cclaw-cli 0.51.21 → 0.51.22

package/dist/content/stages/scope.js

@@ -45,13 +45,13 @@ export const SCOPE = {
     },
     executionModel: {
         checklist: [
-            "**Compact CEO pass first** — read brainstorm, name the job-to-be-done, challenge whether this is the right product slice, and propose the highest-leverage scope in one pass. For simple apps, keep this to a tight scope contract instead of a full strategy workshop.",
+            "**Scope contract first** — read brainstorm, name the job-to-be-done, draft the explicit in-scope/out-of-scope/deferred contract, select one mode, and write the rationale. This is the default path; use dream/10-star/temporal/deep strategy sections only when risk, novelty, or user ambition justifies them.",
             "**Premise and leverage check** — answer in the artifact: *Right problem? Direct path? What if nothing? Where can we leverage existing code? What is the reversibility cost?* Take a position; do not hedge.",
-            "**Draft the 10-star vs current-slice boundary** — show what would make the product meaningfully better, then explicitly choose what ships now, what is deferred, and what is excluded without using vague `later/for now` placeholders.",
+            "**Conditional 10-star boundary** — for deep/high-risk/product-strategy work, show what would make the product meaningfully better, then explicitly choose what ships now, what is deferred, and what is excluded without vague `later/for now` placeholders. Skip this for straightforward repair work and record `not needed: compact scope`.",
             "**Pick one of four gstack modes with the user** — SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, or SCOPE REDUCTION. Recommend one, state why and what signal would change it, then STOP for the user's mode/scope approval before writing the final artifact.",
-            "**Run mode-specific analysis** — match the analysis to the chosen mode: SCOPE EXPANSION enumerates 10x opportunities + delight features; SELECTIVE EXPANSION lists baseline + cherry-picked additions with leverage rationale; HOLD SCOPE proves rigor on the current slice; SCOPE REDUCTION names the smallest useful wedge and what is cut, with follow-up split.",
+            "**Run mode-specific analysis only to needed depth** — ordinary path is a selected-mode row plus rationale tied to the scope contract. For deep/high-risk work, expand the analysis to match the chosen mode: SCOPE EXPANSION enumerates 10x opportunities + delight features; SELECTIVE EXPANSION lists baseline + cherry-picked additions; HOLD SCOPE proves rigor on the current slice; SCOPE REDUCTION names the smallest useful wedge.",
             "**Compare implementation alternatives** — include minimum viable, product-grade, and ideal architecture options with effort (S/M/L/XL), risk (Low/Med/High), pros, cons, and reuses. Recommend one and tie it to mode.",
-            "**Run outside voice before final approval** — for simple/low-risk scope, record one concise adversarial self-check row; for complex/high-risk/configured scope, iterate until threshold. Record the loop summary in `## Spec Review Loop`, but do not treat it as user approval.",
+            "**Run outside voice before final approval** — for simple/low-risk scope, record one concise adversarial self-check row; for complex/high-risk/configured scope, iterate until threshold. Record the loop summary in `## Scope Outside Voice Loop`, but do not treat it as user approval.",
             "**Ask only one decision-changing question** — if the user rejects the contract but is unsure, offer 3-4 concrete scope moves instead of open-ended interrogation.",
             "**Write the scope contract after approval** — include in-scope/out-of-scope, discretion areas, deferred items, locked decisions, error/rescue notes, completion dashboard, scope summary (with canonical mode token + next-stage handoff), and explicit approval evidence."
         ],
@@ -61,18 +61,18 @@ export const SCOPE = {
             "For simple web-app flows, default to HOLD SCOPE or SELECTIVE EXPANSION, show the exact in/out/deferred contract as a proposal, and STOP for one explicit approval before writing the final scope artifact or completing the stage.",
             "Challenge premise first, take a firm position, and name one concrete condition that would change it.",
             "Push back on weak framing: vague scope needs a specific user/problem, platform vision needs a narrow wedge, social proof needs behavioral evidence.",
-            "Resolve one structural scope issue at a time; otherwise state the assumption and move on.",
+            "Resolve one structural scope issue at a time. Only non-critical preference/default assumptions may continue; STOP on uncertainty about scope boundary, architecture commitment, security, data loss, public API, migration, auth/pricing, or required user approval.",
             "If the user says no but cannot name the change, offer concrete moves: keep scope, add one obvious adjacent capability, reduce to wedge, or re-open stack/product direction.",
-            `Before final approval, record outside-voice findings and a \`## Spec Review Loop\` table using ${reviewLoopPolicySummary("scope")}`,
+            `Before final approval, record outside-voice findings and a \`## Scope Outside Voice Loop\` table using ${reviewLoopPolicySummary("scope")}`,
             "**STOP.** Wait for explicit user approval of the scope mode and scope contract before writing final approval language or advancing.",
             "**STOP BEFORE ADVANCE.** Mandatory delegation `planner` must be completed or explicitly waived. If no isolated planner is available, use `--waive-delegation=planner --waiver-reason=\"role-switch scope self-review completed\"`. Then close with `node .cclaw/hooks/stage-complete.mjs scope --passed=scope_mode_selected,scope_contract_written,scope_user_approved --evidence-json '{\"scope_mode_selected\":\"<user-approved mode + rationale>\",\"scope_contract_written\":\"<artifact path + sections>\",\"scope_user_approved\":\"<explicit user approval quote or summary>\"}'`. `scope_user_approved` must cite the user's approval; review-loop evidence alone is not approval."
         ],
         process: [
             "Run configured pre-scope audit only when enabled.",
-            "Run the gstack-style CEO scope pass scaled to risk: job-to-be-done, premise challenge, 10-star upside, smallest useful wedge, and what would change the recommendation.",
+            "Run the scope pass scaled to risk: default to job-to-be-done plus explicit scope contract; add premise challenge, 10-star upside, smallest useful wedge, and change conditions only for deep/high-risk scope.",
             "Compare minimum viable, product-grade, and ideal architecture scope alternatives with explicit reuse/effort/risk.",
             "Recommend a scope mode with explicit rationale, then ask for user opt-in before treating it as selected.",
-            "Run outside voice / adversarial self-check before final approval and record a valid `## Spec Review Loop` table.",
+            "Run outside voice / adversarial self-check before final approval and record a valid `## Scope Outside Voice Loop` table.",
             "Write explicit scope contract, discretion areas, deferred items, error/rescue registry, and D-XX locked decisions.",
             "Produce scope summary, completion dashboard, and exact next-stage handoff before asking final approval."
         ],
@@ -90,7 +90,7 @@ export const SCOPE = {
             "Locked Decisions section lists stable LD#hash anchors for non-negotiable boundaries.",
             "Premise challenge findings documented.",
             "Outside Voice findings and dispositions are recorded (accept/reject/defer with rationale) before final approval.",
-            `Spec review loop summary includes a table with columns Iteration, Quality Score, Findings, plus Stop reason, Target score, and Max iterations. This is outside-voice evidence only; it does not satisfy user approval. ${reviewLoopPolicySummary("scope")}`,
+            `Scope outside-voice loop summary includes a table with columns Iteration, Quality Score, Findings, plus Stop reason, Target score, and Max iterations. This is outside-voice evidence only; it does not satisfy user approval. ${reviewLoopPolicySummary("scope")}`,
             reviewLoopSecondOpinionSummary("scope"),
             "Deferred items list with one-line rationale for each.",
             "When an upside deferred idea is parked, a seed file is created under `.cclaw/seeds/` and referenced in the artifact.",
@@ -146,17 +146,17 @@ export const SCOPE = {
             { section: "Locked Decisions (LD#hash)", required: false, validationRule: "List of stable locked decisions with unique `LD#<sha8>` anchors. Each anchor is derived from the normalized Decision cell and is referenced downstream for cross-stage traceability." },
             { section: "Implementation Alternatives", required: false, validationRule: "2-3 options with Name, Summary, Effort, Risk, Pros, Cons, and Reuses. Must include minimal viable and ideal architecture options." },
             { section: "Scope Mode", required: true, validationRule: "Must state selected mode and rationale with default heuristic justification." },
-            { section: "Mode-Specific Analysis", required: false, validationRule: "Deep/complex scope only: document the analysis matching the selected mode. Default path may record a concise mode rationale instead." },
+            { section: "Mode-Specific Analysis", required: false, validationRule: "Default path: one selected-mode row with rationale. Deep/complex scope only: document the expanded analysis matching the selected mode." },
             { section: "In Scope / Out of Scope", required: true, validationRule: "Two separate explicit lists. Canonical form is one `## In Scope / Out of Scope` section with `### In Scope` and `### Out of Scope`; legacy split `## In Scope` and `## Out of Scope` headings are accepted. Out-of-scope must not be empty." },
             { section: "Discretion Areas", required: false, validationRule: "Explicit list of implementer decision zones, or 'None' if scope is fully locked." },
             { section: "Deferred Items", required: false, validationRule: "Each item has one-line rationale. If empty, state 'None' explicitly." },
             { section: "Error & Rescue Registry", required: false, validationRule: "Each scoped capability has: failure mode, detection method, fallback decision." },
             { section: "Outside Voice Findings", required: false, validationRule: "Must list external/adversarial findings and disposition (accept/reject/defer) with rationale." },
-            { section: "Spec Review Loop", required: false, validationRule: `Must record iterations, quality score per iteration, stop reason, and unresolved concerns. Enforce ${reviewLoopPolicySummary("scope")}` },
+            { section: "Scope Outside Voice Loop", required: false, validationRule: `Must record iterations, quality score per iteration, stop reason, and unresolved concerns. Enforce ${reviewLoopPolicySummary("scope")}` },
             { section: "Completion Dashboard", required: true, validationRule: "Lists per-review-section status, count of critical/open gaps, resolved decisions, and unresolved decisions (or 'None')." },
             { section: "Scope Summary", required: true, validationRule: "Compact recap of the locked scope. Must name the selected mode using one of the canonical tokens (`SCOPE EXPANSION`, `SELECTIVE EXPANSION`, `HOLD SCOPE`, `SCOPE REDUCTION`) and record the track-aware next-stage handoff (`design` for standard, `spec` for medium); the linter checks structure, not English wording." },
-            { section: "Dream State Mapping", required: false, validationRule: "If present (complex projects): CURRENT STATE, THIS PLAN, 12-MONTH IDEAL, and alignment verdict." },
-            { section: "Temporal Interrogation", required: false, validationRule: "If present (complex projects): timeline simulation table with decision pressures and lock-now vs defer verdicts." }
+            { section: "Dream State Mapping", required: false, validationRule: "Deep/optional only: CURRENT STATE, THIS PLAN, 12-MONTH IDEAL, and alignment verdict. Omit for compact scope." },
+            { section: "Temporal Interrogation", required: false, validationRule: "Deep/optional only: timeline simulation table with decision pressures and lock-now vs defer verdicts. Omit for compact scope." }
         ]
     },
     reviewLens: {

package/dist/content/stages/spec.js

@@ -36,10 +36,10 @@ export const SPEC = {
     },
     executionModel: {
         checklist: [
-            "Read upstream — load design artifact and scope contract. Cross-reference architecture decisions.",
+            "Read upstream — standard track loads design + scope; medium loads brainstorm/spec handoff; quick loads `00-idea.md` plus any reproduction context. Cross-reference only artifacts that exist on the active track.",
             "Define measurable acceptance criteria — each criterion must be observable and falsifiable. No vague adjectives.",
             "Capture edge cases — for each criterion, define at least one boundary condition and one error condition.",
-            "Document constraints and assumptions — regulatory, system, integration, and performance boundaries. Surface implicit assumptions explicitly.",
+            "Document constraints and assumptions — regulatory, system, integration, and performance boundaries. Only non-critical preference/default assumptions may continue; STOP on uncertainty about scope, architecture, security, data loss, public API, migration, auth/pricing, or required user approval.",
             "Surface assumptions before finalization — list each assumption with source/confidence, validation path, and whether it is accepted, rejected, or still open.",
             "Build the Acceptance Mapping contract — for each AC, map upstream design decision, observable evidence, verification method, and likely test level. If any column is unclear, rewrite the criterion.",
             "Present acceptance criteria to the user in 3-5-item batches, pausing for explicit ACK between batches (see Interaction Protocol).",
@@ -53,7 +53,7 @@ export const SPEC = {
             "**Chunk acceptance criteria for review.** When presenting the spec to the user for sign-off, deliver acceptance criteria in batches of 3-5 and **pause for explicit ACK** (via Decision Protocol) before sending the next batch. Do not dump the full criteria wall in one message — small batches surface objections earlier and keep the sign-off meaningful. Full spec writeup still lands in `04-spec.md`, but the conversation itself must be digestible.",
             "Require user confirmation on the written spec. **STOP.** Do NOT proceed to plan until user approves.",
             "For each criterion, ask: what exact evidence proves this passed? If the evidence or verification command/manual step is vague, rewrite.",
-            "When encountering ambiguity, classify it before acting: (A) ask user for missing info, (B) enumerate interpretations and pick one with justification, (C) propose hypothesis with validation path. Do NOT silently resolve ambiguity."
+            "When encountering ambiguity, classify it before acting: (A) ask user for missing info, (B) enumerate non-critical interpretations and pick one with justification, (C) propose hypothesis with validation path. Do NOT silently resolve ambiguity. STOP on scope, architecture, security, data loss, public API, migration, auth/pricing, or user-approval uncertainty."
         ],
         process: [
             "Define measurable acceptance criteria.",
@@ -75,7 +75,8 @@ export const SPEC = {
             "Each acceptance criterion maps to upstream design decision, observable evidence, verification method, and likely test level.",
             "Edge cases documented per criterion.",
             "Assumptions Before Finalization section records source/confidence, validation path, and accepted/rejected/open disposition.",
-            "Approval marker captured in artifact."
+            "Approval marker captured in artifact.",
+            "For quick bug-fix specs, reproduction contract records symptom, repro steps, expected RED test, and acceptance criterion."
         ],
         inputs: ["design artifact", "business constraints", "quality requirements"],
         requiredContext: [
@@ -112,7 +113,8 @@ export const SPEC = {
         },
         artifactValidation: [
             { section: "Upstream Handoff", required: false, validationRule: "Summarizes scope/design decisions, constraints, open questions, and explicit drift before acceptance criteria." },
-            { section: "Acceptance Criteria", required: true, validationRule: "Each criterion is observable, measurable, and falsifiable. Table must include a Requirement Ref column linking to R# IDs in 02-scope-<slug>.md (legacy 02-scope.md is accepted during migration) and a Design Decision Ref column tracing back to design artifact. AC IDs (AC-1, AC-2…) are stable across revisions — dropped ACs stay with Priority `DROPPED`." },
+            { section: "Acceptance Criteria", required: true, validationRule: "Each criterion is observable, measurable, and falsifiable. Standard track should include Requirement Ref and Design Decision Ref columns; quick track may instead link each AC to the reproduction contract or bug slice. AC IDs (AC-1, AC-2…) are stable across revisions — dropped ACs stay with Priority `DROPPED`." },
+            { section: "Quick Reproduction Contract", required: false, validationRule: "Quick bug-fix specs own the reproduction contract: symptom, repro steps, expected RED test behavior, and acceptance criterion." },
             { section: "Edge Cases", required: true, validationRule: "At least one boundary and one error condition per criterion." },
             { section: "Constraints and Assumptions", required: false, validationRule: "All implicit assumptions surfaced. Constraints have sources." },
             { section: "Assumptions Before Finalization", required: true, validationRule: "Each assumption has source/confidence, validation path, and accepted/rejected/open disposition before the Approval section is finalized." },

package/dist/content/stages/tdd.js

@@ -50,7 +50,7 @@ export const TDD = {
             "Run verification-before-completion discipline for the slice — capture a fresh test command, commit SHA, and explicit PASS/FAIL status before completion claims.",
             "REFACTOR: continue the `test-author` evidence cycle (or a dedicated refactor mode when available) to improve code quality without behavior changes. Set `CCLAW_ACTIVE_AGENT=tdd-refactor` when the harness supports phase labels.",
             "Record evidence — capture test discovery, system-wide impact check, RED failure, GREEN output, and REFACTOR notes in the TDD artifact. When logging a `green` row, attach the closed acceptance-criterion IDs in `acIds` so Ralph Loop status counts them.",
-            "Annotate traceability — link to plan task ID and spec criterion.",
+            "Annotate traceability — link to the active track's source: plan task ID + spec criterion on standard/medium, or spec acceptance item / bug reproduction slice on quick.",
             "Per-Slice Review (conditional) — if `.cclaw/config.yaml::sliceReview.enabled` is true and the slice meets any trigger (touchCount >= filesChangedThreshold, touchPaths match touchTriggers, or highRisk=true), append a `## Per-Slice Review` entry for this slice before moving on (see the dedicated section below).",
             "Repeat for each slice — return to step 1 for the next plan slice."
         ],
@@ -286,7 +286,7 @@ function tddStageVariantForTrack(track) {
                 if (row.section === "Traceability") {
                     return {
                         ...row,
-                        validationRule: "Acceptance criterion IDs are linked to RED/GREEN evidence."
+                        validationRule: "Spec acceptance item IDs and, for bug fixes, reproduction slice IDs are linked to RED/GREEN evidence. No plan artifact is required on quick."
                     };
                 }
                 return {

package/dist/content/start-command.d.ts

@@ -1,8 +1,9 @@
 /**
  * Command contract for /cc — the unified entry point.
- * No args → behaves like /cc-next (resume or start the flow at its first stage).
- * With prompt → classifies the idea, selects a track, and starts the first
- * stage of that track (brainstorm for medium/standard, spec for quick).
+ * No args → reads existing flow state and behaves like /cc-next only when a
+ * tracked flow already exists; missing state/fresh placeholder state blocks with
+ * init/start guidance. With prompt → classifies the idea, selects a track, and
+ * starts the first stage of that track (brainstorm for medium/standard, spec for quick).
  */
 export declare function startCommandContract(): string;
 /**

package/dist/content/start-command.js

@@ -7,9 +7,10 @@ function flowStatePath() {
 }
 /**
  * Command contract for /cc — the unified entry point.
- * No args → behaves like /cc-next (resume or start the flow at its first stage).
- * With prompt → classifies the idea, selects a track, and starts the first
- * stage of that track (brainstorm for medium/standard, spec for quick).
+ * No args → reads existing flow state and behaves like /cc-next only when a
+ * tracked flow already exists; missing state/fresh placeholder state blocks with
+ * init/start guidance. With prompt → classifies the idea, selects a track, and
+ * starts the first stage of that track (brainstorm for medium/standard, spec for quick).
  */
 export function startCommandContract() {
     const flowPath = flowStatePath();
@@ -19,7 +20,7 @@ export function startCommandContract() {
 
 **The unified entry point for the cclaw flow.**
 
-- \`/cc\` (no arguments) → behaves exactly like \`/cc-next\`: reads flow state and resumes the current stage, or starts brainstorm if the flow is fresh.
+- \`/cc\` (no arguments) → reads existing flow state and resumes/progresses it through \`/cc-next\`. If flow state is missing or still a fresh init placeholder, stop and guide the user to run \`/cc <prompt>\` or \`cclaw init\`; do not silently create a brainstorm run.
 - \`/cc <prompt>\` (with an idea/description) → saves the prompt as idea context and starts the first stage of the resolved track.
 
 This is the **recommended way to start** working with cclaw. Use \`/cc-next\` for subsequent stage progression.
@@ -41,8 +42,8 @@ ${conversationLanguagePolicyMarkdown()}
    |---|---|---|
    | **non-software** | legal text / docs / marketing copy / meeting notes / therapy-style conversation | Respond directly, do NOT open a stage, do NOT mutate flow state. |
    | **pure-question** | "how does X work?", "explain Y", "what are the trade-offs of Z?" | Answer directly, do NOT open a stage. |
-   | **trivial** | typo, one-liner, rename, config tweak, copy change, version bump with zero behavior change | Fast-path: skip \`brainstorm\` and \`scope\`, seed \`00-idea.md\`, move straight to \`design\` or \`spec\` depending on whether an interface change is involved. |
-   | **software — bug fix with repro** | regression / hotfix / named symptom + repro steps | Fast-path: set track to \`quick\`, seed \`04-spec.md\` with the reproduction, enter \`tdd\` with a RED reproduction test first. |
+   | **trivial** | typo, one-liner, rename, config tweak, copy change, version bump with zero behavior change | Fast-path: set track to \`quick\`, seed \`00-idea.md\`, and enter \`spec\`. Runtime quick never starts at design. |
+   | **software — bug fix with repro** | regression / hotfix / named symptom + repro steps | Fast-path: set track to \`quick\`, enter \`spec\`, and capture a reproduction contract first. TDD later writes the RED reproduction test from that contract. |
    | **software — medium** | additive feature following existing architecture | medium track (\`brainstorm → spec → plan → tdd → review → ship\`). |
    | **software — standard** | feature, refactor, migration, integration, architecture change | Full 8-stage flow starting at \`brainstorm\`. |
 
@@ -92,7 +93,7 @@ ${conversationLanguagePolicyMarkdown()}
 12. Load the **first-stage skill for the chosen track** and its command file:
     - quick → \`.cclaw/skills/specification-authoring/SKILL.md\`
     - medium/standard → \`.cclaw/skills/brainstorming/SKILL.md\`
-    - trivial fast-path → spec skill per Phase 0 decision.
+    - trivial fast-path → quick track spec skill per Phase 0 decision.
 13. Execute that stage with the prompt + Phase 1/Phase 2 + seed context as initial input.
 
 ### Reclassification on discovery
@@ -107,8 +108,9 @@ If during any stage the agent discovers evidence that contradicts the initial Ph
 ### Without prompt (\`/cc\`)
 
 1. Read \`${flowPath}\`.
-2. If flow state is missing → run \`cclaw init\` guidance and stop.
-3. Behave exactly like \`/cc-next\`: check current stage gates, resume if incomplete, advance if complete.
+2. If flow state is missing → guide the user to run \`cclaw init\` and stop.
+3. If flow state is only a fresh init placeholder (\`completedStages: []\`, all \`passed\` arrays empty, and no \`00-idea.md\`) → stop and ask for \`/cc <prompt>\` to start a tracked run. Do not create a brainstorm state implicitly.
+4. Otherwise behave exactly like \`/cc-next\`: check current stage gates, resume if incomplete, advance if complete.
 
 ## Headless mode
 
@@ -116,7 +118,7 @@ When called by another skill or subagent in machine mode, emit exactly one
 JSON envelope (no prose) and stop:
 
 \`\`\`json
-{"version":"1","kind":"stage-output","stage":"brainstorm","payload":{"command":"/cc","track":"standard","action":"start_or_resume"},"emittedAt":"<ISO-8601>"}
+{"version":"1","kind":"stage-output","stage":"<currentStage>","payload":{"command":"/cc","track":"<track>","action":"start_or_resume"},"emittedAt":"<ISO-8601>"}
 \`\`\`
 
 Validate envelopes with:
@@ -147,7 +149,7 @@ description: "Unified entry point for the cclaw flow. No args = resume/next. Wit
 
 \`/cc\` is the **starting command** for cclaw. It intelligently routes:
 
-- **No arguments** → acts as \`/cc-next\` (resume current stage or advance to next)
+- **No arguments** → acts as \`/cc-next\` only for an existing tracked flow; missing/fresh placeholder state blocks with start guidance
 - **With a prompt** → classifies the task, picks a track (quick/medium/standard), and starts the **first stage of that track** (not always brainstorm — e.g. the \`quick\` track starts at \`spec\`)
 
 ## HARD-GATE
@@ -159,7 +161,7 @@ ${conversationLanguagePolicyMarkdown()}
 
 ### Path A: \`/cc <prompt>\`
 
-1. **Task classification (Phase 0).** Decide whether the prompt is \`software-standard\`, \`software-trivial\`, \`software-bugfix\`, \`pure-question\`, or \`non-software\`. Non-software and pure-question exit immediately — answer directly, do not open a stage.
+1. **Task classification (Phase 0).** Decide whether the prompt is \`software-standard\`, \`software-trivial\`, \`software-bugfix\`, \`pure-question\`, or \`non-software\`. Non-software and pure-question exit immediately — answer directly, do not open a stage. Bugfixes with a clear repro still start on quick \`spec\`: capture the reproduction contract first, then TDD writes the RED reproduction test from that contract.
 2. **Seed shelf recall (Phase 0.5).** Scan \`${RUNTIME_ROOT}/seeds/SEED-*.md\` and match \`trigger_when\` tokens against the prompt text. Surface up to 3 matching seeds with file/title/action and ask whether to apply or ignore. When applied, add them to \`00-idea.md\` under \`Discovered context\`.
 3. **Origin-document discovery (Phase 1).** Scan for \`docs/prd/**\`, \`docs/rfcs/**\`, \`docs/adr/**\`, \`docs/design/**\`, \`specs/**\`, root-level \`PRD.md\` / \`SPEC.md\` / \`DESIGN.md\` / \`REQUIREMENTS.md\`. Summarize any hits in \`00-idea.md\` under \`Discovered context\`. Surface conflicts with the prompt before routing.
 4. **Stack detection (Phase 2).** Inspect \`package.json\` engines, \`pyproject.toml\`, \`go.mod\`, \`Cargo.toml\`, \`pom.xml\`, \`build.gradle*\`, \`Dockerfile\`, \`docker-compose*.yml\`, and CI configs. Record stack + versions on the \`Stack:\` line. Do not invent stack details.
@@ -191,13 +193,15 @@ If mid-stage evidence contradicts the initial Class/Track decision (the "trivial
 
 ### Path B: \`/cc\` (no arguments)
 
-Delegate entirely to \`/cc-next\` behavior:
+Delegate to \`/cc-next\` behavior only when a tracked flow exists:
 
 1. Read \`${flowPath}\`.
-2. Check gates for \`currentStage\`.
-3. If incomplete → load current stage skill and execute.
-4. If complete → advance to next stage and execute.
-5. If flow is done → report completion.
+2. If missing, guide the user to run \`cclaw init\` and stop.
+3. If it is only a fresh init placeholder (\`completedStages: []\`, no passed gates, and no \`${RUNTIME_ROOT}/artifacts/00-idea.md\`), stop and ask for \`/cc <prompt>\` to start a tracked run. Do not silently create a brainstorm run.
+4. Check gates for \`currentStage\`.
+5. If incomplete → load current stage skill and execute.
+6. If complete → advance to next stage and execute.
+7. If flow is done → report completion.
 
 ## When to use \`/cc\` vs \`/cc-next\`
 

package/dist/content/templates.d.ts

@@ -1,4 +1,4 @@
 export declare const ARTIFACT_TEMPLATES: Record<string, string>;
 export declare const RULEBOOK_MARKDOWN = "# Cclaw Rulebook\n\n## MUST_ALWAYS\n- Follow flow order: brainstorm -> scope -> design -> spec -> plan -> tdd -> review -> ship\n- Require explicit user confirmation after plan before TDD\n- Keep evidence artifacts in `.cclaw/artifacts/`\n- Enforce RED before GREEN in TDD\n- Run two-layer review (spec_compliance and code_quality) before ship\n- Validate all inputs before processing \u2014 never trust external data without sanitization\n- Prefer immutable data patterns and pure functions where the language supports them\n- Follow existing repo conventions, patterns, and directory structure \u2014 match the codebase\n- Verify claims with fresh evidence: \"tests pass\" requires running tests in this message\n- Use conventional commits: `type(scope): description` (feat, fix, refactor, test, docs, chore)\n\n## MUST_NEVER\n- Skip RED phase and jump directly to GREEN in TDD\n- Ship with critical review findings\n- Start implementation during /brainstorm\n- Modify generated cclaw files manually when CLI can regenerate them\n- Commit `.cclaw/` or generated shim files\n- Expose secrets, tokens, API keys, or absolute system paths in agent output\n- Duplicate existing functionality without explicit justification \u2014 search before building\n- Bypass security checks, linting hooks, or type checking to \"move faster\"\n- Claim success (\"Done,\" \"All good,\" \"Tests pass\") without running verification in this message\n- Make changes outside the blast radius of the current task without user consent\n\n## DELEGATION\nWhen a task requires specialist knowledge (security audit, performance profiling, database review),\ndelegate to a specialized agent or skill if the harness supports it. The primary agent should:\n1. Identify the specialist domain\n2. Provide focused context (relevant files, the specific concern)\n3. Evaluate the specialist output before acting on it \u2014 do not blindly apply recommendations\n";
-export declare const CURSOR_WORKFLOW_RULE_MDC = "---\ndescription: cclaw workflow guardrails for Cursor agent sessions\nglobs:\n  - \"**/*\"\nalwaysApply: true\n---\n\n<!-- cclaw-managed-cursor-workflow-rule -->\n\n# Cclaw Workflow Guardrails\n\n## Activation Rule\n\nBefore responding to coding work:\n1. Read `.cclaw/state/flow-state.json`.\n2. Start with `/cc` or continue with `/cc-next`.\n3. If no software-stage flow applies, respond normally.\n\n## Stage Order\n\n`brainstorm -> scope -> design -> spec -> plan -> tdd -> review -> ship`\n\nTrack-specific skips are allowed only when `flow-state.track` + `skippedStages` explicitly say so.\n\n## Task Classification\n\n| Class | Route |\n|---|---|\n| non-trivial software work | `/cc <idea>` |\n| trivial software fix | `/cc <idea>` (quick or medium track) |\n| bugfix with repro | `/cc <idea>` and enforce RED-first in tdd |\n| pure question / non-software | direct answer (no stage flow) |\n\n## Command Surface\n\n- `/cc` = entry and resume.\n- `/cc-next` = only progression path.\n- Knowledge capture and recall use the `learnings` skill when requested.\n\n## Verification Discipline\n\n- No completion claim without fresh command evidence in this turn.\n- Do not mark gates passed from memory.\n- Keep evidence in `.cclaw/artifacts/`; archive via `npx cclaw-cli archive`.\n\n## Delegation And Approvals\n\n- Machine-only checks in design/plan/tdd/review/ship should auto-dispatch when tooling supports it.\n- Ask for user input only at explicit approval gates (scope mode, plan approval, challenge resolution, ship finalization).\n- If harness capabilities are partial, record waiver reasons in delegation logs.\n\n## Routing Source Of Truth\n\n- Primary router: `.cclaw/skills/using-cclaw/SKILL.md`.\n- Stage behavior: current stage skill plus `.cclaw/state/flow-state.json`.\n- Preamble budget: keep role/status announcements brief and avoid repeating\n  them unless the stage or role changes.\n";
+export declare const CURSOR_WORKFLOW_RULE_MDC = "---\ndescription: cclaw workflow guardrails for Cursor agent sessions\nglobs:\n  - \"**/*\"\nalwaysApply: true\n---\n\n<!-- cclaw-managed-cursor-workflow-rule -->\n\n# Cclaw Workflow Guardrails\n\n## Activation Rule\n\nBefore responding to coding work:\n1. Read `.cclaw/state/flow-state.json`.\n2. Start with `/cc` or continue with `/cc-next`.\n3. If no software-stage flow applies, respond normally.\n\n## Stage Order\n\n`brainstorm -> scope -> design -> spec -> plan -> tdd -> review -> ship`\n\nTrack-specific skips are allowed only when `flow-state.track` + `skippedStages` explicitly say so.\n\n## Task Classification\n\n| Class | Route |\n|---|---|\n| non-trivial software work | `/cc <idea>` |\n| trivial software fix | `/cc <idea>` (quick track) |\n| bugfix with repro | `/cc <idea>` and enforce RED-first in tdd |\n| pure question / non-software | direct answer (no stage flow) |\n\n## Command Surface\n\n- `/cc` = entry and resume.\n- `/cc-next` = only progression path.\n- Knowledge capture and recall use the `learnings` skill when requested.\n\n## Verification Discipline\n\n- No completion claim without fresh command evidence in this turn.\n- Do not mark gates passed from memory.\n- Keep evidence in `.cclaw/artifacts/`; archive via `npx cclaw-cli archive`.\n\n## Delegation And Approvals\n\n- Machine-only checks in design/plan/tdd/review/ship should auto-dispatch when tooling supports it.\n- Ask for user input only at explicit approval gates (scope mode, plan approval, challenge resolution, ship finalization).\n- If harness capabilities are partial, record waiver reasons in delegation logs.\n\n## Routing Source Of Truth\n\n- Primary router: `.cclaw/skills/using-cclaw/SKILL.md`.\n- Stage behavior: current stage skill plus `.cclaw/state/flow-state.json`.\n- Preamble budget: keep role/status announcements brief and avoid repeating\n  them unless the stage or role changes.\n";
 export declare function buildRulesJson(): Record<string, unknown>;

package/dist/content/templates.js

@@ -143,6 +143,7 @@ ${SEED_SHELF_SECTION}
 | Reversibility cost? |  |  |
 
 ## Dream State Mapping
+- Deep/optional only; omit for compact scope.
 - CURRENT STATE:
 - THIS PLAN:
 - 12-MONTH IDEAL:
@@ -156,6 +157,7 @@ ${SEED_SHELF_SECTION}
 | C (optional) |  |  |  |  |  |  |
 
 ## Temporal Interrogation
+- Deep/optional only; omit for compact scope.
 | Time slice | Likely decision pressure | Lock now or defer? | Reason |
 |---|---|---|---|
 | HOUR 1 (foundations) |  |  |  |
@@ -170,12 +172,11 @@ ${SEED_SHELF_SECTION}
 - [ ] SCOPE REDUCTION — strip to the smallest useful wedge when risk/blast radius is too high.
 
 ## Mode-Specific Analysis
-- **Selected mode:**
-- **Analysis:**
-  - (SCOPE EXPANSION: 10-star opportunities, delight features)
-  - (SELECTIVE EXPANSION: hold-scope baseline, cherry-picked expansions)
-  - (HOLD SCOPE: approved slice with maximum rigor)
-  - (SCOPE REDUCTION: ruthless cuts, follow-up split)
+| Selected mode | Rationale | Depth |
+|---|---|---|
+|  |  | default / deep |
+
+> Default path: one selected-mode row plus rationale. Deep/high-risk scope may expand below with mode-specific analysis.
 
 ## Requirements (stable IDs)
 | ID | Requirement (observable outcome) | Priority | Source (origin doc / prompt line) |
@@ -224,7 +225,7 @@ ${SEED_SHELF_SECTION}
 |---|---|---|---|---|
 | F-1 | premise_fit |  | accept/reject/defer |  |
 
-## Spec Review Loop
+## Scope Outside Voice Loop
 | Iteration | Quality Score | Findings | Stop decision |
 |---|---|---|---|
 | 1 | 0.00 | 0 | continue/stop |
@@ -288,8 +289,13 @@ ${SEED_SHELF_SECTION}
 
 # Design Artifact
 
+## Compact-First Scaffold
+- Default to the compact design spine unless risk requires Standard/Deep add-ons.
+- Compact required spine: Codebase Investigation, Architecture Boundaries, Architecture Diagram, Data Flow, Failure Mode Table, Test Strategy, and Completion Dashboard.
+- Mark optional Standard/Deep sections as \`Omitted - compact design\` when they do not apply; do not expand the scaffold just to fill empty tables.
+
 ## Upstream Handoff
-- Source artifacts: \`02-scope-<slug>.md\`, \`02a-research.md\` when present
+- Source artifacts: \`02-scope-<slug>.md\`, \`02a-research.md\` only when present for deep/high-risk research
 - Decisions carried forward:
 - Constraints carried forward:
 - Open questions:
@@ -308,12 +314,11 @@ ${SEED_SHELF_SECTION}
 | Layer 3 |  |  |
 
 ## Research Fleet Synthesis
-| Lens | Key findings | Design impact | Evidence |
+| Lens actually run | Key findings | Design impact | Evidence |
 |---|---|---|---|
-| stack-researcher |  |  |  |
-| features-researcher |  |  |  |
-| architecture-researcher |  |  |  |
-| pitfalls-researcher |  |  |  |
+| compact inline synthesis |  |  |  |
+
+> Default path: compact inline synthesis here. Deep/high-risk work may also write \`.cclaw/artifacts/02a-research.md\`.
 
 ## Architecture Boundaries
 | Component | Responsibility | Requirement Refs (R#) | Decision Refs (LD#hash) | Owner |
@@ -329,12 +334,14 @@ ${MARKDOWN_CODE_FENCE}
 ${MARKDOWN_CODE_FENCE}
 
 ## Data-Flow Shadow Paths
+- Standard/Deep add-on; omit when compact design does not need a shadow path.
 <!-- diagram: data-flow-shadow-paths -->
 | Path | Trigger | Fallback/Degrade behavior |
 |---|---|---|
 |  |  |  |
 
 ## Error Flow Diagram
+- Standard/Deep add-on; omit when the Failure Mode Table is sufficient.
 
 <!-- diagram: error-flow -->
 
@@ -343,6 +350,7 @@ ${MARKDOWN_CODE_FENCE}
 ${MARKDOWN_CODE_FENCE}
 
 ## State Machine Diagram
+- Deep add-on; omit for compact design.
 
 <!-- diagram: state-machine -->
 
@@ -351,6 +359,7 @@ ${MARKDOWN_CODE_FENCE}
 ${MARKDOWN_CODE_FENCE}
 
 ## Rollback Flowchart
+- Deep add-on; omit for compact design.
 
 <!-- diagram: rollback-flowchart -->
 
@@ -359,6 +368,7 @@ ${MARKDOWN_CODE_FENCE}
 ${MARKDOWN_CODE_FENCE}
 
 ## Deployment Sequence Diagram
+- Deep add-on; omit for compact design.
 
 <!-- diagram: deployment-sequence -->
 
@@ -426,7 +436,7 @@ ${MARKDOWN_CODE_FENCE}
 |---|---|---|---|---|
 | F-1 | architecture_fit |  | accept/reject/defer |  |
 
-## Spec Review Loop
+## Design Outside Voice Loop
 | Iteration | Quality Score | Findings | Stop decision |
 |---|---|---|---|
 | 1 | 0.00 | 0 | continue/stop |
@@ -439,6 +449,7 @@ ${MARKDOWN_CODE_FENCE}
 - 
 
 ## Parallelization Strategy
+- Standard/Deep add-on when multi-module; omit for compact sequential work.
 - Parallel lanes:
 - Conflict risks:
 
@@ -448,11 +459,13 @@ ${MARKDOWN_CODE_FENCE}
 |  |  |  |
 
 ## Interface Contracts
+- Standard/Deep add-on when module boundaries or APIs change; omit for compact local changes.
 | Module | Produces | Consumes |
 |---|---|---|
 |  |  |  |
 
 ## Unresolved Decisions
+- Standard/Deep add-on; use \`None\` for compact design with no unresolved decisions.
 | Decision | Missing info | Owner | Default |
 |---|---|---|---|
 |  |  |  |  |
@@ -481,7 +494,7 @@ ${SEED_SHELF_SECTION}
 # Specification Artifact
 
 ## Upstream Handoff
-- Source artifacts: \`02-scope-<slug>.md\`, \`03-design-<slug>.md\`
+- Source artifacts: standard uses \`02-scope-<slug>.md\` + \`03-design-<slug>.md\`; medium uses \`01-brainstorm-<slug>.md\` when present; quick uses \`00-idea.md\` plus reproduction context.
 - Decisions carried forward:
 - Constraints carried forward:
 - Open questions:
@@ -492,9 +505,14 @@ ${SEED_SHELF_SECTION}
 |---|---|---|---|
 | AC-1 | R1 |  |  |
 
-> Every AC must reference at least one \`R#\` from \`02-scope.md\`. ACs are
-> stable (never renumber): dropped ACs stay with Priority \`DROPPED\`; new
-> ones append with the next free \`AC-#\`.
+> Standard ACs reference at least one \`R#\` from \`02-scope.md\`. Quick-track ACs may instead put \`Quick Reproduction Contract\` / bug-slice refs in the Requirement Ref column and \`N/A\` for Design Decision Ref. ACs are stable (never renumber): dropped ACs stay with Priority \`DROPPED\`; new ones append with the next free \`AC-#\`.
+
+## Quick Reproduction Contract
+> Required for quick bug-fix specs; use \`N/A\` for non-bugfix or standard/medium tracks. TDD turns this contract into the RED reproduction test.
+
+| Bug slice | Symptom | Repro steps | Expected RED test behavior | Linked acceptance criterion |
+|---|---|---|---|---|
+| QS-1 |  |  |  | AC-1 |
 
 ## Edge Cases
 | Criterion ID | Boundary case | Error case |
@@ -627,7 +645,7 @@ Execution rule: complete and verify each batch before starting the next batch.
 # TDD Artifact
 
 ## Upstream Handoff
-- Source artifacts: \`04-spec.md\`, \`05-plan.md\`
+- Source artifacts: \`04-spec.md\`; \`05-plan.md\` when present. Quick track uses spec acceptance items / bug reproduction slices instead of nonexistent plan tasks.
 - Decisions carried forward:
 - Constraints carried forward:
 - Open questions:
@@ -654,9 +672,11 @@ Execution rule: complete and verify each batch before starting the next batch.
 | S-1 |  |  |  |
 
 ## Acceptance Mapping
-| Slice | Plan task ID | Spec criterion ID |
+| Slice | Plan task ID or quick source | Spec criterion ID |
 |---|---|---|
-| S-1 | T-1 | AC-1 |
+| S-1 | T-1 / QS-1 | AC-1 |
+
+> On quick track, map to the \`Quick Reproduction Contract\` bug slice or spec acceptance item. Do not invent a plan task just to satisfy this table.
 
 ## Failure Analysis
 | Slice | Expected missing behavior | Actual failure reason |
@@ -709,7 +729,7 @@ Execution rule: complete and verify each batch before starting the next batch.
 # Review Artifact
 
 ## Upstream Handoff
-- Source artifacts: \`04-spec.md\`, \`05-plan.md\`, \`06-tdd.md\`
+- Source artifacts: \`04-spec.md\`, \`06-tdd.md\`; \`05-plan.md\` only when present. Quick track reviews spec acceptance items / bug reproduction slices without requiring plan-task coverage.
 - Decisions carried forward:
 - Constraints carried forward:
 - Open questions:
@@ -723,7 +743,7 @@ Execution rule: complete and verify each batch before starting the next batch.
 ## Layer 2 Findings
 | ID | Severity | Category | Description | Status |
 |---|---|---|---|---|
-| R-1 | Critical/Important/Suggestion | correctness/security/performance/architecture |  | open/resolved |
+| R-1 | Critical/Important/Suggestion | correctness/security/performance/architecture/external-safety |  | open/resolved |
 - NO_CHANGE_ATTESTATION: <required when Category=security has no entries; explain why no security-relevant changes were detected>
 
 ## Incoming Feedback Queue
@@ -746,15 +766,15 @@ Execution rule: complete and verify each batch before starting the next batch.
 
 ## Completeness Snapshot
 - AC coverage: <N>/<M> (<percent>%)
-- Task coverage (tasks backed by ≥1 test slice): <N>/<M>
-- Slice coverage (slices linked to ≥1 AC): <N>/<M>
+- Task coverage (tasks backed by ≥1 test slice): <N>/<M> or \`N/A - quick track has no plan artifact\`
+- Slice coverage (slices linked to ≥1 AC or bug reproduction slice): <N>/<M>
 - Adversarial review: not triggered | pass | fail
 - Overall: complete | concerns | blocked
 
 ## Trace Matrix Check
-- Command: \`cclaw internal trace-matrix\`
+- Command: \`cclaw internal trace-matrix\` when plan artifacts exist or the active track enforces it; quick track may record direct AC/reproduction-slice coverage instead.
 - Orphaned criteria: 0
-- Orphaned tasks: 0
+- Orphaned tasks: 0 or \`N/A - quick track\`
 - Orphaned tests: 0
 - Evidence ref:
 
@@ -955,7 +975,7 @@ Track-specific skips are allowed only when \`flow-state.track\` + \`skippedStage
 | Class | Route |
 |---|---|
 | non-trivial software work | \`/cc <idea>\` |
-| trivial software fix | \`/cc <idea>\` (quick or medium track) |
+| trivial software fix | \`/cc <idea>\` (quick track) |
 | bugfix with repro | \`/cc <idea>\` and enforce RED-first in tdd |
 | pure question / non-software | direct answer (no stage flow) |
 

package/dist/content/view-command.js

@@ -37,9 +37,11 @@ ${conversationLanguagePolicyMarkdown()}
 For machine orchestration, emit one JSON envelope:
 
 \`\`\`json
-{"version":"1","kind":"stage-output","stage":"non-flow","payload":{"command":"/cc-view","subcommand":"status","summary":"<short>"},"emittedAt":"<ISO-8601>"}
+{"version":"1","kind":"stage-output","stage":"non-flow","payload":{"command":"/cc-view <status|tree|diff>","subcommand":"<status|tree|diff>","summary":"<short>"},"emittedAt":"<ISO-8601>"}
 \`\`\`
 
+Use the parsed/defaulted subcommand in both \`payload.command\` and \`payload.subcommand\`; do not collapse \`tree\` or \`diff\` responses to \`status\`.
+
 Validate envelopes with:
 \`cclaw internal envelope-validate --stdin\`