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/carbeneai/forge/gitworktreesnpx skills add CarbeneAI/Forge --skill gitworktreesgit clone --depth 1 https://github.com/CarbeneAI/ForgeWhat 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 | $0.00068 | $0.03244 |
| Opus 5 | $0.00034 | $0.01622 |
| Sonnet 5 | $0.00014 | $0.00649 |
| Haiku 4.5 | $0.00007 | $0.00324 |
Grade C, and why
git-worktrees 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .worktrees/user-auth/ How it starts
The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktrees
Creates isolated git worktree directories for feature development with automatic safety verification and project setup.
🎯 Load Full CORE Context
read ${PAI_DIR}/skills/CORE/SKILL.md
When to Activate This Skill
- "create worktree for feature X" → Isolated feature development
- "set up feature branch" → Before implementation
- "isolate this work" → Separate from main codebase
- Before executing implementation plans → Clean environment
- Before starting complex feature → Risk isolation
Core Philosophy
Isolation Prevents Accidents
Git worktrees create completely separate working directories that:
- Share git history (efficient)
- Have independent branches
- Can't accidentally commit to main
- Enable parallel development
- Simplify cleanup (delete directory = gone)
Safety First: Verify Gitignore
Project-local directories (node_modules/, .venv/, dist/, target/) MUST be gitignored before creating worktrees.
If not ignored, these directories would be tracked by git and shared across worktrees, causing:
- Dependency conflicts
- Build artifacts corruption
- Lock file collisions
- Massive git repository size
CRITICAL: Always verify and fix .gitignore before creating worktree.
Clean Baseline: Setup and Test
New worktree should start with:
- Project dependencies installed
- Project built/compiled if needed
- Tests passing (clean baseline)
If tests fail in new worktree, something's wrong with setup. Fix before implementation.
The Process
Step 1: Directory Selection
Priority order for worktree location:
- Project has
.worktrees/directory → Use it - Project has
worktrees/directory → Use it - CLAUDE.md specifies preference → Follow it
- Ask user where to create
Example:
## Worktree Location
Checking for standard worktree directories...
- `.worktrees/`: Not found
- `worktrees/`: Not found
- CLAUDE.md preference: Not specified
Where should I create the worktree?
Options:
1. `.worktrees/feature-name` (recommended - gitignored by default)
2. `../feature-name` (sibling directory)
3. Specify custom path
What's your preference?
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 · 598 lines · 68 tokens per session scan C 13a72a6eaf0a
git-worktrees is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 3,244 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
pentesting-everything
Guides authorized penetration testing with PentestingEverything as the source-grounded knowledge base. Use when scoping an engagement, building domain checklists, hunting a vulnerability class, choosing tools/commands, or drafting evidence-based findings from this repository's Markdown.
implementing-devsecops-security-scanning
Integrates Static Application Security Testing (SAST), Dynamic Application Security Testing (DAST), and Software Composition Analysis (SCA) into CI/CD pipelines using open-source tools. Covers Semgrep for SAST, Trivy for SCA and container scanning, OWASP ZAP for DAST, and Gitleaks for secrets detection. Activates for…
hunt-ato
Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…
aod-orchestrate
Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…
security
Claude-powered SAST and SCA security scan skill. Invoked automatically as the Security Scan step (Step 7) of /aod.build (after Design Quality Gate, before Code Simplification) or standalone via /security. Analyzes all code files and dependency manifests changed on the feature branch relative to main for OWASP Top 10…
aod-foundation
Guided post-init workshop that helps new AOD Kit adopters establish product vision and design identity. Two-part flow: Part 1 (Vision) asks 5 guided questions to populate product-vision.md; Part 2 (Design) browses archetypes to generate brand files (brand.md, tokens.css, anti-patterns.md). Supports --vision and…