agentweaver: Skill for Claude Code

.github/skills/git-workflow/SKILL.md

git-workflow is a skill for Claude Code, Codex from sabbour/agentweaver. It costs 16 tokens per session (2,095 once invoked), scanned C, original, MIT.

A Git workflow for a project that uses separate branches for development, early previews, and released code. Git is the version-control system used to track changes, and a branch is an independent line of work.

In plain words
What is it for?
It helps create issue branches and clean worktrees, mark GitHub issues as in progress, and move changes through development and release branches.
Why use it?
It gives feature work a consistent starting point and keeps development, preview releases, and production releases separate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is sabbour/agentweaver's own configuration. It tells Claude Code and Codex how to work on agentweaver 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 agentweaver configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../squad-195 -b squad/195-fix-stamp-bug origin/dev.

Reuse

Borrowing it

Nothing to install: this file belongs to sabbour/agentweaver. 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/sabbour/agentweaver/dev/.github/skills/git-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

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.

agentmods badge for git-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sabbour/agentweaver/git-workflow"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/git-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,095 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00016 $0.02095
Opus 5.5 $0.00006 $0.00838
Sonnet 5.5 $0.00003 $0.00419
Haiku 4.5 $0.00002 $0.00210

Measured 1mo ago against content hash 351b9c46d86d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

git-workflow scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

If a worktree was deleted manually (rm -rf), `git worktree prune` recovers the state.
.github/skills/git-workflow/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Squad uses a three-branch model. All feature work starts from dev, not main.

Branch Purpose Publishes
main Released, tagged, in-npm code only npm publish on tag
dev Integration branch — all feature work lands here npm publish --tag preview on merge
insiders Early-access channel — synced from dev npm publish --tag insiders on sync

Branch Naming Convention

Issue branches MUST use: squad/{issue-number}-{kebab-case-slug}

Examples:

  • squad/195-fix-version-stamp-bug
  • squad/42-add-profile-api

Workflow for Issue Work

  1. Prepare a clean issue worktree and branch from dev before dispatching implementation:

    git fetch origin dev
    git worktree add .worktrees/{issue-number} -b squad/{issue-number}-{slug} origin/dev
    git -C .worktrees/{issue-number} status --short --branch
    

    Confirm the worktree is clean, on the assigned branch, and pass its absolute path as the agent's explicit CWD. A dirty or diverged root is coordination-only, never an implementation CWD.

  2. Mark issue in-progress:

    gh issue edit {number} --add-label "status:in-progress"
    
  3. Do the work. Make changes, write tests, and commit the completed issue on its own branch before accepting another issue.

  4. Run bounded independent review, then push and open a draft PR:

    git push -u origin squad/{issue-number}-{slug}
    gh pr create --base dev --title "{description}" --body "Closes #{issue-number}" --draft
    

    Mark the PR ready only after required validation and independent review/admission have completed with no unresolved blocker:

    gh pr ready <number>
    gh pr merge <number> --squash --match-head-commit <validated-sha>
    

    Before ready and immediately before this command, Ralph fetches origin/dev, gets the live PR head SHA, and runs node scripts/ci/squad-admission-preflight.mjs <owner/repository> <pr-number> --head-sha <live-head-sha>. The preflight uses the pinned Squad SDK to resolve declared external state and checks the coordinator-owned findings ledger. Ralph records the returned <validated-sha> and uses it immediately with --match-head-commit. Coordinator/Ralph and authoritative external Squad state are trusted operational components; GitHub is evidence and CI only, and repository code is not an adversarially immutable boundary. Confirm the PR reports MERGED, mergedAt, and merge SHA before dispatching dependent work.

Read the full file on GitHub · 234 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. 1mo ago Changed · +8 lines 351b9c46d86d
  2. 1mo ago First seen · 226 lines · 16 tokens per session scan C 2a6e60c38e32

Subscribe to this mod's changes

git-workflow is a skill published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 2,095 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.

Related

Other skills, from other repositories

github-pr-workflow

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

paperclipai/paperclip · 39 tokens

codew-release-qa-sweep

Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.

Hmbown/CodeWhale · 31 tokens

gh-find-prs

Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.

Hmbown/CodeWhale · 27 tokens

contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

Hmbown/CodeWhale · 57 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

release-revoke

Revoke or rollback a pi-agent-dashboard release: delete the GitHub Release, remove the git tag locally and on origin, deprecate the npm version (npm unpublish is blocked after 72h), and optionally revert the release commit. Use when the user says "revoke release", "rollback release", "delete release", "unpublish…

BlackBeltTechnology/pi-agent-dashboard · 85 tokens