@iceinvein/agent-skills 0.21.4 → 0.21.5

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@iceinvein/agent-skills",
-  "version": "0.21.4",
+  "version": "0.21.5",
   "description": "Install agent skills into AI coding tools",
   "author": "iceinvein",
   "license": "MIT",

package/skills/index.json

@@ -283,7 +283,7 @@
     "name": "sluice",
     "description": "Routes work by change shape into four channels (bypass, fast, main, deep) and applies only the rules each channel needs, so a one-line fix does not pay the cost of a multi-subsystem build. Carries seven rules as one-liners in the router and the full treatment in references read only on friction. Checks the finished plan with plan.sh validate rather than trusting it to memory, seeds the run state from it, keeps a deep run's task breakdown in .sluice/run.json so a statusline segment, one status command and a SessionStart hook can answer where the run is (the hook prints a live run at every session start, compaction included), and closes each run with a ledger read out of the session transcript: elapsed, tools, tokens, and what each dispatched agent cost where the transcript recorded it. Claude Code only; stands down where the superpowers pipeline governs the repo.",
     "type": "prompt",
-    "version": "0.23.0"
+    "version": "0.23.1"
   },
   {
     "name": "temporal-coupling-detector",

package/skills/sluice/SKILL.md

@@ -28,9 +28,14 @@ Two subsystems is `main`; the third is what makes it `deep`.
 
 `bypass`, `fast`, and `main` proceed without stopping for approval; only
 `deep` stops: once for design sign-off before code, once for the plan and
-pre-flight together before Task 1. A stop ends your turn. Asking a question
-with a tool is not one, however many options it carried: the answer comes
-back to you and the run never left your hands.
+pre-flight together before Task 1. A stop ends your turn.
+
+A choice that is your partner's to make goes to them through `AskUserQuestion`
+wherever the harness has it, at a stop or between them: options to pick from,
+your recommendation first, not a paragraph or a lettered list to reply to.
+Asking is not itself a stop, however many options it carried, because the
+answer comes back to you and the run never left your hands. So at a stop, ask
+with the tool, then end the turn once the answers are in.
 
 Name the channel and the signal that actually routed you there. The strings above
 are examples, not fixed copy, and a channel with a two-part signal should say
@@ -66,9 +71,9 @@ announces nothing to measure from.
 One line each. Read the reference only on friction: the moment you notice
 yourself wanting to skip the rule, or arguing that this one is the exception.
 
-- **Agree intent** before building. One question at a time. Propose approaches
-  with a recommendation, not a survey. `main` agrees in a message, `deep` writes
-  it down. `references/intent.md`
+- **Agree intent** before building. One question at a time, through
+  `AskUserQuestion`. Propose approaches with a recommendation, not a survey.
+  `main` agrees in a message, `deep` writes it down. `references/intent.md`
 - **Test first.** The test comes before the code; run it while it should
   still be failing, then write the least code that turns it green. Skip that
   watching step and a green result is only an unchecked guess. A test no
@@ -104,7 +109,10 @@ collapses to `fast`.
 
 Design to `docs/specs/YYYY-MM-DD-<topic>.md`, plan to
 `docs/plans/YYYY-MM-DD-<topic>.md`, unless the repo has a convention or
-your partner states a preference. Get the design signed off before code.
+your partner states a preference. Get the design signed off before code. When
+the design's shape turns on a fork only your partner can settle, ask that one
+question through `AskUserQuestion`, with your recommendation, before the design
+is written. `references/deep-channel.md` has the test for what counts.
 
 Take the design stop through the harness's plan mode where there is one. Its
 gate is enforced rather than requested and it holds edits shut while it is open,
@@ -162,8 +170,9 @@ instead of to the branch at large.
 
 Pre-flight rides in that same stop: which flagged tasks get a reviewer, which
 mechanical ones the plan marked for low effort, and whether the work runs
-in a worktree. Ask them as choices with the counts in them, never as a
-paragraph, then end the turn. Task 1 opens on their next
+in a worktree. Ask them through `AskUserQuestion`, one question each with the
+counts in the options, never as a paragraph or a lettered list, then end the
+turn on the answers. Task 1 opens on their next
 instruction, and an answer that already carries one is that instruction. A
 session that dispatches only when asked has not ruled dispatch out, it has made
 this question the place to ask; genuine unavailability is the tool not being

package/skills/sluice/references/deep-channel.md

@@ -155,7 +155,7 @@ a fork only your partner can settle, one whose answer changes the design's
 shape (where state lives, what shares it, which process owns it) rather than a
 value the design can leave as config, ask it as one question with your
 recommendation before the design is written, and write the design on the
-answer. Ask it with the question tool where there is one, which returns the
+answer. Ask it with `AskUserQuestion` where there is one, which returns the
 answer without ending the turn; without one, the question is a stop of its
 own, and the design is written, to its file, on the next turn. A design drafted
 across both branches of a fork doubles the reading and still has to be
@@ -186,19 +186,23 @@ enforcement was.
 ## Pre-flight
 
 Design signed off, plan written, nothing built yet. Before Task 1, stop once
-and settle three things with your partner. Ask them as questions with options,
-not as a paragraph they have to reply to in prose: what you are after is a
-decision, and a wall of considerations asks them to extract the decision from
-it first.
-
-This stop is the plan's sign-off as well, so it ends your turn, and a
-question tool does not end it for you. That tool returns an answer without
-returning control: two options came back, the plan itself did not, and your
+and settle three things with your partner. Ask them with `AskUserQuestion`,
+one question per decision, your recommendation as the first option and the
+counts in the option text: what you are after is a decision, and a wall of
+considerations asks them to extract the decision from it first. A lettered
+list in prose is that same paragraph with letters on it, still something to
+reply to rather than pick from.
+
+This stop is the plan's sign-off as well, so it ends your turn, and the tool
+does not end it for you. It returns the answers without returning control:
+the options came back, the plan itself did not, and if you carry on, your
 partner reads the summary of it in the same message as Task 1's first edit,
-by which point their only remaining move is to interrupt. Ask the questions,
-then end the turn on the answers and let the next instruction start the
+by which point their only remaining move is to interrupt. So ask with the
+tool, then end the turn on the answers and let the next instruction start the
 build. If the answers arrive with that instruction already attached, you have
-your sign-off and Task 1 begins.
+your sign-off and Task 1 begins. Where the harness has no question tool, the
+same questions go at the end of the message as numbered options with the
+recommendation marked, and the turn ends on them.
 
 **Review.** Name the tasks the table below sends to a reviewer, each with the
 trigger that qualified it, and say how many of the rest skip with a ledger

package/skills/sluice/references/finish.md

@@ -18,7 +18,8 @@ Confirm the base branch instead of assuming it; untangling a wrong merge
 costs far more than asking would have.
 
 With the suite green and the base confirmed, put exactly three options to
-your partner, with the run ledger above them so the choice is made against
+your partner through `AskUserQuestion`, with the run ledger in the message
+above them so the choice is made against
 what the work actually cost rather than against your account of it;
 `references/meter.md` owns that. Say in one clause whether the work was
 reviewed. Merging reviewed work and merging unreviewed work are different
@@ -53,7 +54,7 @@ the one list of them. In order:
    controller stat read plus the final whole-plan pass rather than a per-task
    dispatch" is the accurate line, and it is a coverage level rather than a
    debt. Where nothing was priced, it is a debt and says so.
-5. The three options, and nothing after them.
+5. The three options, asked through `AskUserQuestion`, and nothing after them.
 
 A `deep` run closes when the work stops being yours to act on: after a local
 merge and its re-run of the suite, or when your partner leaves the branch where

package/skills/sluice/references/intent.md

@@ -1,7 +1,9 @@
 # Agree intent
 
-Ask one question at a time. Use multiple choice when the answer set is
-bounded.
+Ask one question at a time, through `AskUserQuestion` where the harness has
+it, with the options as choices and your recommendation first. Prose is the
+fallback for a harness without the tool or an answer set that is genuinely
+open, not the default.
 
 Offer two or three approaches, never a survey. Put your top pick first
 and explain what makes it the better bet. Cut every feature YAGNI would

package/skills/sluice/skill.json

@@ -1,6 +1,6 @@
 {
   "name": "sluice",
-  "version": "0.23.0",
+  "version": "0.23.1",
   "description": "Routes work by change shape into four channels (bypass, fast, main, deep) and applies only the rules each channel needs, so a one-line fix does not pay the cost of a multi-subsystem build. Carries seven rules as one-liners in the router and the full treatment in references read only on friction. Checks the finished plan with plan.sh validate rather than trusting it to memory, seeds the run state from it, keeps a deep run's task breakdown in .sluice/run.json so a statusline segment, one status command and a SessionStart hook can answer where the run is (the hook prints a live run at every session start, compaction included), and closes each run with a ledger read out of the session transcript: elapsed, tools, tokens, and what each dispatched agent cost where the transcript recorded it. Claude Code only; stands down where the superpowers pipeline governs the repo.",
   "author": "iceinvein",
   "type": "prompt",