Skip to content
Development
Skill

/sw-auto

Run a SpecWeave increment unattended until every task is done, then verify and close. Use for "auto mode", "run until done", "ship this while I sleep".

From plugin
specweave
16422 skills1 agent
Install
$ npx -y skills add anton-abyzov/specweave --skill sw-auto --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/sw-auto

Context preview

The summary Claude sees to decide when to auto-load this skill.

Run a SpecWeave increment unattended until every task is done, then verify and close. Use for "auto mode", "run until done", "ship this while I sleep".

SKILL.md

sw-auto.SKILL.md
description: Run a SpecWeave increment unattended until every task is done, then verify and close. Use for "auto mode", "run until done", "ship this while I sleep".
argument-hint: "[increment-ids...] [--dry-run|--reset]"
version: 3.0.0

sw-auto: run until done

Auto mode is the sw-do loop without stopping to ask. The bar does not drop: claim before editing, a passing test for every `done`, verify before closing.

Start

1. The spec has no open questions and every task has `Files` and a `Test`. If not, fix the spec first. 2. `specweave auto 0042` records the session (`--dry-run` previews it, `--reset` clears stale state). In a tool that runs SpecWeave's Stop hook (Claude Code with the `sw` plugin) the hook hands you the remaining work after every turn until nothing is left. In any other tool, nothing feeds you back: keep looping yourself. 3. `specweave auto-status` shows progress; `specweave cancel-auto` stops it.

Each turn

1. `specweave task next` → `specweave task claim T-NN` → implement inside its `Files` → commit `0042: ...` → `specweave task done T-NN --run "<Test>"`. 2. A failing test is fixed in the next turn, never marked done. 3. Genuinely blocked (missing secret, ambiguous spec, external dependency): `specweave task block T-NN --reason "<what is missing>"` and move on. Blocked tasks still count as work left: when only blocked tasks remain, run `specweave cancel-auto` and tell the user what each one needs, instead of looping until the turn limit. 4. Nothing claimable left: run sw-done (verify, review, complete).

Running out of budget

Before the session ends for tokens or time: `specweave handoff --reason "auto: out of tokens"`. The next session, in any tool or account, says "pick up" and continues.

Manual path (no CLI)

Without the CLI there is no hook and no session file: follow the manual path of sw-do in a loop until every task in spec.md has a `done` or `skip` line, then sw-done.

Rules

  • Never edit `.specweave/state/auto-mode.json` by hand; `specweave auto --reset` clears it.
  • One auto session per project; check `specweave auto-status` before starting another.
  • Never widen a task's `Files` or weaken a test to keep the loop moving.
Read more
Ships withspecweave

Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.

Get the whole plugin
Stats
164
Stars
21
Forks
Active
Maintenance
TypeScript
Language
MIT
License
11h ago
Last commit
11mo ago
Created

Repo: anton-abyzov/specweave

Other skills on specweave.