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 terrylica/cc-skills --skill worktree-spinoffgit clone --depth 1 https://github.com/terrylica/cc-skillsWrote 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/terrylica/cc-skills/worktree-spinoff)<a href="https://agentmods.dev/skills/terrylica/cc-skills/worktree-spinoff"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/worktree-spinoff/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/terrylica/cc-skills/worktree-spinoff"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/worktree-spinoff.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00106 | $0.02809 |
| Opus 5.5 | $0.00042 | $0.01124 |
| Sonnet 5.5 | $0.00021 | $0.00562 |
| Haiku 4.5 | $0.00011 | $0.00281 |
Grade A, and why
worktree-spinoff 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree spin-off (Orca IDE)
Self-Evolving Skill: This skill improves through use. If instructions are wrong, Orca's CLI changed, or a workaround was needed: fix this file and the script immediately, don't defer. Only update for real, reproducible issues.
Use this when a task should continue in its own Orca worktree, with its own branch, sidebar entry and agent session, instead of in the current one. One command, scripts/orca-spinoff, does the whole spin-off and the clean removal. It follows Orca's bundled orca-cli guide (orca skills get orca-cli) and keeps to Orca's native model: worktrees, the built-in agent launcher, repos and projects, hosts, and paired runtimes. Everything here was observed on Orca 1.4.22x on Linux and macOS.
Assumptions
- Orca IDE manages the agents. You drive Claude Code (or another TUI agent Orca knows:
codex,gemini, …) through Orca's CLI and GUI, locally and on other devices through paired runtimes. - The toolchain comes from Nix. One Nix profile gives the same current
bash,git,python3and coreutils on macOS, Linux and BSD, so the same commands behave the same everywhere. The script also runs on stock macOS (/bin/bash3.2, BSD userland) because it uses no GNU-only flags. It needsbash ≥ 3.2,git ≥ 2.20,python3 ≥ 3.9and the Orca IDE CLI. - The repository is registered in Orca on the target runtime (
orca repo add --path <checkout>), and its remote is reachable from the machine where you run the script.
Use
SPIN=<this skill's directory>/scripts/orca-spinoff # e.g. from the plugin cache
"$SPIN" create --name my-task --title "My task (issue #12)" \
--handoff ./handoff.md --display "My task: readable name" \
[--issue 12] [--comment "status"] [--link .venv] [--setup skip] [--dry-run]
"$SPIN" remove --name my-task [--delete-remote-branch] [--force] [--dry-run]
--title: the prompt's first line. Orca labels the agent's row in the sidebar with it, so keep it short and specific.--handoff FILE: committed asdocs/handoff/<file>(--handoff-dir) before the agent starts. The default prompt tells the agent to read it first;--prompt-filereplaces the prompt body.--link PATH: symlinks a path of the main checkout into the worktree, for things that are not in git:.venv,node_modules,.env.--handoffand--prompt-file: relative paths are relative to your current directory, also inside a linked worktree.- Base: with a handoff, the remote's default branch (or
--base). Without a handoff or--base, the script omits--base-branch, so Orca uses the repo's default base, as Orca'sorca-cliguide asks for independent top-level handoffs. --dry-run: forcreateandremove, runs every check (repo, remote, base, collisions, leftovers, unsaved work), prints the plan, and changes no branch or worktree. It may stillgit fetch.- Output: stdout is one JSON line,
{"worktree", "path", "branch", "terminal", "terminals", "setup_tabs", "prompt_seen"}(terminalsisnullif Orca could not list them); progress and warnings go to stderr. The handoff is complete whenprompt_seenis true. Report the worktree and terminal to the user; do not wait for the new agent to finish.
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.
- 2d ago First seen · 92 lines · 106 tokens per session scan A 777b93de1173
worktree-spinoff is a skill published in the GitHub repository terrylica/cc-skills (0 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 2,809 once invoked, about $0.0004 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 2026-10-14.
Other skills, from other repositories
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
auto-claude
Autonomous multi-agent coding with git worktree isolation, QA validation, and memory. Use for complex features requiring autonomous implementation.
github-ops
GitHub remote operations and README authoring: repo creation, metadata, releases, issue/PR management with preview-before-send, README as a landing page (badge row, features-as-benefits, screenshots, Recent Updates), and read-only security auditing. Triggers on: write a README, improve the README, README badges…
ci-cd-ops
CI/CD pipeline patterns with GitHub Actions, release automation, and testing strategies. Use for: github actions, workflow, CI, CD, pipeline, deploy, release, semantic release, changesets, goreleaser, matrix, cache, secrets, environment, artifact, reusable workflow, composite action.