What is rigor-worktree?

A tool for creating an isolated Git worktree, a separate working directory connected to another branch. It also prepares a separate Ruby dependency bundle for that worktree.

Use it to create a branch checkout for parallel work, a subagent, or a dependency-bump branch, with its own installed dependencies.

It prevents parallel agents or branches from changing the same files and dependencies underneath each other. This makes concurrent work and dependency updates less likely to interfere.

How rigortype/rigor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rigortype/rigor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rigortype/rigor/master/.claude/skills/rigor-worktree/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/rigortype/rigor

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rigortype/rigor/rigor-worktree/github.svg)](https://agentmods.dev/skills/rigortype/rigor/rigor-worktree)

Your own site

<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-worktree"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-worktree/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rigortype/rigor/rigor-worktree"><img src="https://agentmods.dev/badge/skills/rigortype/rigor/rigor-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00047	$0.01738
Opus 5.5	$0.00019	$0.00695
Sonnet 5.5	$0.00009	$0.00348
Haiku 4.5	$0.00005	$0.00174

Measured 3d ago against content hash 488d992ef407, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rigor-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 3d 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.

.claude/skills/rigor-worktree/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a worktree with its bundle in place

A worktree is the isolation boundary for parallel work: a lib-editing agent gets its own tree so the exe/rigor another agent invokes is not the code being rewritten under it, and a branch with its own Gemfile.lock can bundle install without touching anyone else.

bin/rigor-worktree [--with-references] [--with-tools] <branch> [start-point]

<branch> — an existing branch is checked out; a new name is created from <start-point> (default origin/master).
The worktree lands at $RIGOR_WT_ROOT/<slug>, default <main>/../rigor-wt/<slug> (~/repo/ruby/rigor-wt/<slug> in the usual layout). <slug> is the branch with a leading codex/ stripped and / → -.

The script runs git worktree add, then populates the bundle:

vendor/bundle (~126M, ~9800 files) is copy-on-write cloned from the main clone — cp -Rc / clonefile(2) on APFS, a reflink on btrfs/xfs, a plain copy elsewhere. A few seconds, near-zero disk until blocks diverge, and the copy is writable and isolated.
.bundle/config is copied (BUNDLE_PATH: "vendor/bundle", a relative path — it only resolves because the real vendor/bundle is now in-tree).

No .git/info/exclude entry is needed: the real vendor/bundle/ directory matches the stock .gitignore /vendor/bundle/, so git status stays clean.

The main clone must have a populated vendor/bundle first — the script refuses otherwise. Run make setup there once if needed.

The worktree-only gotchas the script can't hide

references/ submodules are NOT populated in a worktree. A worktree shares .git, but submodule working trees are per-checkout, so every references/* directory is empty. A spec that reads a reference checkout (spec/docs/c_effects_raises_gate_spec.rb is the clear one; the builtin-catalog extraction target reads references/ruby too) then skips — not fails — silently, and a worker believes its gate ran when only the fixture arm did. Options:

Read the full file on GitHub · 149 lines

Files

What ships with it

2 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.

Changes

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.

3d ago Changed 488d992ef407
11d ago First seen · 149 lines · 47 tokens per session scan A e9bd324d2267

Subscribe to this mod's changes

rigor-worktree is a skill published in the GitHub repository rigortype/rigor (107 stars, last pushed today), licensed MPL-2.0. It adds 47 tokens to every session and 1,738 once invoked, about $0.0002 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 2026-10-26.

Git and workflow

rigor-worktree next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rigor-worktreerigortype/rigor	Skill	107	today	MPL-2.0	A	47	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	today	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	today	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code

rigor: Skill for Claude Code