Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsnpx agentmods add skills/florianbruniaux/claude-code-plugins/git-worktreeWrote 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/florianbruniaux/claude-code-plugins/git-worktree)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/git-worktree"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/git-worktree.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 5.1 | $0.00015 | $0.02008 |
| Opus 5 | $0.00008 | $0.01004 |
| Sonnet 5 | $0.00003 | $0.00402 |
| Haiku 4.5 | $0.00002 | $0.00201 |
Grade B, and why
git-worktree scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**/.claude/settings.local.json Copies of this mod
1 near-identical copy found in the catalogue:
- git-worktree — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Setup
Create isolated git worktrees for feature development without switching branches.
Core principle: Smart directory selection + symlink optimization + background verification = fast, reliable isolation.
Requires: Git 2.5.0+ (July 2015)
Companion commands: /git-worktree-status | /git-worktree-remove | /git-worktree-clean
Process
- Validate Branch Name: Check naming convention and conflicts
- Check Existing Directories:
.worktrees/orworktrees/ - Verify .gitignore: Ensure worktree dir is ignored
- Create Worktree:
git worktree add - Symlink Dependencies: Reuse
node_modules/from main worktree - Detect Database Provider: Check for DB branching capability
- Install Dependencies: Auto-detect package manager (if not symlinking)
- Run Background Verification: Type check + tests in background
- Report Location: Confirm ready with status
Flags
| Flag | Effect |
|---|---|
--fast |
Skip dependency install and baseline tests |
--isolated |
Fresh node_modules install (no symlink) |
--skip-install |
Skip dependency install, keep baseline tests |
Branch Name Validation
# Auto-prefix based on naming convention
# "auth" → "feat/auth" (default prefix)
# "fix/login-bug" → kept as-is
# "refactor/db-layer" → kept as-is
# Accepted prefixes: feat/, fix/, refactor/, chore/, docs/, test/, perf/
# If no prefix → default to feat/
# Reject invalid characters
echo "$BRANCH_NAME" | grep -qE '^[a-zA-Z0-9/_-]+$' || exit 1
# Check branch doesn't already exist
git show-ref --verify --quiet "refs/heads/$BRANCH_NAME" && echo "Branch already exists" && exit 1
Directory Selection
Priority Order
# 1. Check existing directories
ls -d .worktrees 2>/dev/null # Preferred (hidden)
ls -d worktrees 2>/dev/null # Alternative
# 2. Check CLAUDE.md for preference
grep -i "worktree.*director" CLAUDE.md 2>/dev/null
# 3. Ask user if neither exists
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 · 273 lines · 15 tokens per session scan B ea118092d5f4
git-worktree is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 2,008 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
testing-conventions
Test conventions across this portfolio — regression-test comment format, property-test setup for TS and Python, the financial-math arbitrary settings that were tuned by measurement, and why a failing check may be pinning a defect rather than reporting one. Load before writing tests, adding a regression test to a bug…
dependency-upgrade
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
fix
Bug-fix fast lane — the entry point for fixing something already broken (a red test, a prod error, a reported defect), not building a new feature. Does the bug-specific part — reproduce as a failing test, find the root cause, write a minimal fix-plan — then hands off to the existing pipeline (/implement → /review →…