using-git-worktrees
Skill1 starsChanged 5 months agoMITView on GitHub
Make sure work happens in an isolated workspace before a feature or plan. A feature branch is the default and is enough for most work; reach for a worktree only when you need a second checkout at once (parallel agents, comparing branches, long build running). Detects existing isolation, prefers the harness's native worktree tool, falls back to git, verifies a clean baseline.
- Installs packages
189 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- chrysogonus/power-agentstheir own version, first seen Nov 8, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- afawfawffaf/my-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
Leodorareluctant259Skillchinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 20 projects that use this
frankxaiSkilldefense-in-depth
Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible
Also in 4 projects that use this
xfstudioSkilltest-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
Also in 3 projects that use this
kntismSkillcondition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
Also in 3 projects that use this
- +3 more from Leodorareluctant259
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- microsoft/FluidFramework★ 4.9ksame name
- silvertakana/worldwideview★ 1.9ksame name
- lingyired/status-trio★ 1.8ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- DemonDamon/AgenticX★ 1ksame name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- api-designSkill
- brainstormingSkill
- councilSkill
- dispatching-parallel-agentsSkill
- document-toolkitSkill
- executing-plansSkill
- gui-input-automationSkill
- humanizeSkill
- hyprland-controlSkill
- incremental-implementationSkill
- issue-to-prSkill
- litreviewSkill
- mcp-builderSkill
- rust-reviewSkill
- screen-captureSkill
- session-handoffSkill
- shadcn-auditSkill
- spec-to-issuesSkill
- subagent-driven-developmentSkill
- teachSkill
- unslopSkill
- visual-computer-use-loopSkill
- writing-flowSkill
- writing-plansSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 182 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 49
Native tool first: If the harness has a worktree tool (something like EnterWorktree, a /worktree command, or a --worktree flag), use it — …
- Distinctive: line 64
If git worktree add fails on a sandbox permission error, tell the user and work in place.
- Very specific: line 81
Run the test command (pnpm test / cargo test / go test ./...).
- Distinctive: line 89
Start work on main/master.
- Distinctive: line 91
Use git worktree add when a native worktree tool exists.
- Distinctive: line 92
Create a project-local worktree without verifying it's ignored.
“Common” is measured: kept by at least 6 in 10 of the 182 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Isolated Workspaces (Branches & Worktrees)
Work should never land directly on main. The default is a feature branch —
that's what fits the usual loop (branch → fix → PR → merge → delete →
next). A worktree is for when you genuinely need two checkouts at once:
running parallel agents on independent tasks, comparing branches side by side, or
keeping a long build/test going while you work elsewhere. If you don't need a
second checkout, a branch is simpler — don't over-engineer it.
Say at the start: "Setting up an isolated workspace."
Branch (default)
git switch -c <feature-branch> # never start on main/masterThat's it for most work. Skip the rest unless you actually need a second checkout.
Worktree (when you need a second checkout)
Step 0 — detect existing isolation
GIT_DIR=$(cd "$(git rev-parse --git-dir)" 2>/dev/null && pwd -P)
GIT_COMMON=$(cd "$(git rev-parse --git-common-dir)" 2>/dev/null && pwd -P)GIT_DIR != GIT_COMMON is also true inside a submodule, so guard:
git rev-parse --show-superproject-working-tree 2>/dev/null # path = submoduleGIT_DIR != GIT_COMMON, not a submodule: already in a worktree — skip to Setup. Don't nest another.- Otherwise: normal checkout. If the user hasn't stated a preference, ask before creating one.
Step 1 — create it
Native tool first. If the harness has a worktree tool (something like
EnterWorktree, a /worktree command, or a --worktree flag), use it — it
handles placement, branch, and cleanup, and the harness can track it. Using
git worktree add when a native tool exists creates phantom state it can't see.
Git fallback (only if no native tool). Default dir .worktrees/ (else
worktrees/; if both, .worktrees/). Project-local dirs MUST be git-ignored
first or their contents get committed:
git check-ignore -q .worktrees || { echo ".worktrees/" >> .gitignore && git add .gitignore && git commit -m "chore: ignore worktrees"; }
git worktree add ".worktrees/<branch>" -b "<branch>"
cd ".worktrees/<branch>"If git worktree add fails on a sandbox permission error, tell the user and
work in place.
Setup
Auto-detect and run:
[ -f pnpm-lock.yaml ] && pnpm install
[ -f package.json ] && [ ! -f pnpm-lock.yaml ] && npm install
[ -f Cargo.toml ] && cargo build
[ -f go.mod ] && go mod download
[ -f pyproject.toml ] && (poetry install || pip install -e .)Verify a clean baseline
Run the test command (pnpm test / cargo test / go test ./...).
- Fail: report and ask whether to proceed — otherwise you can't tell new bugs from pre-existing ones.
- Pass: report ready.
Never
- Start work on
main/master. - Spin up a worktree when a branch is all you need.
- Use
git worktree addwhen a native worktree tool exists. - Create a project-local worktree without verifying it's ignored.
- Skip the baseline test, or push through failures without asking.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

