chore(memory): BDR-091 BDR-092 LRN-155..157, journal 2026-09-16

.claude/memory/decisions.md

@@ -100,6 +100,8 @@ rules:
 | BDR-088 | 2026-09-15 | gstack Playwright bump shared via lib, re-applied after submodule update; update helper never touches the submodule tree | accepted |
 | BDR-089 | 2026-09-15 | No Playwright browser-cache pruner; read-only doctor report — .links proved 0 bytes reclaimable | accepted |
 | BDR-090 | 2026-09-15 | Destructive shell work → autoMode soft_deny/hard_deny; `ask` tier abandoned (inert under auto) | accepted |
+| BDR-091 | 2026-09-16 | Ask, don't guess: open-choice sweep (3 classes) at plan step + mid-run CLASS channel supersede "one question upfront" | accepted |
+| BDR-092 | 2026-09-16 | docker + node framed by the classifier via autoMode.allow + soft_deny; ask entries retired | accepted |
 
 ---
 
@@ -1157,3 +1159,22 @@ Branch feature/user-writing-web-rules, UNMERGED (human gate).
 - **Caveat**: the guardrail `hard_deny` bars REMOVING a `deny`/`soft_deny`/`hard_deny` entry, not adding one. Future loosening goes through `/permissions` or the user's own edit — deliberate, confirmed with the user.
 - **Status**: accepted.
 - **Reference**: `settings.json`, `doctor.sh` `check_automode`, `templates/settings/SETTINGS.md`. Links [[LRN-153]], [[LRN-146]], [[BDR-004]].
+
+## BDR-091 — Ask, don't guess: open-choice sweep + mid-run channel supersede "one question upfront"
+- **Date**: 2026-09-16
+- **Decision**: `CLAUDE.global.md` rule → ask on a VISIBLE (placement, wording, order, behavior), PUBLIC NAME (command, flag, endpoint, file) or SCOPE ("X too?") choice the request leaves open, even mid-task; class 4 (internal technical, no observable effect) never. `lib/contract-interview.md` STEP 2 = CLARIFY: pass A (gaps: outcome / scope / constraints) at contract time; pass B (open-choice sweep, 3 classes) ONCE at each flow's PLAN step, no question cap, >5 open → under-specified, list + stop; "you decide" recorded `A: delegated — <default>`, never re-asked. New MID-RUN CLARIFICATION: executor halts `NEED-DECISION` + `CLASS:` tag; visible / public-name / scope → human verbatim; internal → loop decides, max 2 round-trips. New HOW TO ASK (LRN-102: ≤4 → one AskUserQuestion, context in option descriptions; else plain text ending the turn). Wiring: feat STEP 1, bugfix STEP 3, hotfix LOCATE (pass A stays silent autofill; one re-dispatch on class-tagged BLOCKED = the sole hotfix re-dispatch), ship-feature STEP 2, init-project STEP 3; interviewer: class 1-3 item never `(assumed)`, one extra targeted question. Executors (feater, bugfixer, hotfixer) report the class. Locks: contract-verifier (9), loops-light (hotfix), gates (3).
+- **Why**: gap-only trigger structurally blind to taste — "add a share icon" passes outcome / scope / constraints and the icon lands wherever the executor put it; raising the 3-question cap changes nothing. feat:153 / bugfix:165 told the orchestrator "make the decision HERE", twice, before escalating = institutional guessing. Fresh re-dispatch keeps the tree, loses the executor's reasoning → a plan-time batch costs less than the same question mid-run; the mid-run channel stays for leftovers.
+- **Alternatives rejected**: bigger budget (quota was never the limiter); new `lib/clarify.md` (extra hop, STEP 2 already the mandatory passage every orchestrator runs); global rule only (skills carried explicit counter-instructions — `zero questions ever`, `make the decision HERE`, `max 3 questions` — the specific beats the general).
+- **Risk watched**: chattiness. Brakes = class 4 exclusion + over-5 guard. hotfix identity (speed, silence) = the flow to watch; if pass B fires on most hotfixes the class definitions are too wide, not the flow.
+- **Status**: accepted. Behavioral check OPEN: `/feat "add a share icon to the header"` must ask placement before dispatch; the fully specified variant must ask nothing → record in `evals.md`.
+- **Reference**: spec + plan `docs/superpowers/{specs,plans}/2026-09-16-ask-dont-guess*` (purged at finish, in history at `22ce57f`), commits `9eb6934..22ce57f`, merge `56bd035`. Supersedes the `CLAUDE.global.md:51` rule line. Refines [[BDR-049]] (contract), applies [[LRN-102]]. Links [[LRN-157]].
+
+## BDR-092 — docker + node framed by the classifier (`autoMode.allow`), `ask` rules retired
+- **Date**: 2026-09-16
+- **Decision**: `Bash(docker run|exec *)`, `Bash(docker[-| ]compose up*)`, `Bash(node -e *)` out of `permissions.ask`. New `autoMode.allow` (`$defaults` first): (1) local dev containers — `docker exec/run/compose` against a workstation container whose name lacks `prod`/`production`, running a repo SQL file or script inside, output piped; Remote Shell Writes / Production Reads / Sensitive Remote Exec scoped to sensitive-named hosts; a literal `DROP/TRUNCATE/DELETE` on the command line stays under Mass Delete. (2) project-local node — `node <file>`, `npm run`/`pnpm`/`yarn` scripts, `npx`/`pnpm exec` of a lockfile-declared package, effects in cwd. +2 `soft_deny`: docker data destruction (`rm -f`, `volume rm/prune`, `system prune`, `compose down -v`, `--privileged`, bind mount outside cwd); undeclared node packages (`npx`/`dlx` absent from lockfile, `npm install <name>`). `model` bump to fable 5.1 committed alongside.
+- **Why**: real gate = built-in `Remote Shell Writes` / `Production Reads` soft_deny catching `docker exec` into `supabase_db_game`; inside the classifier `allow` = exception tier (hard_deny > soft_deny > allow > explicit intent). Static `Bash(node *)` allow is suspended under auto (wildcarded interpreter) → prose is the only lever for a conditional node permission; `awk`/`echo` statics short-circuit, `node` cannot. `ask` inert on 2.1.273 (probe, [[LRN-155]]) — retiring it is forward-safe: if the documented prompt behavior lands, those entries would prompt for exactly what should run free.
+- **Alternatives rejected**: static `permissions.allow` for docker (short-circuits the classifier, framing impossible); keep the `ask` entries (inert today, wrong tomorrow); strict on every `.sql` (blocks the repo's verify scripts).
+- **Trade-off accepted**: a repo SQL file runs even when its content is opaque to the classifier — local dev DB only, resettable.
+- **Guardrail**: S6 (loosening = user's own edit) overridden explicitly by the user for this change; diff reviewed on the branch before merge.
+- **Status**: accepted. Verified: `jq` valid; `claude auto-mode config` shows the 4 entries with `$defaults` expanded; `doctor.sh` autoMode PASS; live `docker exec -i supabase_db_game psql … -f - < verify/0043 … | tail` → `ROLLBACK`, exit 0, no prompt. `claude auto-mode critique` printed nothing (2.1.273).
+- **Reference**: `settings.json`, `templates/settings/SETTINGS.md` (`autoMode.allow` row + interpreter note), commit `5eccc3f`, merge `ddadca6`. Links [[BDR-090]], [[LRN-153]], [[LRN-155]], [[LRN-156]].

.claude/memory/journal.md

@@ -471,3 +471,8 @@ rules:
 - `make test` 0 RED, `doctor.sh` 0 errors, `shellcheck` clean.
 - graphify skill untracked + gitignored (written by `graphify install --platform claude` since `~/.claude/skills` symlinks to `skills/`). Cost one self-inflicted incident: `git rm --cached` kept the files, `gitflow finish` deleted them at the merge ([[LRN-154]]). Restored at 0.9.61, guarded configs snapshotted and verified untouched.
 - `.claude/settings.local.json` 14.6 KB -> 6.2 KB. It was not just duplication: its local `deny` still carried the 4 rules moved out of global deny, making [[BDR-090]]'s soft_deny a dead letter in this repo, and its `allow` carried `sed *` / `cp *` / `python3 -`, which short-circuit the classifier on the same rules.
+
+## 2026-09-16
+- Ask, don't guess ([[BDR-091]]): spec + plan, 9 lock-first tasks (contract-interview CLARIFY two passes, MID-RUN CLARIFICATION with `CLASS:` tag, HOW TO ASK; global rule; feat / bugfix / hotfix / ship-feature / init-project wired; interviewer; 3 executors), suite green. Behavioral fixture check still open ([[LRN-157]]).
+- docker + node under auto mode ([[BDR-092]]): `ask` entries retired (inert on 2.1.273, probe — [[LRN-155]]), `autoMode.allow` + 2 soft_deny, live `docker exec … psql` OK. Static interpreter allow is suspended under auto → prose only ([[LRN-156]]).
+- Both merged into develop 2026-09-17 via gitflow (`ddadca6`, `56bd035`), two stack conflicts (TODO, CHANGELOG) resolved keeping both blocks. Symlinked `settings.json` follows the checkout: live config = whatever branch is out.

.claude/memory/learnings.md

@@ -144,6 +144,9 @@ rules:
 | LRN-152 | 2026-09-15 | git `protocol.file=user` blocks submodule fixtures; `-c` misses the code under test, `GIT_CONFIG_*` env does not | tests building git fixtures |
 | LRN-153 | 2026-09-15 | `autoMode` lists replace built-ins without `"$defaults"`; a user-scope block reaches every project | any `autoMode` edit |
 | LRN-154 | 2026-09-15 | `git rm --cached` + merge into a branch that still tracks the file DELETES it from disk | untracking a generated file |
+| LRN-155 | 2026-09-16 | ask under auto: doc says prompt, probe on 2.1.273 says no; re-probe after upgrades | any permission-tier reasoning |
+| LRN-156 | 2026-09-16 | autoMode.allow = exception tier; static interpreter allow suspended under auto → conditions live in prose | conditional permissions |
+| LRN-157 | 2026-09-16 | gap-only trigger blind to taste → add a trigger class, not budget; ask at plan, mid-run for leftovers | any "ask more" request |
 
 ---
 
@@ -1469,3 +1472,21 @@ Rule: when editing a doctrine file under structure locks, grep the test's lock s
 - **Future application**: untracking any generated file — know the regeneration command BEFORE merging, and `ls` the path right after `finish`. If nothing regenerates it, keep it tracked.
 - **graphify specifics**: `graphify install --platform claude` copies the skill and touches nothing else. `graphify claude install` is a different command — it writes the CLAUDE.md section and the `.claude/settings.json` hooks, rewrites both guarded configs, and does NOT copy the skill. Confusing the two wastes a recovery attempt.
 - **Reference**: `CLAUDE.md` machine-owned section, commit 80ccdaf. Links [[BDR-090]].
+
+## LRN-155 — `permissions.ask` under auto mode: the probe beats the doc
+- **Date**: 2026-09-16
+- **Pattern**: `auto-mode-config` + `permissions` docs say a content-scoped `ask` rule (`Bash(git push *)`) is evaluated BEFORE the classifier and always prompts, even in auto mode. Probe on 2.1.273: `node -e 'console.log(...)'` matching `Bash(node -e *)` in `ask` ran, no prompt, exit 0. [[LRN-146]] holds. Either the doc describes a later build or "content-scoped" means something narrower; observed wins.
+- **Future application**: before reasoning about a permission tier, probe it with a benign command matching the rule; re-probe after every Claude Code upgrade — the day `ask` starts prompting, every leftover `ask` entry becomes a nag for things meant to run free.
+- **Reference**: [[BDR-092]], `templates/settings/SETTINGS.md` "ask is not a prompt" §.
+
+## LRN-156 — Conditional permissions live in classifier prose, not static rules
+- **Date**: 2026-09-16
+- **Pattern**: `autoMode.allow` = exception tier: an entry overrides a matching `soft_deny`, built-in or own (precedence hard_deny > soft_deny > allow > explicit intent). Under auto, static allow rules granting arbitrary execution (`Bash(*)`, wildcarded interpreters like `Bash(node *)`) are suspended → classifier anyway; non-interpreter statics (`awk`, `echo`) resolve before it. A condition ("package declared in the lockfile", "container is local dev") is therefore expressible ONLY as `autoMode.allow` prose. Word it narrowly: it punches through built-in rules too.
+- **Tooling**: `claude auto-mode defaults` prints the built-in lists (grep it for the rule that bit); `claude auto-mode config` = effective lists with `$defaults` expanded; `claude auto-mode critique` printed nothing on 2.1.273. Shell-snapshot `claude` wrapper is broken (`exec command claude` → "command: not found") → call `~/.local/bin/claude` directly.
+- **Reference**: [[BDR-092]], [[LRN-153]].
+
+## LRN-157 — Taste is invisible to a gap-only trigger; ask at plan time
+- **Date**: 2026-09-16
+- **Pattern**: a trigger that fires only on missing outcome / scope / constraints lets every taste choice through — "add a share icon" is complete by those criteria and the icon's side is decided downstream. More budget changes nothing; the fix is a new trigger class (VISIBLE / PUBLIC NAME / SCOPE). Cost geometry: a fresh re-dispatch keeps the working tree and loses the executor's reasoning → the same question costs about one executor run more mid-run than at PLAN. So: sweep once at the plan step, keep the mid-run channel for leftovers. Executor tags the class; orchestrator re-reads it (tag = hint, a mis-tag would offload class 4 onto the human). Relayed questions obey [[LRN-102]]: context inside `AskUserQuestion`, nothing the user needs printed before it.
+- **Future application**: any "ask more" request → check WHICH trigger is blind before touching a quota. Any orchestrator with a "decide it yourself" fallback on an executor halt → route by class first.
+- **Reference**: [[BDR-091]], `lib/contract-interview.md` STEP 2 + MID-RUN CLARIFICATION.

.claude/tasks/TODO.md

@@ -1,5 +1,56 @@
 # TODO
 
+## 2026-09-16 — docker + node framed by the classifier (feature/automode-docker-node)
+User: `docker exec -i supabase_db_game psql … -f - < supabase/verify/*.sql | tail`
+must run unprompted under auto mode; same for node/npm/npx when the package
+is declared and effects stay in the cwd; "ajoute du soft deny pour bien le
+cadrer". Findings: `ask` is inert under auto (LRN-146 re-verified on 2.1.273
+with a `node -e` probe; the docs claim otherwise for content-scoped rules);
+the real gate is the built-in `Remote Shell Writes` / `Production Reads`
+classifier rules; a static `Bash(node *)` allow rule is suspended under auto
+(wildcarded interpreter), so `autoMode.allow` prose is the only lever for
+node. User approved the design and the `ask` removal explicitly (S6 override
+for this change, diff reviewed on the branch).
+- [x] A1 `settings.json` — drop 4 docker + `node -e` from `ask`; new
+      `autoMode.allow` (`$defaults` + local dev containers + project-local
+      node); 2 `soft_deny` entries (docker data destruction, undeclared
+      node packages); `model` bump committed separately
+- [x] A2 `templates/settings/SETTINGS.md` — `autoMode.allow` tier row +
+      why a static interpreter allow rule cannot do it; LRN-146 re-verify note
+- [x] A3 CHANGELOG [Unreleased] Changed
+- [x] A4 verify (2026-09-16, all green; `critique` printed nothing): `jq`, `claude auto-mode config`,
+      `doctor.sh`, live `docker exec` in game
+- [x] A5 registries written 2026-09-17: LRN (doc vs observed `ask` under auto,
+      2.1.273; `autoMode.allow` = exception tier; wildcarded-interpreter
+      allow suspended), BDR-090 addendum
+## 2026-09-16 — ask, don't guess: orchestrators ask about open choices (feature/ask-dont-guess)
+User: the orchestrators (ship-feature, feat, hotfix, bugfix, init-project)
+settle choices they should ask about ("cet icône, plutôt à gauche ou à
+droite ?"), even mid-run. Diagnosis: contract-interview STEP 2 only fires on
+gaps (outcome / scope / constraints), so a taste choice never triggers a
+question; feat:153 and bugfix:165 tell the orchestrator to "make the
+decision HERE" on NEED-DECISION. Decisions (user, 2026-09-15/16): global
+rule changes for all work, hotfix included; classes VISIBLE / PUBLIC NAME /
+SCOPE ask, internal technical choices never. Spec:
+`docs/superpowers/specs/2026-09-16-ask-dont-guess-design.md`; plan:
+`docs/superpowers/plans/2026-09-16-ask-dont-guess.md` (9 tasks, lock-first).
+- [x] P1 `lib/contract-interview.md` — STEP 2 CLARIFY (pass A gaps, pass B
+      open choices), MID-RUN CLARIFICATION, HOW TO ASK; 9 locks in
+      `contract-verifier.test.sh`
+- [x] P2 `CLAUDE.global.md:51-55` — "Ask rather than guess" replaces the
+      one-question rule; bug line reconciled
+- [x] P3 `skills/feat/SKILL.md` — pass B at STEP 1, NEED-DECISION routed on class
+- [x] P4 `skills/bugfix/SKILL.md` — pass B at STEP 3, NEED-DECISION routed on class
+- [x] P5 `skills/hotfix/SKILL.md` — pass B at LOCATE, tagged BLOCKED relayed;
+      lock `loops-light.test.sh:84`
+- [x] P6 `skills/ship-feature` STEP 2 + `skills/init-project` contract §/STEP 3
+- [x] P7 `agents/interviewer.md` — visible/public/scope item never `(assumed)`
+- [x] P8 `agents/{feater,bugfixer,hotfixer}.md` — CLASS tag; 3 locks in `gates.test.sh`
+- [x] P9 `make test` green (2026-09-16), CHANGELOG, TODO tick; manual behavioral check still OPEN before merge
+- [x] P10 registries written 2026-09-17: BDR (supersedes the one-question rule),
+      LRN (taste is invisible to a gap-only trigger; fresh re-dispatch cost
+      favors plan-time questions)
+
 ## 2026-09-15 — align config + deployment on the hand-edited settings.json (feature/automode-config-alignment)
 User edited global `settings.json` by hand: 4 destructive rules moved
 deny→ask (`rsync`, `kill -9`, `killall`, `pkill`), 4 removed from ask

CHANGELOG.md

@@ -28,6 +28,40 @@ Format follows [Keep a Changelog](https://keepachangelog.com/).
   destructive command under auto mode.
 
 ### Changed
+- **Docker and node go through the classifier with a framing, instead of
+  an inert `ask` tier.** `Bash(docker run|exec *)`, `Bash(docker[-| ]compose
+  up*)` and `Bash(node -e *)` leave `permissions.ask` (no prompt under auto
+  mode, re-verified on 2.1.273). A new `autoMode.allow` list, `$defaults`
+  first, names the two routine cases the built-in `Remote Shell Writes` /
+  `Production Reads` rules were catching: `docker exec`/`run`/`compose`
+  against a local dev container whose name does not carry `prod`, running a
+  SQL file or script from the repo inside it; and project-local node
+  (`node <file>`, `npm run`, `npx`/`pnpm exec` of a lockfile-declared
+  package, effects inside the cwd). Two `soft_deny` entries frame what that
+  opens: docker data destruction (`rm -f`, `volume rm`/`prune`, `system
+  prune`, `compose down -v`, `--privileged`, bind mounts outside the cwd)
+  and undeclared node packages (`npx`/`dlx` of a package absent from the
+  lockfile, `npm install <name>`). `SETTINGS.md` gains the `autoMode.allow`
+  tier and the reason a static `Bash(node *)` rule cannot do this job.
+- **Ask, don't guess: the orchestrators ask about open choices instead of
+  settling them.** `CLAUDE.global.md` replaces "one question upfront, never
+  mid-task" with: a choice visible in the result, a name that becomes
+  public, or a scope the request does not settle → ask, even mid-task;
+  internal technical choices stay Claude's. `lib/contract-interview.md`
+  STEP 2 becomes CLARIFY: pass A (the three gap checks, at contract time)
+  and pass B (the open-choice sweep in three classes, run once at each
+  flow's PLAN step, no question cap, over-5 guard, "you decide" recorded as
+  delegated). New MID-RUN CLARIFICATION section: an executor's
+  `NEED-DECISION` carries a `CLASS:` tag; visible / public-name / scope go
+  to the user verbatim, internal is decided in the loop; answers land in
+  the contract `[gated]`. New HOW TO ASK section (LRN-102). `/feat`,
+  `/bugfix`, `/hotfix`, `/ship-feature`, `/init-project` wire pass B at
+  their plan step; `/feat` and `/bugfix` stop deciding `NEED-DECISION`
+  themselves; `/hotfix` drops "zero questions ever" and allows one
+  re-dispatch for a class-tagged BLOCKED; the interviewer never ships a
+  visible / public-name / scope item as `(assumed)`; feater, bugfixer and
+  hotfixer report the class. Locks updated in the `contract-verifier`,
+  `loops-light` and `gates` tests.
 - **The classifier, not `permissions.ask`, now guards destructive shell
   work** (BDR-090). Ten rules left the static tiers: `rsync`, `kill -9`,
   `killall`, `pkill` out of `deny`, and `python3 -c`, `python -c`,

CLAUDE.global.md

@@ -48,11 +48,15 @@ Apply unless repo-specific instructions override.
   calls. Skill-mandated gates (fresh verifier/security/challenge)
   always dispatch as written. Don't redo delegated work by hand —
   failed gates re-dispatch fresh executors instead.
-- One question upfront if needed — don't interrupt mid-task.
+- Ask rather than guess. A choice visible in the result (placement,
+  wording, order, behavior), a name that becomes public (command, flag,
+  endpoint, file), or a scope the request does not settle → ask, even
+  mid-task. Batch what can be batched. Internal technical choices with
+  no observable effect stay yours.
   *Exception: skill-mandated gates and checkpoints (orchestrator
   validation gates, approval gates, darwin checkpoints) always fire.*
 - Bug received → fix directly: check logs, find root cause, resolve
-  autonomously.
+  autonomously; a visible choice in the fix still gets asked.
 - Something goes wrong → STOP, re-plan. Never push through.
 - Deviations: minor or clearly justified → do, explain after.
   Significant or shaky justification → ask before deviating.

agents/bugfixer.md

@@ -27,8 +27,9 @@ Every choice was made in the plan or is a NEED-DECISION to report.
 
 - Apply the FIX PLAN to the letter — fix the ROOT CAUSE named in DIAGNOSIS,
   not the symptom. A plan hole or an open choice (naming, data shape, API
-  surface, dependency) → STOP, report `NEED-DECISION` with the precise
+  surface, dependency, a user-visible choice such as placement, wording or
-  question. Never re-investigate or improvise a different fix.
+  behavior) → STOP, report `NEED-DECISION` with the precise question and
+  its `CLASS:`. Never re-investigate or improvise a different fix.
 - Stay inside the contract FILE SCOPE. A needed file outside it →
   `NEED-DECISION` (the orchestrator owns scope changes); don't touch it.
 - Add or update the regression test the plan names — it must fail before the
@@ -73,5 +74,6 @@ FILE(S)  : <created/modified paths>
 TEST(S)  : <regression test added/updated + final suite run result, verbatim line>
 SMOKE    : <build/typecheck result if run, or n/a>
 NOTES    : <DONE: deviations (must be none) | NEED-DECISION: the exact
-           question + the options you see | BLOCKED: the blocker verbatim>
+           question + the options you see + CLASS: visible | public-name |
+           scope | internal | BLOCKED: the blocker verbatim>
 ```

agents/feater.md

@@ -37,8 +37,9 @@ report below is optional on this path (the dispatcher needs the edit applied
 ## EXECUTION RULES
 
 - Follow the plan to the letter. A plan hole or an open choice (naming,
-  data shape, API surface, dependency) → STOP, report `NEED-DECISION` with
+  data shape, API surface, dependency, a user-visible choice such as
-  the precise question. Never improvise a design decision.
+  placement, wording or behavior) → STOP, report `NEED-DECISION` with the
+  precise question and its `CLASS:`. Never improvise a design decision.
 - Stay inside the contract FILE SCOPE. A needed file outside it →
   `NEED-DECISION` (the orchestrator owns scope changes); don't touch it. On
   the applier path the scope is the files named in the bundle item — apply
@@ -84,5 +85,6 @@ STATUS   : DONE | NEED-DECISION | BLOCKED
 FILES    : <created/modified paths>
 TESTS    : <added/updated + final suite run result, verbatim line>
 NOTES    : <DONE: deviations (must be none) | NEED-DECISION: the exact
-           question + the options you see | BLOCKED: the blocker verbatim>
+           question + the options you see + CLASS: visible | public-name |
+           scope | internal | BLOCKED: the blocker verbatim>
 ```

agents/hotfixer.md

@@ -43,6 +43,10 @@ the edit applied + self-verified, not the report grammar).
   BLOCKED`, report why (the orchestrator escalates to `/bugfix`), never
   expand scope yourself. On the applier path it is the files named in the
   bundle item — apply only those.
+- An open user-visible choice the contract does not settle (placement,
+  wording, behavior) → `STATUS BLOCKED` with `CLASS: visible | public-name |
+  scope` in NOTES, BEFORE editing anything. The orchestrator asks the user
+  and re-dispatches once.
 - If tests exist for the affected code, run them. Detection cascade:
   ```bash
   # JS/TS
@@ -78,5 +82,6 @@ STATUS  : DONE | BLOCKED
 FILE(S) : <changed files — suffix files you CREATED with " (new)">
 FIX     : <one-line description>
 SMOKE   : <test/build result, verbatim line>
-NOTES   : <BLOCKED: the blocker; DONE: none>
+NOTES   : <BLOCKED: the blocker, + CLASS: visible | public-name | scope when
+          you halted at an open choice before editing; DONE: none>
 ```

agents/interviewer.md

@@ -14,13 +14,13 @@ Gather context. Produce complete PROJECT BRIEF as single source of truth.
 - If the initial prompt already provides name + purpose + stack + features + architecture → skip questions and generate the BRIEF directly.
 - Otherwise ask only what's genuinely missing, in a single structured block.
 - After answers: produce BRIEF. One follow-up allowed if answer is ambiguous.
-- Hard budget: 2 question rounds total (initial block + one follow-up). The BRIEF ships after round 2 no matter what — gaps become OPEN DECISIONS, never a third round.
+- Hard budget: 2 question rounds total (initial block + one follow-up) for gaps. The BRIEF ships after round 2 — gaps become OPEN DECISIONS. Sole exception: a VISIBLE, PUBLIC NAME or SCOPE choice (a user-facing placement or wording, a public command/flag/endpoint name, whether X is in scope) still open after round 2 gets ONE more targeted question; it never ships as `(assumed)`.
 
 ## FAILURE MODES
 
 | Trigger | First response | If still unresolved |
 |---|---|---|
-| Answer vague/ambiguous | One targeted follow-up on that item only | Record item in OPEN DECISIONS with the safest reading, marked `(assumed)` — never invent a confident value |
+| Answer vague/ambiguous | One targeted follow-up on that item only | Gap: record it in OPEN DECISIONS with the safest reading, marked `(assumed)` — never invent a confident value. Visible / public-name / scope item: one more targeted question instead, never `(assumed)` |
 | "I don't know / you decide" | Propose ONE concrete default + why, ask yes/no | Take the default, mark `(assumed)`, list in OPEN DECISIONS |
 | Contradictory answers (e.g. embedded runtime + managed cloud DB) | Name the contradiction, ask which side wins | Put BOTH options in OPEN DECISIONS; do not silently pick one |
 | Partial answer to the block | Re-ask ONLY the missing items in the follow-up round | Missing fields → `none stated` + OPEN DECISIONS entry |
@@ -77,6 +77,6 @@ Stop after BRIEF. Orchestrator handles next step.
 - Design, architect, or implement anything — the BRIEF is the entire deliverable.
 - Recommend a stack/framework unless the user asks or a FAILURE MODES default applies.
 - Re-ask a question the initial prompt or a previous answer already covered.
-- Exceed the 2-round budget, whatever is still missing.
+- Exceed the 2-round budget for gaps; the only extra question is the single targeted one a visible / public-name / scope item earns.
 - Fill any BRIEF field with an invented value — `(assumed)` + OPEN DECISIONS is the only path for gaps.
 - Editorialize on the user's choices (no "great choice", no unsolicited warnings — one factual flag in OPEN DECISIONS if a choice conflicts with a stated constraint).

lib/contract-interview.md

@@ -7,8 +7,9 @@ subagents = execution + report only; gates and loop decisions live in the
 main loop).
 
 Run this in the ORCHESTRATOR MAIN LOOP, never in a subagent — STEP 2 may
-talk to the human. Mandatory passage in every flow; questions are optional
+talk to the human, at contract time (pass A) and again at the flow's PLAN
-and proportional — a complete request goes through silently.
+step (pass B). Questions follow the open choices, never a quota — a complete
+request goes through silently.
 
 ## STEP 1 — CAPTURE (verbatim)
 
@@ -17,16 +18,51 @@ message). No paraphrase, no cleanup, no translation, no summarizing. This
 section is IMMUTABLE for the life of the run — every later consumer
 (planner, dev, verifier) reads THESE words, never a restatement.
 
-## STEP 2 — AMBIGUITY CHECK (questions optional, proportional)
+## STEP 2 — CLARIFY (ask, never guess)
 
-Ask ONLY if one of these is missing AND not derivable from the repo:
+Two passes, both in the main loop, both may talk to the human.
+
+**Pass A — gaps.** Run here, against the request. Ask if one of these is
+missing AND not derivable from the repo:
 - a testable expected outcome
 - an unambiguous scope (what is allowed to change)
 - non-contradictory constraints
 
-Complete request → ZERO questions, stay silent. Otherwise: max 3 questions,
+**Pass B — open choices.** Defined here, run ONCE at the flow's PLAN step
-one single batch (house rule: one question upfront, never mid-task). Never
+(see "Where pass B fires" below), against the plan just written — that is
-ask what the repo can answer — verify paths/APIs/behavior yourself first.
+where choices become concrete. Enumerate every choice the run will settle
+that the request leaves open; keep those in these classes:
+1. VISIBLE — the user would see it in the result: placement, label, wording,
+   color, order, what a click does.
+2. PUBLIC NAME — a name that outlives the run: command, flag, endpoint, env
+   var, a file the human will read.
+3. SCOPE — "should X change too?", where the request does not name X.
+
+NEVER ask class 4 — internal technical choices with no observable effect
+(function decomposition, data shape, local naming, layout inside an
+already-scoped zone). Those are delegated; asking them is the noise that
+makes classes 1-3 ignorable. Never ask what the repo or the request already
+answers — verify paths/APIs/behavior yourself first.
+
+No question cap. Each pass asks what it finds, in ONE batch. A request that
+leaves nothing open goes through silently. More than 5 open choices in pass B
+= the request is under-specified: list them, say so, stop — do not fire a
+questionnaire. "You decide" / "peu importe" is an answer: record it as
+`A: delegated — <default taken>` and never re-ask it.
+
+Pass B answers land in the contract's CLARIFICATIONS marked
+`[gated <YYYY-MM-DD>]` — the contract is already on disk by then.
+
+### Where pass B fires
+
+| Flow | Pass B runs at | Against |
+|------|----------------|---------|
+| feat | STEP 1 PLAN, before 1b CHALLENGE | the PLAN checklist |
+| bugfix | STEP 3 FIX PLAN, before 3b | the FIX PLAN |
+| hotfix | STEP 1 LOCATE | the 1-2 target files' visible effect |
+| ship-feature | STEP 2 PLAN, after the brainstorm | the plan, minus what the brainstorm settled |
+| init-project | STEP 3 DESIGN, before VALIDATION GATE #1 | the DESIGN, minus what the interview and brainstorm settled |
+| onboard | its STEP 3 interview, unchanged | scope, in one block |
 
 ## STEP 3 — DERIVE
 
@@ -85,7 +121,7 @@ Template:
 <the user's exact words>
 
 ## CLARIFICATIONS
-Q: <question> / A: <answer>
+Q: <question> / A: <answer>   (pass B and mid-run entries: [gated <YYYY-MM-DD>])
 (or: none — request complete)
 
 ## ACCEPTANCE CRITERIA
@@ -105,6 +141,33 @@ Q: <question> / A: <answer>
 Print one line to the user, then continue the flow:
 `CONTRACT: <path> — <n> criteria, scope <files|repo-wide>, <q> questions asked`
 
+## MID-RUN CLARIFICATION (the channel executors halt into)
+
+An executor cannot talk to the human. It halts with `NEED-DECISION`, the
+exact question, the options it sees, and a `CLASS:` tag (visible |
+public-name | scope | internal). `/hotfix`: the hotfixer keeps
+`DONE | BLOCKED`; a BLOCKED carrying the tag follows the same routing instead
+of escalating to `/bugfix`. The orchestrator re-reads the class — the tag is
+a hint, not a verdict — then routes:
+- visible / public-name / scope → ASK THE HUMAN, verbatim question and
+  options. Never decide these yourself, never spend a round-trip guessing.
+- internal → decide here, note the decision, re-dispatch. The only case the
+  orchestrator settles alone; max 2 such round-trips → escalate.
+
+Every answer, human or orchestrator, appends to the contract's
+CLARIFICATIONS marked `[gated <YYYY-MM-DD>]` — the same micro-gate as scope
+enrichment — and to the plan handed to the FRESH re-dispatched executor,
+which reads the decision from disk, never from a transcript.
+
+## HOW TO ASK (LRN-102)
+
+The harness reliably renders only the turn's FINAL text; text printed before
+a tool call may be swallowed. So:
+- up to 4 questions → one `AskUserQuestion` call; option descriptions carry
+  the context; print nothing the user needs before the call.
+- more than 4, or a list handed back for re-specification → plain text, end
+  the turn.
+
 ## Lifecycle
 
 - **REQUEST**: immutable, for the life of the run. Never rewritten, never
@@ -134,7 +197,7 @@ Print one line to the user, then continue the flow:
 
 | Flow | Weight |
 |------|--------|
-| hotfix | Silent autofill — criteria: "symptom gone; build/tests green"; scope = the 1-2 target files. Zero questions ever. |
+| hotfix | Pass A silent autofill — criteria: "symptom gone; build/tests green"; scope = the 1-2 target files. Pass B runs at LOCATE against the 1-2 target files' visible effect; a typo fix asks nothing. |
 | feat / bugfix | Proportional. bugfix: the DIAGNOSIS feeds the criteria (symptom reproduced-then-gone + regression test present). |
 | ship-feature | Full. Design decisions approved at the validation gate append criteria `[gated <date>]` — the human validates the enriched contract, the verifier receives that version. |
 | init-project | Full. The interviewer's PROJECT BRIEF pours into the contract (V1 features → criteria). |

lib/tests/contract-verifier.test.sh

@@ -48,8 +48,15 @@ fi
 tf  "verbatim request immutable"      "$LIB" "REQUEST (verbatim — IMMUTABLE)"
 tf  "contracts dir committed path"    "$LIB" ".claude/tasks/contracts/"
 tf  "unique per-run slug"             "$LIB" "<YYYY-MM-DD>-<slug>-<HHMM>"
-tf  "silent when complete"            "$LIB" "ZERO questions"
+tf  "silent when nothing open"        "$LIB" "goes through silently"
-tf  "question budget"                 "$LIB" "max 3 questions"
+tf  "no question cap"                 "$LIB" "No question cap"
+tf  "pass B classes"                  "$LIB" "PUBLIC NAME"
+tf  "class 4 excluded"                "$LIB" "NEVER ask class 4"
+tf  "over-5 guard"                    "$LIB" "More than 5 open choices"
+tf  "delegated answer"                "$LIB" "delegated —"
+tf  "mid-run channel"                 "$LIB" "## MID-RUN CLARIFICATION"
+tf  "class tag"                       "$LIB" "CLASS:"
+tf  "how to ask"                      "$LIB" "## HOW TO ASK"
 tf  "aborted status"                  "$LIB" "status: aborted"
 tf  "never left dirty"                "$LIB" "NEVER left dirty"
 tf  "scope enrichment micro-gate"     "$LIB" "micro-gate"

lib/tests/gates.test.sh

@@ -311,6 +311,9 @@ lock "bugfixer passes"         "$BF" "## FOUR PASSES"
 lock "bugfixer stays minimal"  "$BF" "keep the fix minimal"
 lock "bugfixer neg control"    "$BF" "**Negative control.**"
 lock "bugfixer test must fail" "$BF" "A test that passes both ways"
+lock "feater class tag"        "$FE" "CLASS:"
+lock "bugfixer class tag"      "$BF" "CLASS:"
+lock "hotfixer class tag"      "$REPO/agents/hotfixer.md" "CLASS:"
 
 echo ""
 echo "gates: $PASS pass, $FAIL fail"

lib/tests/loops-light.test.sh

@@ -81,7 +81,7 @@ tf "hotfixer report grammar"    "$HOT" "HOTFIX-EXEC REPORT"
 
 echo "── skills/hotfix/SKILL.md (hotfix wiring — revert, not loop) ──"
 tf "hotfix silent contract"     "$HSKL" "STEP 1.7 — CONTRACT (silent autofill)"
-tf "hotfix zero questions"      "$HSKL" "questions ever"
+tf "hotfix pass B at locate"    "$HSKL" "run pass B of"
 tf "hotfix security gate"       "$HSKL" "Security gate (fresh auditor)"
 tf "hotfix block reverts"       "$HSKL" "failure REVERTS, never loops"
 tf "hotfix no verifier"         "$HSKL" "No verifier is dispatched at hotfix weight"

settings.json

@@ -224,13 +224,8 @@
       "Bash(curl * | sh)",
       "Bash(wget * | sh)",
       "Bash(mkfifo *)",
-      "Bash(node -e *)",
       "Bash(git push *)",
       "Bash(git push)",
-      "Bash(docker run *)",
-      "Bash(docker exec *)",
-      "Bash(docker-compose up*)",
-      "Bash(docker compose up*)",
       "Bash(brew install *)",
       "Bash(apt install *)",
       "Bash(apt-get install *)",
@@ -250,7 +245,7 @@
     "disableBypassPermissionsMode": "disable",
     "additionalDirectories": []
   },
-  "model": "opus[1m]",
+  "model": "claude-fable-5-1[1m]",
   "hooks": {
     "SessionStart": [
       {
@@ -360,6 +355,11 @@
   "inputNeededNotifEnabled": true,
   "skipAutoPermissionPrompt": true,
   "autoMode": {
+    "allow": [
+      "$defaults",
+      "Local dev containers: `docker exec`, `docker run`, `docker compose up`/`exec`/`logs`/`ps` against a container running on this workstation whose name does not carry `prod` or `production` (a local Supabase or Postgres such as `supabase_db_*`) is routine development, not a remote shell into a shared host. Running a SQL file or script that lives in the repo inside it (`psql -f`, migrations, verify scripts) and piping the output through `tail` or `grep` passes. Remote Shell Writes, Production Reads and Sensitive Remote Exec apply only to hosts named as sensitive in Environment or carrying `prod`. A literal `DROP`, `TRUNCATE` or `DELETE` without a predicate typed on the command line stays under Mass Delete.",
+      "Project-local node: `node <file>`, `npm run`, `pnpm` or `yarn` scripts, and `npx` or `pnpm exec` of a package declared in the project's manifest or lockfile, with effects inside the current working directory, pass like `awk` or `echo`. `node -e` that computes or edits inside the working directory passes; the soft block on inline interpreters that delete or write outside it still applies."
+    ],
     "soft_deny": [
       "$defaults",
       "Scope of intent: an instruction clears a SOFT BLOCK for the current turn only. An approval given in an earlier turn is not an approval now, and the same action repeated in a later turn has to be asked for again.",
@@ -368,7 +368,9 @@
       "Sending SIGKILL (`kill -9`) or killing processes by name (`killall`, `pkill`). These reach processes outside this session, including the user's editors, shells, dtach sessions and background jobs, and the target is chosen by a pattern, so a typo kills the wrong thing. Clear only when the user named the process in this turn.",
       "Editing more than one file in place in a single command: `sed -i` or `perl -pi` over a glob, or a loop over `git ls-files`. The damage is not loss, since git recovers it, but a diff spanning hundreds of files that nobody reads before committing. `sed -i` on a single named file passes. Clear only when the user asked for the sweep.",
       "Moving or renaming a directory inside the repo (`mv src/api src/api_old`, or any `mv` of a tree). It breaks imports and paths silently, and the breakage surfaces far from the command. Clear only when the user asked for that move.",
-      "An inline interpreter or `xargs` that deletes, or that writes outside the current working directory: `python3 -c`, `python -c` or `node -e` calling `rmtree`, `remove`, `unlink` or `truncate`; `xargs` feeding `rm`, `mv` or `dd`. `find ... | xargs rm` is the case that matters, since it routes around the `find * -exec rm` deny rule. Reading, computing, and editing a file inside the working directory pass untouched."
+      "An inline interpreter or `xargs` that deletes, or that writes outside the current working directory: `python3 -c`, `python -c` or `node -e` calling `rmtree`, `remove`, `unlink` or `truncate`; `xargs` feeding `rm`, `mv` or `dd`. `find ... | xargs rm` is the case that matters, since it routes around the `find * -exec rm` deny rule. Reading, computing, and editing a file inside the working directory pass untouched.",
+      "Docker data destruction on this workstation: `docker rm -f`, `docker volume rm` or `prune`, `docker system prune`, `docker compose down -v` (drops named volumes, which hold local database data with no undo), and `docker run` with `--privileged` or a bind mount outside the current working directory. Clear only when the user named the container or volume in this turn.",
+      "Undeclared node packages: `npx <pkg>`, `pnpm dlx` or `yarn dlx` of a package absent from the manifest and lockfile runs code fetched at call time; `npm install <name>` or `pnpm add <name>` adds a dependency the house rule requires naming first. Clear only when the user named the package in this turn."
     ],
     "hard_deny": [
       "$defaults",

skills/bugfix/SKILL.md

@@ -116,6 +116,10 @@ RISK: <low/medium — what could go wrong>
   obvious fix.
 - If the fix is significant (>10 lines, multiple files,
   behavior change): wait for user approval.
+- Then run pass B of `$HOME/.claude/lib/contract-interview.md` against the
+  FIX PLAN: every VISIBLE / PUBLIC NAME / SCOPE choice it settles that the
+  bug report left open → one batch of questions, before STEP 3b. The trivial
+  fast-path is not exempt: a 1-line fix with a visible choice still asks.
 
 ## STEP 3b — CHALLENGE THE FIX PLAN (before the contract)
 Unless the fix is the trivial 1-2 line case STEP 3 already fast-paths, the
@@ -135,8 +139,8 @@ the STEP 3 approval gate.
 Run `$HOME/.claude/lib/contract-interview.md` (main loop). The DIAGNOSIS
 feeds it: REQUEST verbatim = the bug report as received; ACCEPTANCE CRITERIA
 = the symptom reproduced-then-gone + a regression test present and passing;
-FILE SCOPE = the FIX PLAN files. Questions stay proportional (a clear,
+FILE SCOPE = the FIX PLAN files. Pass A only here (pass B ran at STEP 3); a
-reproduced bug → zero). It writes the contract to
+clear, reproduced bug asks nothing. It writes the contract to
 `.claude/tasks/contracts/<date>-<slug>-<HHMM>.md`; keep the path — the
 executor reads it first and GATE 1 (STEP 6) hands it to a fresh verifier.
 
@@ -162,9 +166,11 @@ ops, no security dispatch. Finish with the BUGFIX-EXEC REPORT."
 
 Parse the `BUGFIX-EXEC REPORT`:
 - `STATUS : DONE` → STEP 6.
-- `STATUS : NEED-DECISION` → make the decision HERE (that is reflection),
+- `STATUS : NEED-DECISION` → route on its `CLASS:` per MID-RUN CLARIFICATION
-  append it to the plan, re-dispatch a FRESH bugfixer with plan + decision.
+  in `$HOME/.claude/lib/contract-interview.md`: visible / public-name / scope
-  Max 2 decision round-trips → escalate to the user.
+  → ask the user, verbatim; internal → decide HERE (max 2 such round-trips
+  → escalate). Append the answer to the contract `[gated]` and to the plan,
+  re-dispatch a FRESH bugfixer with plan + decision.
 - `STATUS : BLOCKED` → surface the blocker to the user, stop.
 
 ## STEP 6 — VERIFY + SECURE + PRE-COMMIT GATE + COMMIT (main loop, LRN-083)

skills/feat/SKILL.md

@@ -85,9 +85,9 @@ MEMORY; feed STEP 1 PLAN. Inline consumption — reader = planner, no injection.
 ## STEP 0.7 — CONTRACT
 
 Run `$HOME/.claude/lib/contract-interview.md` (main loop — you are it). It
-captures the request verbatim, asks 0-3 questions PROPORTIONAL to ambiguity
+captures the request verbatim, runs pass A (gaps: outcome, scope,
-(a complete request → zero questions, silent), derives testable acceptance
+constraints — a complete request goes through silently), derives testable
-criteria + file scope, and writes the contract to
+acceptance criteria + file scope, and writes the contract to
 `.claude/tasks/contracts/<date>-<slug>-<HHMM>.md`. Keep the path — the
 executor reads it first and GATE 1 (STEP 4) hands it to a fresh verifier.
 
@@ -114,8 +114,11 @@ PLAN:
   [ ] <test file> — <test to add>
 ```
 
-If the approach is ambiguous: ask the user ONE focused question BEFORE
+Then run pass B of `$HOME/.claude/lib/contract-interview.md` against this
-dispatching — never after (the executor cannot relay questions).
+plan: every VISIBLE / PUBLIC NAME / SCOPE choice the plan settles that the
+request left open → one batch of questions BEFORE dispatching; answers land
+in the contract's CLARIFICATIONS `[gated]` and in the plan. A choice that
+surfaces only during execution comes back as `NEED-DECISION` (STEP 3).
 
 ## STEP 1b — CHALLENGE THE PLAN (before branching)
 The STEP 1 plan is a reflection worth attacking before a branch is spent on it.
@@ -125,8 +128,8 @@ Persist it to `.claude/tasks/plans/<date>-<slug>-<HHMM>.md`, then run
 Three blind challengers attack it; RE-THINK every aspect a BLOCKER lands (a named
 plan change, or `[deferred]`), re-challenge once if the plan materially changed. The
 STEP 3 executor receives the REVISED plan. Before dispatch, print a CHALLENGE SUMMARY
-(BLOCKERs addressed / deferred / lenses returned), surfacing any deferred BLOCKER via
+(BLOCKERs addressed / deferred / lenses returned), surfacing any deferred BLOCKER in
-STEP 1's one-question gate.
+the STEP 1 pass B batch.
 
 ## STEP 2 — BRANCH
 
@@ -150,9 +153,11 @@ Finish with the FEAT-EXEC REPORT."
 
 Parse the `FEAT-EXEC REPORT`:
 - `STATUS : DONE` → STEP 4.
-- `STATUS : NEED-DECISION` → make the decision HERE (that is reflection),
+- `STATUS : NEED-DECISION` → route on its `CLASS:` per MID-RUN CLARIFICATION
-  append it to the plan, re-dispatch a FRESH feater with plan + decision.
+  in `$HOME/.claude/lib/contract-interview.md`: visible / public-name / scope
-  Max 2 decision round-trips → escalate to the user.
+  → ask the user, verbatim; internal → decide HERE (max 2 such round-trips
+  → escalate). Append the answer to the contract `[gated]` and to the plan,
+  re-dispatch a FRESH feater with plan + decision.
 - `STATUS : BLOCKED` → surface the blocker to the user, stop.
 
 ## STEP 4 — VERIFY + SECURE (fresh gates, bounded loops)

skills/hotfix/SKILL.md

@@ -47,6 +47,10 @@ git log --oneline -3
   as `/bugfix` (root-cause investigation, then a scoped fix)."
 - Settle the proposed fix HERE — the executor cannot ask questions, so the
   exact edit (what changes, in which file(s)) must be closed before dispatch.
+- Then run pass B of `$HOME/.claude/lib/contract-interview.md` against that
+  edit: a VISIBLE / PUBLIC NAME / SCOPE choice the bug description leaves
+  open (which way the icon aligns, the label's wording) → ask before
+  dispatch. A typo or a wrong value asks nothing.
 
 OPTIONAL — memory check (exempt by default; hotfix = obvious fix, mirror of its capitalize
 skip). For a RECURRING or urgent bug only, a quick blockers-only glance may save time:
@@ -66,8 +70,9 @@ Follow `$HOME/.claude/lib/design-gate.md`:
 
 ## STEP 1.7 — CONTRACT (silent autofill)
 
-Run `$HOME/.claude/lib/contract-interview.md` at hotfix weight: **zero
+Run `$HOME/.claude/lib/contract-interview.md` at hotfix weight: pass A is a
-questions ever** (a hotfix is an obvious fix by definition). Autofill the
+silent autofill (a hotfix is an obvious fix by definition); pass B already
+ran at STEP 1, ask nothing more here. Autofill the
 contract — REQUEST verbatim = the bug description as given; ACCEPTANCE
 CRITERIA = "symptom gone; build/tests green"; FILE SCOPE = the 1-2 target
 files from STEP 1. It writes `.claude/tasks/contracts/<date>-<slug>-<HHMM>.md`.
@@ -135,8 +140,14 @@ security dispatch, no revert. Finish with the HOTFIX-EXEC REPORT."
 Parse the `HOTFIX-EXEC REPORT`:
 - `STATUS : DONE` → STEP 4 (the SMOKE line in the report decides pass/fail
   there; DONE here means execution completed, not that it verified clean).
-- `STATUS : BLOCKED` → if any edits were made, revert ONLY the executor's
+- `STATUS : BLOCKED` with `CLASS: visible | public-name | scope` in NOTES →
-  files: `git restore --source=$PRE -- <FILE(S) from the report>` and delete
+  the executor halted at an open choice before editing (nothing to revert):
+  ask the user per MID-RUN CLARIFICATION in
+  `$HOME/.claude/lib/contract-interview.md`, append the answer to the
+  contract `[gated]`, re-dispatch ONCE with the closed choice. This is the
+  one re-dispatch hotfix allows; it is not a retry of a failed attempt.
+- `STATUS : BLOCKED` otherwise → if any edits were made, revert ONLY the
+  executor's files: `git restore --source=$PRE -- <FILE(S) from the report>` and delete
   any NEW file the report lists (untracked, absent from $PRE). Never
   `git restore .` — it would wipe the tolerated pre-existing edits too.
   Surface the blocker to the user; STOP. One attempt only — hotfix never
@@ -227,9 +238,10 @@ trivial hotfix still produces a `chore(memory): journal — …` commit (Frame 2
 - Reflection (LOCATE, contract, gate decisions) NEVER leaves this main
   loop; execution NEVER stays in it — the executor is the sonnet-pinned
   hotfixer subagent (BDR-066).
-- The executor is dispatched FRESH, once — hotfix never re-dispatches (no
+- The executor is dispatched FRESH, once — hotfix never re-dispatches after
-  decision round-trips; a blocked or failed attempt reverts and escalates
+  a failed or blocked attempt (it reverts and escalates to `/bugfix`, it
-  to `/bugfix`, it does not retry).
+  does not retry). Sole exception: a class-tagged BLOCKED answered by the
+  user (STEP 3), re-dispatched once with the closed choice.
 - Design gate only if CSS/style signals detected. See STEP 1.5.
 - **Revert-not-loop preserved**: smoke FAIL or security BLOCK →
   file-scoped revert from `$PRE` (STEP 4's protocol — never `git

skills/init-project/SKILL.md

@@ -58,8 +58,8 @@ In both cases: MANDATORY STOP until user answers remaining questions. Produce PR
 
 **Then run `$HOME/.claude/lib/contract-interview.md`** seeded from the BRIEF:
 REQUEST verbatim = the user's project description; ACCEPTANCE CRITERIA = the
-V1 FEATURES (each testable); FILE SCOPE = the planned tree. No new questions
+V1 FEATURES (each testable); FILE SCOPE = the planned tree. Pass A is covered
-(the interview already asked). It writes
+by the interview; pass B runs at STEP 3 against the DESIGN. It writes
 `.claude/tasks/contracts/<date>-<slug>-<HHMM>.md`; the DESIGN approved at STEP
 4 ENRICHES it, and STEP 9's verifier judges the MVP against the enriched
 contract.
@@ -70,6 +70,9 @@ Load `$HOME/.claude/agents/analyzer.md`. Analyze BRIEF: existing code, stack con
 ## STEP 3 — DESIGN
 Invoke `superpowers:brainstorming` with BRIEF + ANALYSIS REPORT.
 Produce DESIGN: stack+versions, full folder tree, module responsibilities, data flow, interfaces (signatures only), config+tooling, test strategy, resolved decisions, prereqs list.
+Then run pass B of `$HOME/.claude/lib/contract-interview.md` against the DESIGN
+(minus what the BRIEF and the brainstorm settled): one batch before STEP 4;
+answers append to the contract `[gated]`.
 
 ## STEP 4 — VALIDATION GATE #1 ★ MANDATORY STOP
 Present:

skills/ship-feature/SKILL.md

@@ -116,6 +116,10 @@ Refine request into validated design via Socratic questioning. Don't proceed unt
 Invoke `superpowers:writing-plans` with the validated design AND the 0d digest: every task
 must be consistent with the in-force constraints; where a task implements or affects one,
 note the ID inline. Break design into tasks (2-5 min each). Each task: exact file paths, full code, verification steps.
+Then run pass B of `$HOME/.claude/lib/contract-interview.md` against the plan:
+every VISIBLE / PUBLIC NAME / SCOPE choice the plan settles that neither the
+request nor the STEP 1 brainstorm settled (check the contract's CLARIFICATIONS
+first) → one batch before STEP 2b; answers append to the contract `[gated]`.
 
 ## STEP 2b — CHALLENGE THE PLAN (adversarial, before the gate)
 Before the human sees the plan, harden it. Run `$HOME/.claude/lib/challenge-plan.md`:

templates/settings/SETTINGS.md

@@ -79,8 +79,11 @@ one repo feeds the classifier false facts in all the others.
 
 ### `ask` is not a prompt under auto mode
 
-Verified in-session (LRN-146): with `defaultMode: auto`, Bash rules in
+Verified in-session (LRN-146, re-verified on 2.1.273 on 2026-09-16 with a
-`permissions.ask` were auto-approved and raised no prompt. `deny` is the only
+`node -e` probe matching an `ask` rule): with `defaultMode: auto`, Bash rules
+in `permissions.ask` were auto-approved and raised no prompt. The auto-mode
+docs claim the opposite for "content-scoped" rules such as `Bash(git push *)`;
+the observed behavior wins until a probe shows a prompt. `deny` is the only
 tier the classifier cannot lift.
 
 So for a destructive command you want gated but still reachable, `ask` is the
@@ -94,11 +97,21 @@ it. Keep `deny` for what must never run at all.
 | Never runs, no exception, matchable by a command pattern | `permissions.deny` |
 | Never runs, and a pattern cannot express it (a read then a send, a prod target) | `autoMode.hard_deny` |
 | Runs when the user asks for it, blocked otherwise | `autoMode.soft_deny` |
+| Runs freely when a condition holds that only the classifier can judge (a local dev container, a package declared in the lockfile) | `autoMode.allow` |
 | Runs freely | `permissions.allow`, or nothing |
 
 `permissions.ask` is not on this list on purpose. Under `defaultMode: auto` it
 gates nothing.
 
+`autoMode.allow` is the exception tier: inside the classifier an `allow` entry
+overrides a matching `soft_deny`, built-in or yours, so word it as narrowly as
+the condition allows. It is also the only tier that can open an interpreter:
+under auto mode Claude Code suspends the static allow rules that grant
+arbitrary code execution (`Bash(*)`, wildcarded interpreters such as
+`Bash(node *)`), so those commands reach the classifier whatever
+`permissions.allow` says. `awk` and `echo` pass through a static rule; `node`
+cannot.
+
 ### Scope of intent
 
 A `soft_deny` clears on the user's instruction, and this config scopes that to