/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git

How change is recorded.

Workflow

Work on the branch defined for the task at hand. Never push directly to main.
Create new commits rather than amending. Never force-push any branch, no exceptions; never skip hooks without explicit permission.
Task PRs target their milestone branch; milestone PRs target the latest main. Work outside a milestone stays on a feature branch. No PR opens unless explicitly asked.

Conventional Commits

All commit subjects follow Conventional Commits:
```
<type>(<optional scope>): <imperative summary>
```
- Allowed types: feat, fix, docs, style, refactor, perf, test, build, ci, chore, revert.
- Scopes match the affected area: the surface (home), the layer (templates, tokens, constants), or the docs (prd, docs). Omit when global.
- Subject: ≤ 72 characters, lowercase, no trailing period.
- Body: explain the why when the diff alone doesn't.
- Breaking changes: ! suffix and a BREAKING CHANGE: footer for route moves, renames, or behavior changes.

Branch naming

Branches follow the same type vocabulary as commits:
```
<type>/<short-kebab-summary>
```
- ≤ 40 characters, lowercase, hyphen-separated.
- Milestone and task branches carry their identifiers: feat/m02-works, feat/m02-t04-works-ledger.
- Branches outside a milestone reference the affected area: fix/date-zoning, docs/initial-plan.

Attribution

No AI/agent attribution in commits, PRs, or issues: no Co-Authored-By: Claude/Codex, no "Generated with Claude Code" markers, no claude.ai/code session links.

Review

Read the project's own vendored skills before reviewing the diff. Skills under .claude/skills/ / .agents/skills/ are that project's actual, current standards, not generic advice; load the ones relevant to the changed files (components for a component diff, data for a constants/data change, nextjs for routing, etc.) and check the diff against what they specifically say before reaching for anything else.
Then apply conventional best practice: correctness, security, performance, test coverage, readability: the concerns a project's skills don't cover because they're universal rather than project-specific.
A skill deviation is a finding on its own, distinct from a generic style nit: name the skill and the rule it violates, not just "this looks off."
When a project has no vendored skills, or the change touches an area none of them cover, fall back to conventional best practice alone. Never invent a project standard that isn't written down anywhere.

Read the full file on GitHub · 63 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.

1mo ago Changed · -58 tokens per session e58aa0eddbce
2mo ago First seen · 63 lines · 58 tokens per session scan A 105e4351399d

Subscribe to this mod's changes

git is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 738 tokens. 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.

Commits Git and workflow

git next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gittechtankto/techtank-site	Skill	5	3d ago	MIT	A	0	Claude Code, Codex
create-prprisma/orm	Skill	48k	yesterday	Apache-2.0	A	48	Claude Code, Codex
git-commitThinkInAIXYZ/deepchat	Skill	6.4k	yesterday	Apache-2.0	A	15	Claude Code, Codex
repo-syncdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	25	Claude Code, Codex
engineer-bot-opsmakecindy/cindy	Skill	9.3k	yesterday	Apache-2.0	A	57	Claude Code, Codex
mcore-split-prNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	25	Claude Code
git-commit-writermergisi/awesome-openclaw-agents	Skill	4.1k	2d ago	MIT	A	53	Claude Code, Codex

techtank-site: Skill for Claude Code