agentweaver: Skill for Claude Code

.copilot/skills/agentweaver-git-workflow/SKILL.md

agentweaver-git-workflow is a skill for Claude Code, Codex from sabbour/agentweaver. It costs 24 tokens per session (1,431 once invoked), scanned A, original, MIT.

A Git workflow for coordinating code changes through protected branches, isolated workspaces, and pull requests. It defines where changes go and how local background agents must work.

In plain words
What is it for?
Use it to create issue, fix, maintenance, or documentation branches; give each background agent its own Git worktree; and send completed changes through pull requests into the development branch.
Why use it?
It prevents agents from interfering with each other or changing the shared checkout. It also keeps the stable branch limited to reviewed releases and emergency fixes.

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 →

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/.copilot/skills/agentweaver-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 agentweaver-git-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-git-workflow"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-git-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,431 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01431
Opus 5.5 $0.00010 $0.00572
Sonnet 5.5 $0.00005 $0.00286
Haiku 4.5 $0.00002 $0.00143

Measured 1mo ago against content hash 64d41d6ca32c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentweaver-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 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.

.copilot/skills/agentweaver-git-workflow/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integration Workflow

dev is the default protected integration branch. Use a short-lived issue branch and a PR targeting dev; PRs are squash-merged so dev has one commit per logical change. main is stable/published-only and accepts only soaked release promotions or audited emergency hotfixes.

Issue branches use:

squad/{issue-number}-{kebab-case-slug}

Mandatory Worktree Isolation

Every locally run background agent making code changes MUST work in its own dedicated Git worktree. This is unconditional: it applies to issue-linked work and ad-hoc work alike. Never let a local agent make code changes from the shared primary checkout.

Use these naming conventions:

Work type Branch Worktree
Issue-linked squad/{issue-number}-{short-kebab-slug} .worktrees/{issue-number}-{short-kebab-slug}
Ad-hoc fix fix/{short-kebab-slug} .worktrees/{short-kebab-slug}
Ad-hoc maintenance/docs chore/{short-kebab-slug} or docs/{short-kebab-slug} .worktrees/{short-kebab-slug}

Coordinator responsibility

Whoever spawns a local background agent for any code change MUST put explicit worktree bootstrap commands (git fetch, git worktree add, and cd) in the spawn prompt. Do not assume the agent will infer this requirement or allow it to default to the shared primary checkout.

For an issue-linked task, the prompt must include commands equivalent to:

git fetch origin dev
git worktree add ".worktrees/{issue-number}-{slug}" \
  -b "squad/{issue-number}-{slug}" origin/dev
cd ".worktrees/{issue-number}-{slug}"

For an ad-hoc task, the prompt must include commands equivalent to:

git fetch origin dev
git worktree add ".worktrees/{short-kebab-slug}" \
  -b "fix/{short-kebab-slug}" origin/dev
cd ".worktrees/{short-kebab-slug}"

For example, two local agents that both run Git operations in the same directory can overwrite each other's checked-out branch or staged files, mixing uncommitted changes. Separate worktrees prevent that collision.

Read the full file on GitHub · 124 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 First seen · 124 lines · 24 tokens per session scan A 64d41d6ca32c

Subscribe to this mod's changes

agentweaver-git-workflow is a skill published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,431 once invoked, about $0.0001 per session on Opus 5.5. 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.

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