git-flow

git-flow is a skill for Claude Code, Codex from ahmadulhoq/agentskel. It costs 38 tokens per session (1,730 once invoked), scanned A, original, MIT.

Git branching, commit, and PR procedures. Use when creating branches, making commits, or opening pull requests. Enforces branch naming, commit message format, and PR rules.

Skill for Claude CodeCodex

Part of the agentskel plugin — 52 skills, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/ahmadulhoq/agentskel/git-flow
Any agent
npx skills add ahmadulhoq/agentskel --skill git-flow
Clone the repo
git clone --depth 1 https://github.com/ahmadulhoq/agentskel

Made for: Claude Code, Codex.

Or install agentskel, the plugin that ships this one along with the rest of its 52 skills, 2 hooks.

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-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahmadulhoq/agentskel/git-flow.svg)](https://agentmods.dev/skills/ahmadulhoq/agentskel/git-flow)
Your own site
<a href="https://agentmods.dev/skills/ahmadulhoq/agentskel/git-flow"><img src="https://agentmods.dev/badge/skills/ahmadulhoq/agentskel/git-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01730
Opus 5 $0.00019 $0.00865
Sonnet 5 $0.00008 $0.00346
Haiku 4.5 $0.00004 $0.00173

Measured 2d ago against content hash e2f4354136b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-flow 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.

.agents/skills/git-flow/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Flow Procedure

All development follows the project's Git Workflow. Full spec: see GIT_WORKFLOW.md in the project's standards (.agents/ or skeleton).

Branch Creation

Before writing any code, create a branch.

Direct-Commit Mode check (first): Read .memory/CONFIG.md. If Direct-Commit Mode | on, OR the user's current request is prefixed with direct:, verify the change qualifies (see refusal list in docs/AUTONOMY-MODES.md):

  • If it qualifies → skip this section entirely. Stay on [DEFAULT_BRANCH]. Surface the DIRECT-COMMIT MODE ACTIVE — committing directly to [DEFAULT_BRANCH] (no PR). banner. Jump to Commit Messages.
  • If it does NOT qualify → surface Refusing Direct-Commit Mode — <reason>; switching to full flow. and continue with branch creation as normal.

Otherwise (mode off, or user did not prefix direct:) — proceed with branch creation:

  • Switch to [DEFAULT_BRANCH] and pull latest:
    git checkout [DEFAULT_BRANCH] && git pull
    
  • Create a new branch with the correct naming convention:
    • Ticket given: BOARD-XXXX-kebab-description
    • Tech debt fix (no ticket): debt-id-kebab-description
    git checkout -b <branch-name>
    
  • Never push directly to [DEFAULT_BRANCH].

Commit Messages

  • Ticket work: [BOARD-XXXX] short description
  • Tech debt: [DEBT-ID] short description
  • Commits must describe the change clearly.
  • No empty commits. No WIP commits on shared branches.

Commit Granularity

  • Default: one commit per logical change. A "logical change" is a single coherent unit that could stand on its own in git log — one bug fix, one new function, one refactor pass, one doc update. Not one giant end-of-workflow commit.
  • Honor user-specified commit granularity for the duration of the workflow. If the user says "smaller commits", "atomic commits", "commit per file", "commit per logical unit", or equivalent, that granularity persists until the workflow ends — it is not a one-shot instruction for the next commit only. The workflow plan must include a Commit granularity: line stating the chosen strategy so it stays visible across steps.
  • When user instruction is ambiguous ("smaller" — smaller than what?), ask once for clarification before the first commit. Don't guess.
  • Defer to existing conventions in the project's GIT_WORKFLOW.md when there is a conflict, but only after surfacing the conflict to the user.

Read the full file on GitHub · 148 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.

  1. 2d ago First seen · 148 lines · 38 tokens per session scan A e2f4354136b7

Subscribe to this mod's changes

git-flow is a skill published in the GitHub repository ahmadulhoq/agentskel (13 stars, last pushed 18d ago), licensed MIT. It adds 38 tokens to every session and 1,730 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 2026-09-02.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens