kixelated · Oct 22, 2026 · Oct 22, 2026 · Oct 22, 2026 · Oct 22, 2026 · Oct 22, 2026
diff --git a/.agents/skills/quest-afk/SKILL.md b/.agents/skills/quest-afk/SKILL.md
@@ -0,0 +1,7 @@
+---
+name: quest-afk
+description: Keep quest work moving while the user is away, leaving every decision for their return.
+---
+
+Run `quest skill afk` and follow its output.
+If `quest` is not installed, follow https://github.com/kixelated/quest/blob/main/SETUP.md first.
diff --git a/.claude/skills/quest-afk/SKILL.md b/.claude/skills/quest-afk/SKILL.md
@@ -0,0 +1,7 @@
+---
+name: quest-afk
+description: Keep quest work moving while the user is away, leaving every decision for their return.
+---
+
+Run `quest skill afk` and follow its output.
+If `quest` is not installed, follow https://github.com/kixelated/quest/blob/main/SETUP.md first.
diff --git a/README.md b/README.md
@@ -514,15 +514,13 @@ the version you pin decides what your agents follow:
 | `quest-ready` | Mark a draft PR ready for review, wait for an automated review, then decide whether to merge. |
 | `quest-merge` | Merge a quest's PR once CI and reviews pass, completing the quest. |
 | `quest-complete` | Decide which open PRs to merge, then merge them in parallel. |
+| `quest-afk` | Keep starting agreed work while you are away, leaving every decision for your return. |
 | `quest-delete` | Abandon a quest, deleting it in its own PR. |
 
 Use `/quest-plan` in Claude Code or `$quest-plan` in Codex. Skills coordinate
 within your agent session. A started quest stops at a pull request; merging is
 a separate invocation, so you review every change.
 
-Before stepping away, add `afk` to `/quest-spawn` or `/quest-complete`: the
-agent acts on its own recommendations and asks only before merging or deleting.
-
 To bill spawned agents to API keys instead of your agent's account, export
 `QUEST_API_KEYS` with one or more whitespace-separated keys and run
 `/quest-spawn api`. Entries may be secret references such as 1Password `op://`

diff --git a/assets/AGENTS.md b/assets/AGENTS.md
@@ -82,6 +82,8 @@ A sub-agent's brief carries the quest or PR, the user's picks, and the scope; it
 A background agent reports any decision needing user input, with context and a recommendation, to the foreground agent instead of prompting the user itself.
 Honor explicit instructions to proceed unattended within their scope; do not ask a question and then silently choose its answer.
 
+End every quest skill with a final summary in sections, such as the PRs and their states, the open decisions with recommendations, and suggested follow-ups, so a user returning to the session first sees what needs them.
+
 ## Creation
 
 Quests are created in PRs and reviewed.

diff --git a/assets/skills/afk.md b/assets/skills/afk.md
@@ -0,0 +1,23 @@
+---
+description: Keep quest work moving while the user is away, leaving every decision for their return.
+---
+
+Before you begin, run `quest guide`, `quest skill spawn`, and `quest skill complete`, and read their output completely.
+
+The user has stepped away and will not answer.
+Your goal is to keep the work they already agreed to moving, asking nothing, until only work that needs a decision remains.
+Dispatch, limit, and clean up agents as those skills describe.
+This skill takes no arguments: it filters no quests or PRs and bills agents to this session's account.
+
+Make no decisions, not even by acting on your own recommendation; skip each one and leave it for the user:
+
+- Start every ready quest that `/quest-spawn` starts without asking; leave each quest it would ask about unstarted.
+- Carry on each action the user already picked, such as a `/quest-merge` pick, until it lands or needs the user again.
+- Pick no skip, `/quest-ready`, `/quest-iterate`, `/quest-merge`, or `/quest-delete` for a PR the user has not, so nothing merges or is deleted on your judgment. A started agent still runs `/quest-ready` itself when its quest finishes with no decisions, as `/quest-start` describes.
+- Answer no decision an agent reports. Its PR stays a draft whose `## Decisions needed` section lists the decision with a recommendation.
+- Hold `/quest-plan` sessions, stale claims, and suggested follow-ups for the user.
+
+As merges land, recompute the ready quests and start any that newly qualify.
+Finish once every agent has reported, every picked action has landed or needs the user, and no quest remains that starts without asking.
+
+Write the final summary so a new session can act on it without this one's context, letting the user start fresh on their return: link each quest and PR, give each skipped decision with its options and your recommendation, and describe every follow-up the agents suggested fully enough to hand to `/quest-plan`.
diff --git a/assets/skills/complete.md b/assets/skills/complete.md
@@ -43,12 +43,3 @@ Dispatch already selected actions before asking the next question; background wo
 
 Once every sub-agent has finished, remove local worktrees and branches whose tip is the head of a merged PR; squash merges leave that tip off the base branch.
 Leave the worktree you are running in and any holding uncommitted work; list those in your summary.
-
-## Unattended
-
-With an `afk` argument, the user has stepped away: your recommendation stands in for their pick of skip, `/quest-ready`, or `/quest-iterate`, so dispatch it without asking.
-It also answers each simple decision a sub-agent reports.
-Still ask about each `/quest-merge` and `/quest-delete` you recommend, as one simple question with your recommendation first.
-Skip a PR or reported decision that is not simple, noting why in the summary instead of asking.
-Hold suggested `/quest-plan` follow-ups for the summary, since planning is an interview.
-The rest of the argument still filters the PRs in scope.
diff --git a/assets/skills/spawn.md b/assets/skills/spawn.md
@@ -51,15 +51,6 @@ Run selected `/quest-plan` sessions in the foreground.
 Once every sub-agent has finished, remove local worktrees and branches whose tip is the head of a merged PR; squash merges leave that tip off the base branch.
 Leave the worktree you are running in and any holding uncommitted work; list those in your summary.
 
-## Unattended
-
-With an `afk` argument, the user has stepped away: your recommendation stands in for their pick of `/quest-start`, skip, `/quest-ready`, or `/quest-iterate`, so act on it without asking.
-It also answers each simple decision an agent reports, including when you resume a headless agent.
-Still ask about each `/quest-merge` and `/quest-delete` you recommend, as one simple question with your recommendation first.
-Skip a quest, PR, or reported decision that is not simple, noting why in the summary instead of asking.
-Hold `/quest-plan` sessions, including deprioritizing and suggested follow-ups, for the summary, since planning is an interview.
-The rest of the argument still filters the quests in scope.
-
 ## API keys
 
 With an `api` argument, bill agents to API keys instead of this session's account: run each as a headless agent through `quest agent` rather than as a sub-agent.

diff --git a/quest/m0/helpers/README.md b/quest/m0/helpers/README.md
@@ -56,7 +56,6 @@ commands from Sep-Oct. Session counts in each child come from that window.
 
 ## Required
 
-- [Unattended work](/quest/m0/helpers/afk.md) - `/quest-afk` replaces the `afk` argument: it skips every decision and keeps starting agreed work; every skill ends with a summary
 - [PR state commands](/quest/m0/helpers/pr-states.md) - `quest iterate`, `ready`, `merge`, and `release` label the one owner of a PR
 - [Complete loop](/quest/m0/helpers/complete-loop.md) - `/quest-complete` re-scans PRs, keeps picks and holds, and counts rounds per PR
 - [Headless agents](/quest/m0/helpers/headless-agents.md) - `/quest-spawn api` launches, resumes, and stops billed agents through one command auto mode allows

diff --git a/quest/m0/helpers/afk.md b/quest/m0/helpers/afk.md
diff --git a/quest/m0/helpers/complete-loop.md b/quest/m0/helpers/complete-loop.md
@@ -28,4 +28,3 @@ edits through this plan.
 ## Related
 
 - [PR state commands](/quest/m0/helpers/pr-states.md) - also rewrites how `complete` dispatches and skips held PRs
-- [Unattended work](/quest/m0/helpers/afk.md) - carries on picks the user already made
diff --git a/src/cli/skills.ts b/src/cli/skills.ts
@@ -6,6 +6,7 @@
 // upgrading never rewrites repository files.
 
 import guide from "../../assets/AGENTS.md";
+import afk from "../../assets/skills/afk.md";
 import audit from "../../assets/skills/audit.md";
 import complete from "../../assets/skills/complete.md";
 import del from "../../assets/skills/delete.md";
@@ -65,6 +66,7 @@ export class Skill {
 
 /** Every skill, sorted by name. */
 export const SKILLS: readonly Skill[] = Object.entries({
+	afk,
 	audit,
 	complete,
 	delete: del,

diff --git a/test/cli.test.ts b/test/cli.test.ts
@@ -82,7 +82,7 @@ test("skill lists every skill", () => {
 test("skill rejects an unknown name", () => {
 	const out = run("skill", "nope");
 	expect(out.code).toBe(1);
-	expect(out.stderr).toMatch(/^quest: no skill named nope \(have: audit, /);
+	expect(out.stderr).toMatch(/^quest: no skill named nope \(have: afk, audit, /);
 });
 
 test("usage errors exit 2", () => {
Original file line number	Diff line number	Diff line change
Expand Up		@@ -28,4 +28,3 @@ edits through this plan.
		## Related

		- [PR state commands](/quest/m0/helpers/pr-states.md) - also rewrites how `complete` dispatches and skips held PRs
		- [Unattended work](/quest/m0/helpers/afk.md) - carries on picks the user already made