Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 0 additions & 7 deletions .agents/skills/quest-complete/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .agents/skills/quest-delete/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .agents/skills/quest-export/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .agents/skills/quest-grill/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .agents/skills/quest-recurring/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .agents/skills/quest-spawn/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-complete/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-delete/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-export/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-grill/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-recurring/SKILL.md

This file was deleted.

7 changes: 0 additions & 7 deletions .claude/skills/quest-spawn/SKILL.md

This file was deleted.

16 changes: 5 additions & 11 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ It grew out of [MoQ](https://github.com/moq-dev/moq). This is the standalone
version, being built for use in other repositories.

**Early days:** validation, readiness, init/uninstall, and the planning,
execution, merge, and export skills are here. Release binaries are still being
execution, and merge skills are here. Release binaries are still being
built.

## Every plan is a file
Expand Down Expand Up @@ -266,7 +266,7 @@ the item; `--maintainer` keeps only the maintainer's, and `--json` prints
party is the maintainer's. Drafts come from
the upstream's open PRs, found as for `unblocked --unclaimed`; without the
remote, off GitHub, or when GitHub cannot be read, it lists the tree's items
and warns that drafts were skipped. `/quest-complete` walks you through them.
and warns that drafts were skipped. `/quest-run` walks you through them.

## Claim a quest

Expand Down Expand Up @@ -2168,7 +2168,7 @@ for a periodic audit of what agents keep getting wrong:
```console
$ quest messages --since 2026-11-10
2026-11-10T17:39:10.552Z claude moq-dev/quest 5f0c2a7e-9d3b-4c1a-8e6f-2b7d4a9c1e03
quest-spawn
quest-run
```

Each message shows its time, harness, repository (the checkout's GitHub
Expand Down Expand Up @@ -2455,20 +2455,14 @@ arrives with the guide sections and other skills it builds on, in one call:

| Skill | What it does |
| --- | --- |
| `quest-plan` | Ask the questions that turn an idea into scoped quests. |
| `quest-grill` | Settle open decisions through rounds of questions, each with a recommendation. |
| `quest-recurring` | Plan a quest whose finishing PR creates its next occurrence, and what gates it. |
| `quest-plan` | Ask the questions that turn an idea into scoped quests, including recurring ones whose finishing PR creates the next run. |
| `quest-import` | Bring open GitHub issues into the planning conversation. |
| `quest-export` | Turn active quests into GitHub issues before leaving Quest. |
| `quest-start` | Claim a ready quest, complete it, and open a PR. |
| `quest-spawn` | Run only `quest-run`'s quest starts: triage ready quests and send agents out in parallel, asking nothing. |
| `quest-iterate` | Iterate on an open PR to settle its open decisions, fix CI and review findings, and push. |
| `quest-review` | Review a PR's branch locally with a model other than its latest writer, then mark it ready for review. |
| `quest-merge` | Queue a PR to land, running `quest-iterate` first when it needs work. |
| `quest-complete` | Run only `quest-run`'s PR decisions and settle what quests and draft PRs wait on you: decide which open PRs to merge, clear resolved waits, queue the merges, then plan the follow-ups no quest owns yet. |
| `quest-run` | Orchestrate a project from one session: start ready quests and take PRs to merge in a loop, until only your decisions remain, then plan the follow-ups no quest owns yet. |
| `quest-run` | Orchestrate a project from one session: start ready quests, take PRs to merge, and settle what quests and drafts wait on you, in a loop until only your decisions remain, then plan the follow-ups no quest owns yet. Pass a filter such as `prs` to start no quests. |
| `quest-afk` | Keep a session such as `quest-run` going while you are away: it acts on its recommendations, defers merges, and walks you through the rest when you 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
Expand Down
8 changes: 3 additions & 5 deletions SETUP.md
Original file line number Diff line number Diff line change
Expand Up @@ -148,16 +148,14 @@ work or `/quest-import` to bring in open GitHub issues.

## Remove

1. Run `quest skill export` and follow it, so active quests become GitHub
issues. Skip this only if the user says so.
2. Run `quest uninstall`. It removes only unmodified stubs of any version, the
1. Run `quest uninstall`. It removes only unmodified stubs of any version, the
`Quests: ` line, and the merge driver, and never deletes the quest tree.
3. Remove the pin added above: the mise entry, or the flake input and dev
2. Remove the pin added above: the mise entry, or the flake input and dev
shell package. For an unpinned install, delete the `quest` binary the
installer placed (`~/.local/bin/quest` by default, or `quest.exe` in the
chosen Windows install directory). Remove any PATH entry you added. If the
user uses Quest in no other repository, run `quest setup --remove` before
removing the binary, since Quest's worktree hooks stop Claude Code making
worktrees once it cannot find `quest`.
4. Ask the user whether to delete `quest/`. Git history keeps the plans either
3. Ask the user whether to delete `quest/`. Git history keeps the plans either
way.
15 changes: 6 additions & 9 deletions assets/AGENTS.md
Original file line number Diff line number Diff line change
Expand Up @@ -130,7 +130,7 @@ Automate a step rather than leave it to a person whenever an agent can take it.
A `Maintainer:` item says why an agent cannot take the step and what automation was considered.
Record a wait there, not in a draft PR holding only evidence or steps for a person.
Unlike a blocked quest it stays ready, so it resurfaces whenever ready work is triaged instead of stalling in the backlog.
`quest waiting` lists every waiting item, the maintainer's first, ranked by what each unblocks, and `/quest-complete` walks the maintainer through them.
`quest waiting` lists every waiting item, the maintainer's first, ranked by what each unblocks, and `/quest-run` walks the maintainer through them.

A PR that launches something new for users to try, such as a site, demo, or feature, adds a follow-up quest for the maintainer to try and promote it, its `Maintainer:` item saying where to find it.

Expand Down Expand Up @@ -166,7 +166,7 @@ it over, saying how long ago it was last active.
A quest's branch is its path without `.md`.
For example, `quest/m1/foo/bar.md` is branch `quest/m1/foo/bar`.
Only claims use that namespace: no other branch is named `quest` or starts with `quest/`, since git cannot hold a branch named after another's directory.
Branches for `/quest-plan`, `/quest-recurring`, and other skill PRs use a prefix of their own, such as `quest-plan/<slug>`.
Branches for `/quest-plan`, `/quest-run`, and other skill PRs use a prefix of their own, such as `quest-plan/<slug>`.
If `quest start` names a branch in the way, stop and report it; never delete or rename it yourself.
Never rename an open PR's head branch either: GitHub closes the PR.
Its warning that the quest's local branch already exists is not that refusal: the claim succeeded, and the branch holds an earlier attempt.
Expand All @@ -192,9 +192,8 @@ Add a closing keyword for every issue under `Closes`.
## Deletion

A quest that is no longer needed or cannot be completed is abandoned.
Delete it and explain why in the PR.
Use `quest rm`, which deletes the quest and every link to it.

Delete it with `quest rm`, which deletes the quest and every link to it, edit the mentions it reports, and explain why in the PR.
A quest the user picks to delete at a pick, as `/quest-merge` offers, goes in a PR of quest deletions only, repurposing the quest's open PR if it has one, and that pick is also the pick to merge it; a planning or waits PR deletes quests among its other edits instead.
Remove the `quest` label from issues no other quest tracks.

## Coordination
Expand All @@ -217,7 +216,6 @@ While the error persists, such as a rate limit before its reset, resume and star
Answer these requests at any point, without stopping running agents:

- "finish up": start nothing new, let running agents report, then clean up and write the final summary.
- "pause": start nothing new until the user says to resume; reports are handled as usual.
- "status": a compact list of each agent with its quest or PR, state, and how long ago it started or last reported.

Once every sub-agent has finished, remove each agent checkout `quest worktree status` lists with `quest worktree remove`, since Claude never removes a subagent's checkout; it refuses one with unpreserved work.
Expand All @@ -228,9 +226,8 @@ Run each agent at an entry of `quest`'s ranked lists unless the repository's `AG
Size each `/quest-iterate` you dispatch as a quest, by the work left on its PR, and name that size in its brief.
Start it on the PR's writer, the model of its first `Implementer:` line, at the entry `quest models <size> --writer <model>` prints, or `quest models <PR size> --arm <arm>` when that line names a writer A/B arm, as `(arm B)`, naming the arm in its brief, waiting out its usage limit so the other model can review; a PR whose writer no list names, such as `unknown` or a retired model, takes its size's first entry that can run.

`quest agent start --harness <claude|codex> --model <model> --effort <level> --permission-mode <mode> <worktree> <prompt>` runs a headless agent on that CLI's own login; start it as a background command in its own isolated worktree, so the harness reports its exit like a sub-agent's.
`--permission-mode` is Claude Code's permission mode, or Codex's sandbox mode.
It prints the session id, then the outcome and the agent's final reply, and exits 3 at the account's usage limit, or 4 when the CLI is logged out, printing the login command.
`quest agent start` runs a headless agent on that CLI's own login, as its `--help` describes; start it as a background command in its own isolated worktree, so the harness reports its exit like a sub-agent's.
It exits 3 at the account's usage limit, or 4 when the CLI is logged out.
Tell the agent it cannot prompt, so it ends with its decisions and recommendations in its final reply, and that ending its turn kills its background commands, so it waits in the foreground.
Answer it in the background with `quest agent resume`, passing the same options, worktree, session id, and the answer.
Stop one with `quest agent stop <worktree>`, and each you started that still runs before you finish; `--all` would stop other sessions' agents too.
Expand Down
Loading