Auto-run - take the recommended option and keep going
The user said to run without them. A session parked on a question costs them the whole time they are away and buys
nothing; a wrong ruling costs rework they can see and undo. So every ask that would go to them takes its
(Recommended) option, every such choice is written down, and only the acts below still stop the run.
When to use
- The user's words: 'auto mode', 'auto-run', 'run without asking', 'take the recommended options', 'continue without
me', or that they are away.
- It is on from that message for the rest of the session. A message the user types mid-run keeps it on and is
answered; a message starting with 'stop auto run' turns it off for the rest of the session.
- This repo's own skill; the stack's typed mode for consuming projects is a different thing.
The ledger
ONE run ledger holds the mode for the whole run, however many plans it spans: the ledger file the user's run already
names, else docs/superpowers/<YYYY-MM-DD>-auto-run.md under the project root.
- The first action writes
Auto-run: on - '<the user's words>' into the run ledger, directly under its title.
- Rulings made while a plan executes go to that plan's
docs/superpowers/sdd/<plan basename>/progress.md too.
- After a compaction, Read the run ledger's
Auto-run: line before the next ask: it is how the mode outlives the
summary.
- 'stop auto run' appends
Auto-run: off - <date>.
The rule
- Every ask that would go to the user takes its
(Recommended) option, and the ledger gets
Ruling: <the ask> - <the option taken> - <cost if wrong>.
- An ask with no marked option takes the option you would recommend, ledgered the same way.
- The user's own words about how to run ('one by one without stopping') outrank a prompt file's or a plan's own
'one task only': finish a task, write its ledger line, start the next in the same turn.
What still stops
- A push, a merge, a version bump, a billed run (named with its cost), anything irreversible or outward-facing (a
publish, a deletion outside the scratchpad and the docs root with no backup, a message to another person), and a
security-sensitive action - unless the user's own words in this session already authorised that exact act.
- A merge can be refused even then: Claude Code's auto permission mode denied a
gh pr merge the user had asked
for (2026-11-04). When the run will end in a merge, ask for it before the user leaves - they merge it themselves
(! gh pr merge <n> --merge) or add a permission rule for it. Never route around a denial; what depends on the
merge, such as tags or a marketplace move, waits with it.
- A guard's security ask - a credential shown, work discarded, a write outside the project, a protective guard
switched off - is never auto-run's to answer, whatever the user authorised around it: take its safe option and list
the act under
Left for you. Only the user's own pick of its unsafe option opens it; a reply that merely implies it
does not (2026-11-04: a discard guard refused a receipt written on such a reply).
- A plan so broken that every path forward is a guess.
- The approval of a design - a graded spec or plan, or a bounded in-chat design (the user's ruling). Words in the
user's request that hand the approval of plans or specs to you waive them, all kinds at once - 'approve the graded
specs and plans yourself', 'even plans approval must be done by you', 'plans included' (B2, ruled 2026-11-04). A
request that only names a plan or spec as its work ('implement plans/x.md without stopping') does not, and neither do
the trigger words above; with the waiver, the score path or the design is reported in place of the ask.
- A stop names the one decision it needs.
Scope
Work the request does not name is not done. It goes in a ## Optional list in the close, each line
Recommended - <reason> or Not worth it - <reason>.
Tool permission prompts follow Claude Code's permission mode; this skill changes none.
The close
Done: <what the request asked for, and whether it is met>
Changed: <files, and each commit with its subject>
Checks: <each command run, with its result line>
Decisions auto-mode made for you:
- <the ask> - <the option taken>
Left for you: <each outward act, each NOT RUN and why> | none
1---2name: auto-run3description: "Load before the first step when the user is away or says 'auto mode', 'without stopping', 'run without asking' or 'take the recommended options'."4metadata:5 source: https://skillmd.com/skills/envoydev/auto-run6---78# Auto-run - take the recommended option and keep going910The user said to run without them. A session parked on a question costs them the whole time they are away and buys11nothing; a wrong ruling costs rework they can see and undo. So every ask that would go to them takes its12`(Recommended)` option, every such choice is written down, and only the acts below still stop the run.1314## When to use1516- The user's words: 'auto mode', 'auto-run', 'run without asking', 'take the recommended options', 'continue without17 me', or that they are away.18- It is on from that message for the rest of the session. A message the user types mid-run keeps it on and is19 answered; a message starting with 'stop auto run' turns it off for the rest of the session.20- This repo's own skill; the stack's typed mode for consuming projects is a different thing.2122## The ledger2324ONE run ledger holds the mode for the whole run, however many plans it spans: the ledger file the user's run already25names, else `docs/superpowers/<YYYY-MM-DD>-auto-run.md` under the project root.26271. The first action writes `Auto-run: on - '<the user's words>'` into the run ledger, directly under its title.282. Rulings made while a plan executes go to that plan's `docs/superpowers/sdd/<plan basename>/progress.md` too.293. After a compaction, Read the run ledger's `Auto-run:` line before the next ask: it is how the mode outlives the30 summary.314. 'stop auto run' appends `Auto-run: off - <date>`.3233## The rule3435- Every ask that would go to the user takes its `(Recommended)` option, and the ledger gets36 `Ruling: <the ask> - <the option taken> - <cost if wrong>`.37- An ask with no marked option takes the option you would recommend, ledgered the same way.38- The user's own words about how to run ('one by one without stopping') outrank a prompt file's or a plan's own39 'one task only': finish a task, write its ledger line, start the next in the same turn.4041## What still stops4243- A push, a merge, a version bump, a billed run (named with its cost), anything irreversible or outward-facing (a44 publish, a deletion outside the scratchpad and the docs root with no backup, a message to another person), and a45 security-sensitive action - unless the user's own words in this session already authorised that exact act.46 - A merge can be refused even then: Claude Code's auto permission mode denied a `gh pr merge` the user had asked47 for (2026-11-04). When the run will end in a merge, ask for it before the user leaves - they merge it themselves48 (`! gh pr merge <n> --merge`) or add a permission rule for it. Never route around a denial; what depends on the49 merge, such as tags or a marketplace move, waits with it.50- A guard's security ask - a credential shown, work discarded, a write outside the project, a protective guard51 switched off - is never auto-run's to answer, whatever the user authorised around it: take its safe option and list52 the act under `Left for you`. Only the user's own pick of its unsafe option opens it; a reply that merely implies it53 does not (2026-11-04: a discard guard refused a receipt written on such a reply).54- A plan so broken that every path forward is a guess.55- The approval of a design - a graded spec or plan, or a bounded in-chat design (the user's ruling). Words in the56 user's request that hand the approval of plans or specs to you waive them, all kinds at once - 'approve the graded57 specs and plans yourself', 'even plans approval must be done by you', 'plans included' (B2, ruled 2026-11-04). A58 request that only names a plan or spec as its work ('implement plans/x.md without stopping') does not, and neither do59 the trigger words above; with the waiver, the score path or the design is reported in place of the ask.60- A stop names the one decision it needs.6162## Scope6364Work the request does not name is not done. It goes in a `## Optional` list in the close, each line65`Recommended - <reason>` or `Not worth it - <reason>`.6667Tool permission prompts follow Claude Code's permission mode; this skill changes none.6869## The close7071```text72Done: <what the request asked for, and whether it is met>73Changed: <files, and each commit with its subject>74Checks: <each command run, with its result line>75Decisions auto-mode made for you:76- <the ask> - <the option taken>77Left for you: <each outward act, each NOT RUN and why> | none78```