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.
npx agentmods add skills/medy-gribkov/arcana/git-workflownpx skills add medy-gribkov/arcana --skill git-workflowgit clone --depth 1 https://github.com/medy-gribkov/arcanaWrote 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.
[](https://agentmods.dev/skills/medy-gribkov/arcana/git-workflow)<a href="https://agentmods.dev/skills/medy-gribkov/arcana/git-workflow"><img src="https://agentmods.dev/badge/skills/medy-gribkov/arcana/git-workflow.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.02360 |
| Opus 5 | $0.00016 | $0.01180 |
| Sonnet 5 | $0.00006 | $0.00472 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
git-workflow 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commit Format
# BAD: vague, no type
git commit -m "changes"
# GOOD: clear type, scope, imperative mood
git commit -m "feat(auth): add OAuth2 login flow"
git commit -m "fix(api): handle null response in getUserData"
git commit -m "docs(readme): update installation steps"
Format: type(scope): description
Types: feat, fix, docs, style, refactor, perf, test, build, ci, chore
Breaking changes:
git commit -m "feat(api)!: remove deprecated v1 endpoints"
# Or in body:
git commit -m "feat(api): migrate to v2 endpoints
BREAKING CHANGE: v1 endpoints removed, use v2"
Setup Commit Linting
# Install commitlint
npm install --save-dev @commitlint/config-conventional @commitlint/cli
# Create config
cat > commitlint.config.js <<'EOF'
module.exports = { extends: ['@commitlint/config-conventional'] };
EOF
# Hook with Husky
npx husky add .husky/commit-msg 'npx --no -- commitlint --edit $1'
Merge vs Rebase Decision Tree
Question: Is the branch shared with others?
│
├─ YES → USE MERGE
│ └─ git merge feature-branch
│ (preserves branch history, safer for collaboration)
│
└─ NO → Ask: Do you want linear history?
│
├─ YES → USE REBASE
│ └─ git rebase main
│ (clean history, better for bisect)
│
└─ NO → USE MERGE
└─ git merge --no-ff feature-branch
(preserves feature branch context)
Rebase workflow for feature branches:
# Daily sync (before starting work)
git checkout feature-branch
git fetch origin
git rebase origin/main
# Interactive cleanup before PR
git rebase -i origin/main
# Squash "fix typo", "wip" commits
# After PR approval
git checkout main
git merge --ff-only feature-branch # or squash in GitHub UI
When rebase conflicts occur:
# BAD: panic and force push to main
git push --force origin main # NEVER DO THIS
# GOOD: resolve, test, continue
git rebase main
# Fix conflicts in files
git add resolved-file.js
git rebase --continue
npm test # Always test after resolving
git push --force-with-lease origin feature-branch
What ships with it
1 file 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.
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.
- 5d ago First seen · 373 lines · 32 tokens per session scan A f7ad9668da3f
git-workflow is a skill published in the GitHub repository medy-gribkov/arcana (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,360 once invoked, about $0.0002 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.
Other skills, from other repositories
shared-tooling-git-hooks
Husky v9 setup, lint-staged v16 patterns, commitlint with conventional commits, CI/production handling, monorepo setup, migration from v8.
git-hooks-setup
Use when setting up git hooks (pre-commit, commit-msg, pre-push) with husky or native hooks for linting, formatting, commit conventions, and secret scanning.
git-workflow-guide
Git workflow reference covering branch naming, commit message conventions, PR templates, merge strategies, and common operations — for consistent team collaboration.
pr
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
bailian-train-deploy
用百炼 CLI (bl) 走完"数据→微调训练→导出→部署→调用"的完整闭环,或跳过训练直接部署基座模型。支持文本模型(SFT/DPO/CPT)、音频 TTS 模型(CosyVoice)、图像生成模型(Wan2.7)和视频生成模型(Wan i2v/kf2v)微调。涵盖数据集校验/上传、创建微调任务、等待训练、导出最佳 checkpoint、创建推理部署、等待就绪、给出调用示例。当用户提到在百炼 / DashScope / 阿里云模型工作室上"训练模型""微调""fine-tune""finetune""部署模型""模型上线""把微调模型跑起来/调用""训练一个推理模型""继续预训练""LoRA/SFT/DPO…
github-awesome-copilot-git-commit
Generate high-quality, atomic Conventional Commits by analyzing Git changes, recommending logical commit boundaries, validating commit messages, and assisting with PRs, changelogs, and releases.