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/patelr3/agents/worktreenpx skills add patelr3/agents --skill worktreegit clone --depth 1 https://github.com/patelr3/agentsWhat 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 | $0.00069 | $0.02465 |
| Opus 5 | $0.00034 | $0.01233 |
| Sonnet 5 | $0.00014 | $0.00493 |
| Haiku 4.5 | $0.00007 | $0.00247 |
Grade A, and why
worktree 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Skill
Execute work in an isolated git worktree. This skill manages the full lifecycle: branch creation → worktree setup → subagent execution → PR creation → cleanup.
A subagent runs inside the worktree to do the actual work. The parent session (you) manages the infrastructure around it.
Inputs
When this skill is invoked, gather the following from the user or calling agent:
| Input | Required | Default | Description |
|---|---|---|---|
| Prompt | No | — | Inline instructions for the subagent. Free-form text describing the work to do. |
| Plan file | No | — | Path to a file in the repo that describes the work (e.g., a PRD, a plan, a design doc). The subagent reads it and executes it. |
| Agent type | No | general-purpose |
Which subagent type to spawn via the task tool (e.g., general-purpose, ralph-agent, explore). |
| Branch name | No | Auto-generated | Git branch name (e.g., feat/my-feature). If not provided, derive a kebab-case name from the prompt or plan file. |
| Base ref | No | HEAD |
Branch, tag, or commit to base the new branch from. |
| Existing branch | No | false |
If true, the branch already exists (e.g., prepared by an orchestrator). Skip branch creation; fetch and use it directly. |
| Port offset | No | — | Integer for parallel port isolation (API = 3001 + N, Web = 3000 + N). |
| Auto-merge | No | true |
Whether to enable auto-merge on the created PR. |
| Create PR | No | true |
Whether to create a PR at the end. Set to false if the subagent handles PR creation itself. |
At least one of Prompt or Plan file must be provided. They can also be used together — the plan file provides the specification and the prompt provides additional context or instructions.
Execution Flow
Step 1: Resolve Inputs
BRANCH_NAME="<branch-name>"
REPO_ROOT="$(pwd)"
PROJECT_NAME="$(basename "$REPO_ROOT")"
Set the base ref for the new branch:
BASE_REF="<base-ref>" # e.g., HEAD, origin/main, a commit SHA
What ships with it
4 files 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.
- 2d ago First seen · 275 lines · 69 tokens per session scan A 8d2e6e20671a
worktree is a skill published in the GitHub repository patelr3/agents (2 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 2,465 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…