Merge origin/main into cl-7023-overhaul-implement-skill

Author: TheGreatAxios

CHANGELOG.md

@@ -11,6 +11,13 @@ matching `## [X.Y.Z]` section (plus install instructions). Do not maintain
 parallel copies under `docs/` or `scripts/notes/`. At cut time: rename
 `## [Unreleased]` to `## [X.Y.Z] - YYYY-MM-DD`, then run the release script.
 
+## [Unreleased]
+
+### Fixed
+
+- One-shot confirmation flashes (copy, mouse toggle, attach results, reasoning effort, stall recovery) now clear themselves after a short TTL. Rate-limit waits no longer park on the bottom notice row; the durable error stays in the transcript. Live stall notice and landing hold still omit a TTL so they stay until replaced.
+- A TTL flash no longer paints chrome after the TUI renderer is destroyed, which crashed parallel TUI tests with `TextBuffer is destroyed`.
+
 ## [0.3.1] - 2026-08-24
 
 ### Fixed

docs/TUI.md

@@ -161,10 +161,10 @@ Color is a small, deliberate palette, not decoration
 (`src/tui/theme.ts`). Dimmed text is a dimmed cream, never a neutral
 gray, so every emphasis level keeps the same warm hue. Orange
 (`UI.action`) is spent once per screen: it marks the session identity,
-a leading `/command` or `@mention` in the prompt, and whatever is currently
-awaiting a human decision (an approval subject, an active choice) — nothing
-else competes with it. Standing caution (`mcp !`, `plugin !`, the context
-meter's 61–80 band) uses `UI.warning`; the meter turns `UI.error` at 81–100.
+a leading `/command` or `@mention` in the prompt, and the dithered subject
+of a decision surface (permission or operator ask) — nothing else competes
+with it. Standing caution (`mcp !`, `plugin !`, the context
+meter's 61–80 band, consequence impact under a list) uses `UI.warning`; the meter turns `UI.error` at 81–100.
 Ongoing, non-decision status uses the bronze/sand/ember chrome ramp and green
 (`UI.done`) for completion.
 The one deliberate exception is diff removals, where orange is content (the
@@ -292,9 +292,12 @@ approval.
 The decision surfaces (permission approval, operator question) are the one
 framed content in the shell, and they are shaped rather than merely listed
 (`src/tui/overlay-body.ts`): a dithered header (`░▒▓`) carries the
-subject in the action color, a blank row separates it from context, and each
-choice gets one row with the active choice marked by a solid block (`█`)
-rather than a background fill.
+subject in the action color — the only Breakthrough Orange on the card.
+The overlay host border and title use calm dim chrome (`UI.textDim`);
+consequence impact in the description zone paints `UI.warning` (sand), not
+orange. A blank row separates the subject from context, and each choice gets
+one row with the active choice marked by a solid block (`█`) rather than a
+background fill (cream text, not orange).
 
 ## How selectors should work
 
@@ -546,7 +549,9 @@ running its own selection. Two chords cover remaining copy needs:
   (`CliRenderEvents.SELECTION` → `copyFinishedSelection` in
   `selection-copy.ts`). On mouse-up, non-empty selected text is written
   through the system clipboard port and the highlight clears with a status
-  flash. Empty clicks do not copy.
+  flash. Empty clicks do not copy. Confirmation flashes pass
+  `ttlMs: RUNTIME_FLASH_MS` so they clear themselves; omit TTL only for
+  live conditions that stay true until replaced (stall notice, landing hold).
 - **Alt+M** toggles DEC mouse reporting off and back on
   (`toggleMouseCapture`, `shell.ts`). Off, the terminal's own drag-select
   and copy work exactly as in any other terminal program; the status flash

plugins/corbits-skills/skills/create-issue/SKILL.md

@@ -6,9 +6,9 @@ description: Conduct an iterative multiple-choice interview using ask_operator.
 
 # Interview
 
-Use this skill to gather user input on a topic by asking multiple-choice questions in batches via `ask_operator`. Return the questions and answers in the conversation. The caller decides what to do with them.
+Gather structured user input on a topic via multiple-choice `ask_operator` questions. Emit the Q&A inline; the caller decides what to do with it.
 
-This is a utility, not a planner. It does not decide what to build, write any files, or invoke other skills.
+This is a utility, not a planner. It does not decide what to build, write any files, spawn agents, or invoke other skills.
 
 ## Argument
 
@@ -23,15 +23,17 @@ If no topic is given, ask for one with `ask_operator` before proceeding.
 
 ### Identify dimensions to probe
 
-Enumerate the open questions worth asking, drawn from the topic and context. Skip dimensions the context already settles. Add domain-specific ones where relevant. There is no fixed dimension list — the topic determines it.
+Enumerate the open questions worth asking from the topic and context. Skip dimensions the context already settles. Add domain-specific ones where relevant. There is no fixed dimension list — the topic determines it.
 
 Probe objective and priorities before details. They shape every later question, so anchoring them early prevents reshuffling halfway through.
 
-### Ask in batches
+### Ask with ask_operator
 
-Each question is one `ask_operator` call: `question` (string) plus `options` (array of strings). Batch a round by firing 2–4 independent `ask_operator` calls together (parallel tool calls). Refer to the tool's own documentation for parameter limits.
+Each question is one `ask_operator` call: `question` (string) plus `options` (array of strings). Fire independent questions together as parallel tool calls in the same turn.
 
-`ask_operator` is single-select per call. The operator can also type a custom answer. There is no multi-select flag — if a dimension genuinely permits several answers, encode the realistic combinations as options, or follow up with a second question once the first answer lands.
+`ask_operator` is single-select per call. The operator can also type a custom answer. There is no multi-select flag — if a dimension genuinely permits several answers, encode the realistic combinations as options, or follow up once the first answer lands.
+
+**No false caps.** `ask_operator` has no skill-invented ceiling on option count, parallel questions per round, or total rounds. Batch every independent dimension you can author now. Drop to one question only when the next question's text or options cannot be written without this answer. Stop when marginal value is low (see below) — never because a made-up quota was hit. If the caller passed an explicit cap, honour it.
 
 **Quality bar for options:**
 
@@ -42,11 +44,7 @@ Each question is one `ask_operator` call: `question` (string) plus `options` (ar
 - Combination options only when the dimension genuinely permits more than one answer
 - If you have a recommendation, put it first and label it
 
-**Batching:**
-
-- Default 2–4 `ask_operator` calls per round, bundling dimensions that do not depend on each other
-- Drop to 1 question only when the next question's text or options cannot be authored without this answer
-- Referencing a prior answer inside a later question's text is fine
+Referencing a prior answer inside a later question's text is fine.
 
 ### Decide when to stop
 
@@ -57,7 +55,7 @@ Stop when:
 - The user has signalled fatigue (declines to choose, short non-substantive custom answers, asks to wrap up)
 - The topic has shifted into territory outside this interview's scope
 
-There is no fixed round cap. Stop when the marginal value of another round is low. If the caller passed an explicit cap, honour it.
+There is no fixed round cap. Stop when the marginal value of another round is low.
 
 ### Handle trouble
 
@@ -92,7 +90,7 @@ After emitting the findings, stop. Do not load other skills, invoke other agents
 
 **Invocation:** `use_skill(name="interview")` with the topic in the conversation, or `/interview notification system; backend is Node/Postgres, internal users only, must integrate with existing auth`
 
-**Round 1** (3 parallel `ask_operator` calls, bundled because none depends on the others):
+**Round 1** (three parallel `ask_operator` calls — independent dimensions, so ask together):
 
 ```
 ask_operator({
@@ -138,7 +136,8 @@ ask_operator({
 ## Anti-patterns
 
 - **Interviewing yourself.** Filling in answers because they "seem obvious" — stop and ask, or note as assumption.
-- **One question per round, ten rounds deep.** Batch related questions as parallel `ask_operator` calls.
+- **Serializing independent questions.** If dimensions do not depend on each other, ask them in parallel.
+- **Inventing quotas.** Do not stop or thin options because of a made-up question or option count.
 - **Asking about everything.** Prune dimensions that do not apply.
 - **Treating a custom answer as failure.** Custom answers are signal.
 - **Forgetting context.** Read it. Do not re-ask things the context already settled.

plugins/corbits-skills/skills/interview/SKILL.md

@@ -8,15 +8,20 @@ argument-hint: "[paths | PR | diff | hygiene | architecture]"
 
 You are Skywalker. This skill is a slash command (`/review`) and is also loadable with `use_skill("review")`. Do not implement fixes. Do not write product patches to "just quickly" address findings. Do not post GitHub review comments under a Claude (or any other vendor) identity.
 
-Spawn a director. Pass the operator's scope — paths, PR, branch, or diff — as the brief. Report that director's Summary / Findings / Blockers / Paths.
+Classify the lens, spawn the matching director(s), wait for reports, synthesize. Findings only — never land fixes in this recipe.
 
 ## Routing
 
-- **Default** (correctness, completeness, brief adherence, defects with evidence): `task(agent="critique")`
-- **Hygiene-only** (nits, naming, lint, pedantry with receipts): `task(agent="neckbeard")`
-- **Architecture-only** (structure, boundaries, approach): `task(agent="greybeard")`
+- **Default** (correctness, completeness, brief adherence, defects with evidence): `critique`
+- **Hygiene-only** (nits, naming, lint, pedantry with receipts): `neckbeard`
+- **Architecture-only** (structure, boundaries, approach): `greybeard`
 
-If the operator did not say hygiene-only or architecture-only, spawn critique. Do not spawn all three unless they asked for a wider review.
+If the operator did not say hygiene-only or architecture-only, spawn critique alone. Do not spawn all three unless they asked for a wider review.
+
+## Fleet
+
+- **One lens:** `task(agent="<director>")` — blocking single spawn; prefer this when only one worker is needed.
+- **Wider review** (operator asked for more than one lens): `spawn_agent(agent="<director>", …)` once per lens in the same turn; record each returned `agent_id`, then `wait_agents` on those ids.
 
 Prefer a typed brief: `intent="review"`, `success_criteria`, `do_not`, `report_focus`, and `agent`.
 
@@ -27,9 +32,9 @@ Include whatever the operator gave you, plus enough for a scoped review:
 - Paths, PR number/URL, or branch to review
 - Base for comparison when known (`git diff <base>...HEAD`); if the base is unclear, ask rather than guessing `main`
 - That only the operator's scope is in scope — pre-existing issues outside the diff are out of lane
-- Do not implement fixes; findings only, with evidence
+- Do not implement fixes; findings only, with evidence (`path:line`)
 - Signal over noise: skip hypotheticals and style nits that do not affect correctness, readability, or maintainability (neckbeard is the exception when hygiene was requested)
 
 ## After the report
 
-Synthesize. Do not land fixes. If the operator then wants repairs, that is a later `/implement` or `use_skill("dispatch")` — not this skill.
+Synthesize Summary / Findings / Blockers / Paths for the operator. Do not land fixes. If the operator then wants repairs, that is a later `/implement` or `use_skill("dispatch")` — not this skill.