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 skills add dork-labs/dorkos --skill working-in-worktreesgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/dork-labs/dorkos/working-in-worktrees)<a href="https://agentmods.dev/skills/dork-labs/dorkos/working-in-worktrees"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/working-in-worktrees/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dork-labs/dorkos/working-in-worktrees"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/working-in-worktrees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 163 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 166 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 35 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 127 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00066 | $0.04871 |
| Opus 5.5 | $0.00026 | $0.01948 |
| Sonnet 5.5 | $0.00013 | $0.00974 |
| Haiku 4.5 | $0.00007 | $0.00487 |
Grade A, and why
working-in-worktrees 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 20d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in Worktrees
Overview
This skill governs workspace isolation for code work in DorkOS — a repo that is routinely worked by several agents and sessions at once. It teaches the one decision rule (one checkout, one writer), the concrete failure mode that makes isolation non-optional, the exact mechanics for creating, entering, and cleaning up a worktree without losing anyone's work — and the half that isolation does not buy you, because worktrees separate working trees but share every ref.
The repo-wide rule lives in AGENTS.md → Worktrees. This skill is the mechanics and the why.
When to Use
- You are about to make a code change and the checkout may be shared with another agent or session.
- You are running the
/flow:executestage (the workspace-choice phase of the flow plugin'sexecuting-specsskill) — the unified/flowexecution gate. - You are running parallel work that mutates tracked files.
- You are comparing your branch against
mainacross more than one command — a conflict investigation, a red-before drill, a changelog gate, a "what didmainchange" question. - You need to create, enter, exit, or remove a worktree and want the safe procedure.
- You are unsure whether to isolate — the default answer for code work in this repo is yes.
Key Concepts
The rule: one checkout, one writer
main is the clean integration tree, not a shared scratchpad. Code changes default to an isolated worktree; main stays clean and is where branches merge back.
Default to a worktree for any code change. Stay in main only when all three hold:
- You are certainly the sole writer in this checkout, and
- The work is non-code (
research/,specs/, tracker, docs prose) or a single commit you land immediately, and - No long-running dev server in this checkout needs to stay undisturbed.
Create a worktree when any trigger fires:
- 🔴 Another agent/session may be active here — the DorkOS default. You usually cannot prove you are alone, so assume you are not.
- 🔴 Multi-commit / long-lived code work — a feature, refactor, or spec implementation.
- 🟡 The checkout is already dirty or on an unrelated topic branch.
- 🟡 A dev server or build must run undisturbed (port isolation).
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.
- 20d ago Changed d0f867e3ad5e
- 1mo ago Changed · +2 lines c9cb8f01c095
- 1mo ago Changed · +31 lines b7b435b6af56
- 1mo ago First seen · 166 lines · 66 tokens per session scan A 284ae691c9aa
working-in-worktrees is a skill published in the GitHub repository dork-labs/dorkos (12 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 4,871 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
github-flow-for-claude-on-web
Complete GitHub workflow for Claude Code on the web. ALL GitHub operations MUST use REST API (never gh CLI). Includes branch naming (claude/-sessionId), push retry logic, PR/issue management via API, and complete workflows. Use for all GitHub interactions in Claude Code web environment.
stacked-pr-merge
Merging a stack of dependent PRs in this repository — a branch cut from another PR's branch rather than from main. Covers the one merge API that is not 403 here, taking the head SHA from the API, and the stale-lineage rebase that produces mass conflicts if you use plain git rebase origin/main. Use when gh pr merge…
vibing-worktree-create
Create a new git-worktree-backed isolated work area for the current vibing.nvim chat via natural language — no separate UI. Use when the user wants to isolate work in its own worktree ("split this into its own worktree", "start this in isolation", "give this its own branch").
vibing-worktree-attach
Attach the current or a new vibing.nvim chat to an already-existing git worktree via natural language — no separate UI. Use when the user wants to switch/attach a chat to an existing worktree ("let's go into the auth-fix worktree", "attach to worktree X", "continue in the feature-y worktree").
vibing-worktree-finish
Remove a git-worktree-backed isolated work area for vibing.nvim chats via natural language — no separate UI. Use when the user wants to clean one up when done ("clean up this worktree", "I'm done with this branch's worktree", "remove the auth-fix worktree").
vibing-worktree-list
List git-worktree-backed isolated work areas for vibing.nvim chats via natural language — no separate UI. Use when the user wants to see what worktrees/branches exist ("what worktrees do I have", "what's in progress", "show me all worktrees").