--- name: new-feature description: Start a new task in an isolated Git worktree branched from origin/main so multiple agents can work on the same repo in parallel without conflicts. Use at the beginning of every new feature, fix, or task — before writing any code. title: new-feature canonical_url: https://skilld.dev/gh/michaelshimeles/skills/new-feature last_updated: 2026-09-22T16:01:33.000Z --- > **Skill from skilld.dev.** Follow the user's requested action. > If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it. > Otherwise, follow the instructions below for this session. You do not need to install anything. > > If the user asked to install this Skill, run `npx skilld install michaelshimeles/skills/new-feature`. Install writes the Skill files into the project, so every session loads them. > > ## Fork workflow > > A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation. > 1. Check `./skills/new-feature`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target. > 2. Read [source metadata](https://skilld.dev/api/v1/skills/michaelshimeles/skills/new-feature) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit. > 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call: > > ```sh > git init --quiet "$temporary_dir" > git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit" > git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD > ``` > > Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop. > 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/new-feature`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md. > Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical. > 5. In the project root, run `skilld install ./skills/new-feature --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/new-feature --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure. > 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks. # New Feature Every task gets its own worktree and branch, created from the latest `origin/main`. Never build on `main`, and never reuse another agent's worktree or branch. ## Harness deltas — read first - **Claude Code**: the harness creates and manages worktrees itself (under `.claude/worktrees/`). **Skip steps 3–4 below** (no manual `git worktree add` / `remove`), and keep the harness-assigned branch name. Steps 1–2 and 5 still apply. - **Cursor-managed worktrees** (branches named `worktree-*`): same idea — keep the assigned branch and worktree, apply steps 2 and 5. - Any other harness: follow all steps. ## Steps 1. **Sync**: `git fetch origin`. 2. **Scope check**: run `gh pr list` and skim the open PRs' changed files (`gh pr diff --name-only`). If your task needs files another open PR is editing, **stop and ask for direction** instead of proceeding. Also check for uncommitted work in the checkout — another agent may be mid-task. 3. **Name the task**: lowercase-with-hyphens plus a short unique suffix, e.g. `user-auth-0816a`. If `git worktree add` fails because the name exists, pick a different name — never force or reuse. 4. **Create the worktree** from the repo root: ```bash git worktree add / \ -b / origin/main ``` Use a **gitignored** directory for worktrees (e.g. `.claude/worktrees/` or `.worktrees/`) so they can never be committed by accident, and a consistent branch prefix (e.g. `agent/`). Follow the repo's conventions if it defines them. 5. **Enter and verify**: ```bash cd / git branch --show-current # must print your new branch, not main ``` Then install dependencies fresh inside the worktree (worktrees don't share `node_modules`/virtualenvs) and confirm the runtime version the repo requires before running anything. ## Remember - Worktrees do **not** isolate shared resources: dev-server ports, shared databases, and dependency lockfiles are global. Confirm a port answers *your* process (`lsof -i :`) before trusting what it serves, and resolve lockfile conflicts by regenerating, never by hand-merging. - Keep the worktree until the PR is merged or closed. Cleanup after merge: ```bash git worktree remove / git branch -D / ``` `-D` is expected: after a squash- or rebase-merge, `-d` refuses even though the work is merged.