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/fprochazka/claude-code-plugins/git-workflownpx skills add fprochazka/claude-code-plugins --skill git-workflowgit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWhat 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 | $0.00055 | $0.03026 |
| Opus 5 | $0.00028 | $0.01513 |
| Sonnet 5 | $0.00011 | $0.00605 |
| Haiku 4.5 | $0.00006 | $0.00303 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-workflow
How to think about commits, branches, and merge requests — the shape the history should take, not the commands to get there.
The underlying principle: a reviewer should be able to read the branch commit-by-commit and never be confused about what each commit does or why. Every rule below serves that goal. When a rule fights it, the rule loses.
The test that decides every commit boundary
Before splitting anything, classify the pieces as siblings or ancestors.
- Siblings — complete on their own terms, revertible in any order, each one meaningful on
masterto somebody who never saw the branch. Siblings stay separate commits. - Ancestors — incomplete halves of a single behaviour, each one meaningful only once the next one lands. Ancestors are one commit, no matter how logically they were built in sequence.
The mechanical form: if commit N+1's subject cannot be understood without the artifact commit N introduced, they are the same commit.
The order work gets done is almost always an ancestor chain: add the columns, persist them, wire them into the callers, expose them on the endpoint, regenerate the client, build the UI. That is a correct working sequence and a wrong commit sequence. The atomic commit is the whole vertical slice — schema, domain logic, transport, generated client, frontend, tests — because none of those halves means anything alone.
What makes a commit atomic
An atomic commit solves exactly one thing — not less, not more, with all related changes included and all unrelated changes excluded. "One thing" is one complete change in what the system does, cut through every layer it needs. Vertical slices can and should be small, but each one is a fully functioning increment: it builds, its tests pass, it makes sense on master alone.
Is atomic:
- A feature cut vertically: migration + entity + domain logic + endpoint + regenerated client + UI + its tests, in one commit.
- A bugfix that changes only the lines needed for the fix, with the test that now passes.
- A pure rename/move touching many files but changing no behaviour.
- A formatting-only commit, or a single typo fix.
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.
- 2d ago First seen · 151 lines · 55 tokens per session scan A bfab32c83018
git-workflow is a skill published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 3,026 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.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.