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/madappgang/magus/worktree-lifecyclenpx skills add MadAppGang/magus --skill worktree-lifecyclegit clone --depth 1 https://github.com/MadAppGang/magusWrote 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.
[](https://agentmods.dev/skills/madappgang/magus/worktree-lifecycle)<a href="https://agentmods.dev/skills/madappgang/magus/worktree-lifecycle"><img src="https://agentmods.dev/badge/skills/madappgang/magus/worktree-lifecycle.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00039 | $0.03721 |
| Opus 5 | $0.00019 | $0.01861 |
| Sonnet 5 | $0.00008 | $0.00744 |
| Haiku 4.5 | $0.00004 | $0.00372 |
Grade D, and why
worktree-lifecycle scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > "$HOME/.claude/.statusline-worktree-${SESSION_ID}" <<MARKER_EOF Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- [ ] Manually deleting worktree with `rm -rf` (use `git worktree remove`) This is a copy
86% identical to worktree-lifecycle — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Lifecycle
Purpose: Manage git worktrees for isolated feature work with safety checks, multi-stack setup, and clean lifecycle management.
When to Use
This skill applies whenever you:
- Start a new feature that requires isolated workspace
- Execute risky or experimental changes
- Need to keep current work untouched while testing alternatives
- Coordinate parallel agent work (each agent in separate worktree)
- Follow an implementation plan requiring clean environment
- Preserve long-running feature work across sessions
Trigger keywords: experiment, prototype, risky, breaking, parallel, isolate, worktree, workspace
Red Flags (Anti-Patterns)
- Creating worktree without checking if branch already exists
- Creating worktree without checking if directory path is available
- Forgetting to add worktree directory to .gitignore
- Manually deleting worktree with
rm -rf(usegit worktree remove) - Removing worktree with uncommitted changes without user confirmation
- Using same branch in multiple worktrees simultaneously
- Working in worktree after returning to main directory (stale CWD)
- Not storing original CWD before entering worktree
- Skipping dependency installation in new worktree
- Not running baseline tests before starting work
6-Phase Lifecycle
Phase 1: Pre-flight Checks
Purpose: Verify all prerequisites before creating anything.
Required checks (all must pass):
# 1. Verify git repository
git rev-parse --git-dir &>/dev/null
if [ $? -ne 0 ]; then
ERROR: "Not a git repository"
RECOVERY: Abort with clear error message
fi
# 2. Detect detached HEAD state
if ! git symbolic-ref HEAD &>/dev/null; then
WARNING: "Currently in detached HEAD state"
RECOVERY: Ask user if they want to create branch from current commit
fi
# 3. Check if branch already in a worktree
if git worktree list | grep -q "$BRANCH"; then
ERROR: "Branch $BRANCH already checked out in a worktree"
RECOVERY: Ask user - reuse existing, rename branch, or cancel
fi
# 4. Check if branch exists (but not in worktree)
if git branch --list "$BRANCH" | grep -q .; then
WARNING: "Branch $BRANCH already exists"
RECOVERY: Ask user - use existing branch or create new with different name
fi
# 5. Check if target path is available
# IMPORTANT: Create directory first before checking (git check-ignore needs path to exist)
mkdir -p "$WORKTREE_DIR"
if [ -d "$WORKTREE_PATH" ]; then
ERROR: "Directory $WORKTREE_PATH already exists"
RECOVERY: Ask user - choose different path or remove existing
fi
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.
- yesterday First seen · 454 lines · 39 tokens per session scan D 6f69614ab232
worktree-lifecycle is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 3,721 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). It is 86% identical to worktree-lifecycle, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…