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/wan-huiyan/agent-traffic-control/git-worktreenpx skills add wan-huiyan/agent-traffic-control --skill git-worktreegit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote 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/wan-huiyan/agent-traffic-control/git-worktree)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/git-worktree"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/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 | $0.00074 | $0.03090 |
| Opus 5 | $0.00037 | $0.01545 |
| Sonnet 5 | $0.00015 | $0.00618 |
| Haiku 4.5 | $0.00007 | $0.00309 |
Grade B, and why
git-worktree scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$WTM" ] || WTM="$(find -L "$HOME/.claude/plugins/cache" -mindepth 7 -maxdepth 7 \ How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Manager
This skill provides a unified interface for managing Git worktrees across your development workflow. Whether you're reviewing PRs in isolation or working on features in parallel, this skill handles all the complexity.
What This Skill Does
- Create worktrees from main branch with clear branch names
- List worktrees with current status
- Switch between worktrees for parallel work
- Clean up completed worktrees automatically
- Interactive confirmations at each step
- Automatic .gitignore management for worktree directory
- Automatic .env file copying from main repo to new worktrees
- Automatic dev tool trusting for mise and direnv configs with review-safe guardrails
Resolve the manager script first (once per shell)
Every command below runs "$WTM". Resolve it once:
# Three roots, in order. A plugin install creates NEITHER of the first two:
# CLAUDE_PLUGIN_ROOT is frequently unset in the shell a step actually runs in, and
# ~/.claude/skills/agent-traffic-control/ does not exist — the plugin lives under
# ~/.claude/plugins/cache/<marketplace>/agent-traffic-control/<version>/.
REL="skills/git-worktree/scripts/worktree-manager.sh"
WTM="${CLAUDE_PLUGIN_ROOT:+${CLAUDE_PLUGIN_ROOT}/$REL}"
[ -f "$WTM" ] || WTM="$HOME/.claude/skills/agent-traffic-control/$REL"
# Rank on the VERSION segment, not the whole path: the marketplace name precedes the
# version, so a plain `sort -V` over full paths would let aaa-mkt/2.5.0 lose to
# zzz-mkt/1.0.0. Here the version sits at NF-4 because the script nests two levels
# deeper than a flat plugin layout. Use `find`, not a glob — zsh fails a non-matching
# glob at expansion time, before 2>/dev/null can apply.
[ -f "$WTM" ] || WTM="$(find -L "$HOME/.claude/plugins/cache" -mindepth 7 -maxdepth 7 \
-path "*/agent-traffic-control/*/$REL" 2>/dev/null \
| awk -F/ '{print $(NF-4)"\t"$0}' | sort -V -k1,1 | tail -1 | cut -f2-)"
if [ ! -f "$WTM" ]; then
echo "worktree-manager.sh: not found — tried \$CLAUDE_PLUGIN_ROOT/$REL," \
"\$HOME/.claude/skills/agent-traffic-control/$REL, and" \
"\$HOME/.claude/plugins/cache/*/agent-traffic-control/*/$REL"
fi
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 364 lines · 74 tokens per session scan B 7069215b811e
git-worktree is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 17d ago), licensed MIT. It adds 74 tokens to every session and 3,090 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
bridge
Join a shared per-project chat between AI coding agents (Claude Code, Cursor, …) — group channels + DMs — and receive messages from other instances using whatever your agent supports (push, loop, or poll). Use when coordinating multiple agent instances on the same project.
codex-coplan
Bring in an external model (Codex) to co-develop a plan — both models draft independently, align on disagreements, and merge into one plan. Load this only when the user explicitly names Codex (e.g. "let's discuss this with Codex," "what does Codex think about this approach") — don't auto-trigger just because a plan…
loop-implement
Close a single implementation task with a methodology-grounded verification loop — define done, analyze, plan, write tests first (Red), implement (Green), run, self-review, get an independent test-quality audit, then judge against done; on failure reflect and retry (bounded). Use for one non-trivial task (feature…
codex-orchestrator
Delegate execution tasks to Codex (Claude plans and reviews). Load this only when the user names Codex explicitly — no matter how big the task is, if the user hasn't mentioned Codex, do it yourself.
orchestrate
Orchestrate one natural-language goal into parallel tmux Claude Code sessions — clarify requirements, branch by environment, decompose into tasks (with approval), launch a session per task running loop-implement, review and integration-test, then merge after your confirmation. Use when asked to build/implement a goal…
good-bad-ugly
Use when the user asks to "orchestrate", "conduct", invoke "good bad ugly" / "gbu", or tackle a large multi-part coding task (audits, refactor sweeps, multi-feature sessions, "clean this up and fix everything") — anything too big for one linear pass. Runs the tiered orchestration workflow: The Good (brain) plans and…