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 axiomantic/spellbook --skill using-git-worktreesgit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/using-git-worktrees)<a href="https://agentmods.dev/skills/axiomantic/spellbook/using-git-worktrees"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/using-git-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/axiomantic/spellbook/using-git-worktrees"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/using-git-worktrees.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 257 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.02338 |
| Opus 5.5 | $0.00030 | $0.00935 |
| Sonnet 5.5 | $0.00015 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
Grade A, and why
using-git-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 1mo 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Git Worktrees
Announce: "Using git-worktrees skill for isolated workspace."
Invariant Principles
- Directory precedence: CLAUDE.md/AGENTS.md override > existing ~/Development/worktrees/ > default (never assume)
- Safety gate: Project-local worktrees MUST be gitignored before creation
- Clean baseline: Tests must pass before implementation begins (interactive default; autonomous mode applies graduated policy -- see Autonomous Mode)
- Auto-detect over hardcode: Infer setup from manifest files
Inputs
| Input | Required | Description |
|---|---|---|
feature_name |
Yes | Name for the worktree branch (e.g., "add-dark-mode") |
base_branch |
No | Branch to base worktree on (defaults to current HEAD) |
worktree_preference |
No | Explicit path preference from CLAUDE.md or user |
Outputs
| Output | Type | Description |
|---|---|---|
worktree_path |
Path | Absolute path to created worktree directory |
branch_name |
String | Name of the created branch |
baseline_status |
Report | Test results confirming clean starting state |
Workspace Structure
Worktrees are organized by workspace (branch or feature name), not by project:
~/Development/worktrees/
{workspace-name}/
{repo-a}/ <- git worktree
{repo-b}/ <- git worktree
When multiple repos share a branch name or belong to the same feature, they nest under the same workspace directory. This makes it easy to find all repos related to a single effort.
Examples:
~/Development/worktrees/mcp-events/fastmcp/ # shared branch across repos
~/Development/worktrees/mcp-events/python-sdk/
~/Development/worktrees/mcp-events/typescript-sdk/
~/Development/worktrees/fix-auth-flow/myproject/ # single-repo feature
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.
- 1mo ago First seen · 288 lines · 76 tokens per session scan A 313479dd9f6e
using-git-worktrees is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 2,338 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
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
docs-update-from-diff
Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local changes, update docs after a feature or refactor, or when phrases like "git diff", "local changes", "update docs", or "official docs" appear.
prepare-pr
Prepare GitHub pull request title and body files from the current branch diff, especially for non-interactive CI/autofix flows that must follow the repository PR template without pushing or creating the PR.
git-revert-safety
Apply when reverting commits, undoing merges, or recovering from branch contamination. Covers collateral damage verification (manifest, package.json, CHANGELOG, lockfiles), cherry-pick vs revert decision matrix, partial-revert detection, merge-parent handling, and post-revert CI verification. Prevents the most common…
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.