@wolfx/oh-my-openagent 4.1.1 → 4.2.0-patch.1

package/dist/agents/prometheus/plan-template.d.ts

@@ -4,4 +4,4 @@
  * The markdown template structure for work plans generated by Prometheus.
  * Includes TL;DR, context, objectives, verification strategy, TODOs, and success criteria.
  */
-export declare const PROMETHEUS_PLAN_TEMPLATE = "## Plan Structure\n\nGenerate plan to: `.sisyphus/plans/{name}.md`\n\n```markdown\n# {Plan Title}\n\n## TL;DR\n\n> **Quick Summary**: [1-2 sentences capturing the core objective and approach]\n> \n> **Deliverables**: [Bullet list of concrete outputs]\n> - [Output 1]\n> - [Output 2]\n> \n> **Estimated Effort**: [Quick | Short | Medium | Large | XL]\n> **Parallel Execution**: [YES - N waves | NO - sequential]\n> **Critical Path**: [Task X \u2192 Task Y \u2192 Task Z]\n\n---\n\n## Context\n\n### Original Request\n[User's initial description]\n\n### Interview Summary\n**Key Discussions**:\n- [Point 1]: [User's decision/preference]\n- [Point 2]: [Agreed approach]\n\n**Research Findings**:\n- [Finding 1]: [Implication]\n- [Finding 2]: [Recommendation]\n\n### Metis Review\n**Identified Gaps** (addressed):\n- [Gap 1]: [How resolved]\n- [Gap 2]: [How resolved]\n\n---\n\n## Work Objectives\n\n### Core Objective\n[1-2 sentences: what we're achieving]\n\n### Concrete Deliverables\n- [Exact file/endpoint/feature]\n\n### Definition of Done\n- [ ] [Verifiable condition with command]\n\n### Must Have\n- [Non-negotiable requirement]\n\n### Must NOT Have (Guardrails)\n- [Explicit exclusion from Metis review]\n- [AI slop pattern to avoid]\n- [Scope boundary]\n\n---\n\n## Verification Strategy (MANDATORY)\n\n> **ZERO HUMAN INTERVENTION** - ALL verification is agent-executed. No exceptions.\n> Acceptance criteria requiring \"user manually tests/confirms\" are FORBIDDEN.\n\n### Test Decision\n- **Infrastructure exists**: [YES/NO]\n- **Automated tests**: [TDD / Tests-after / None]\n- **Framework**: [bun test / vitest / jest / pytest / none]\n- **If TDD**: Each task follows RED (failing test) \u2192 GREEN (minimal impl) \u2192 REFACTOR\n\n### QA Policy\nEvery task MUST include agent-executed QA scenarios (see TODO template below).\nEvidence saved to `.sisyphus/evidence/task-{N}-{scenario-slug}.{ext}`.\n\n- **Frontend/UI**: Use Playwright (playwright skill) - Navigate, interact, assert DOM, screenshot\n- **TUI/CLI**: Use interactive_bash (tmux) - Run command, send keystrokes, validate output\n- **API/Backend**: Use Bash (curl) - Send requests, assert status + response fields\n- **Library/Module**: Use Bash (bun/node REPL) - Import, call functions, compare output\n\n---\n\n## Execution Strategy\n\n### Parallel Execution Waves\n\n> Maximize throughput by grouping independent tasks into parallel waves.\n> Each wave completes before the next begins.\n> Target: 5-8 tasks per wave. Fewer than 3 per wave (except final) = under-splitting.\n\n```\nWave 1 (Start Immediately - foundation + scaffolding):\n\u251C\u2500\u2500 Task 1: Project scaffolding + config [quick]\n\u251C\u2500\u2500 Task 2: Design system tokens [quick]\n\u251C\u2500\u2500 Task 3: Type definitions [quick]\n\u251C\u2500\u2500 Task 4: Schema definitions [quick]\n\u251C\u2500\u2500 Task 5: Storage interface + in-memory impl [quick]\n\u251C\u2500\u2500 Task 6: Auth middleware [quick]\n\u2514\u2500\u2500 Task 7: Client module [quick]\n\nWave 2 (After Wave 1 - core modules, MAX PARALLEL):\n\u251C\u2500\u2500 Task 8: Core business logic (depends: 3, 5, 7) [deep]\n\u251C\u2500\u2500 Task 9: API endpoints (depends: 4, 5) [unspecified-high]\n\u251C\u2500\u2500 Task 10: Secondary storage impl (depends: 5) [unspecified-high]\n\u251C\u2500\u2500 Task 11: Retry/fallback logic (depends: 8) [deep]\n\u251C\u2500\u2500 Task 12: UI layout + navigation (depends: 2) [visual-engineering]\n\u251C\u2500\u2500 Task 13: API client + hooks (depends: 4) [quick]\n\u2514\u2500\u2500 Task 14: Telemetry middleware (depends: 5, 10) [unspecified-high]\n\nWave 3 (After Wave 2 - integration + UI):\n\u251C\u2500\u2500 Task 15: Main route combining modules (depends: 6, 11, 14) [deep]\n\u251C\u2500\u2500 Task 16: UI data visualization (depends: 12, 13) [visual-engineering]\n\u251C\u2500\u2500 Task 17: Deployment config A (depends: 15) [quick]\n\u251C\u2500\u2500 Task 18: Deployment config B (depends: 15) [quick]\n\u251C\u2500\u2500 Task 19: Deployment config C (depends: 15) [quick]\n\u2514\u2500\u2500 Task 20: UI request log + build (depends: 16) [visual-engineering]\n\nWave FINAL (After ALL tasks \u2014 4 parallel reviews, then user okay):\n\u251C\u2500\u2500 Task F1: Plan compliance audit (oracle)\n\u251C\u2500\u2500 Task F2: Code quality review (unspecified-high)\n\u251C\u2500\u2500 Task F3: Real manual QA (unspecified-high)\n\u2514\u2500\u2500 Task F4: Scope fidelity check (deep)\n-> Present results -> Get explicit user okay\n\nCritical Path: Task 1 \u2192 Task 5 \u2192 Task 8 \u2192 Task 11 \u2192 Task 15 \u2192 Task 21 \u2192 F1-F4 \u2192 user okay\nParallel Speedup: ~70% faster than sequential\nMax Concurrent: 7 (Waves 1 & 2)\n```\n\n### Dependency Matrix (abbreviated - show ALL tasks in your generated plan)\n\n- **1-7**: - - 8-14, 1\n- **8**: 3, 5, 7 - 11, 15, 2\n- **11**: 8 - 15, 2\n- **14**: 5, 10 - 15, 2\n- **15**: 6, 11, 14 - 17-19, 21, 3\n- **21**: 15 - 23, 24, 4\n\n> This is abbreviated for reference. YOUR generated plan must include the FULL matrix for ALL tasks.\n\n### Agent Dispatch Summary\n\n- **1**: **7** - T1-T4 \u2192 `quick`, T5 \u2192 `quick`, T6 \u2192 `quick`, T7 \u2192 `quick`\n- **2**: **7** - T8 \u2192 `deep`, T9 \u2192 `unspecified-high`, T10 \u2192 `unspecified-high`, T11 \u2192 `deep`, T12 \u2192 `visual-engineering`, T13 \u2192 `quick`, T14 \u2192 `unspecified-high`\n- **3**: **6** - T15 \u2192 `deep`, T16 \u2192 `visual-engineering`, T17-T19 \u2192 `quick`, T20 \u2192 `visual-engineering`\n- **4**: **4** - T21 \u2192 `deep`, T22 \u2192 `unspecified-high`, T23 \u2192 `deep`, T24 \u2192 `git`\n- **FINAL**: **4** - F1 \u2192 `oracle`, F2 \u2192 `unspecified-high`, F3 \u2192 `unspecified-high`, F4 \u2192 `deep`\n\n---\n\n## TODOs\n\n> Implementation + Test = ONE Task. Never separate.\n> EVERY task MUST have: Recommended Agent Profile + Parallelization info + QA Scenarios.\n> **A task WITHOUT QA Scenarios is INCOMPLETE. No exceptions.**\n\n- [ ] 1. [Task Title]\n\n  **What to do**:\n  - [Clear implementation steps]\n  - [Test cases to cover]\n\n  **Must NOT do**:\n  - [Specific exclusions from guardrails]\n\n  **Recommended Agent Profile**:\n  > Select category + skills based on task domain. Justify each choice.\n  - **Category**: `[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]`\n    - Reason: [Why this category fits the task domain]\n  - **Skills**: [`skill-1`, `skill-2`]\n    - `skill-1`: [Why needed - domain overlap explanation]\n    - `skill-2`: [Why needed - domain overlap explanation]\n  - **Skills Evaluated but Omitted**:\n    - `omitted-skill`: [Why domain doesn't overlap]\n\n  **Parallelization**:\n  - **Can Run In Parallel**: YES | NO\n  - **Parallel Group**: Wave N (with Tasks X, Y) | Sequential\n  - **Blocks**: [Tasks that depend on this task completing]\n  - **Blocked By**: [Tasks this depends on] | None (can start immediately)\n\n  **References** (CRITICAL - Be Exhaustive):\n\n  > The executor has NO context from your interview. References are their ONLY guide.\n  > Each reference must answer: \"What should I look at and WHY?\"\n\n  **Pattern References** (existing code to follow):\n  - `src/services/auth.ts:45-78` - Authentication flow pattern (JWT creation, refresh token handling)\n\n  **API/Type References** (contracts to implement against):\n  - `src/types/user.ts:UserDTO` - Response shape for user endpoints\n\n  **Test References** (testing patterns to follow):\n  - `src/__tests__/auth.test.ts:describe(\"login\")` - Test structure and mocking patterns\n\n  **External References** (libraries and frameworks):\n  - Official docs: `https://zod.dev/?id=basic-usage` - Zod validation syntax\n\n  **WHY Each Reference Matters** (explain the relevance):\n  - Don't just list files - explain what pattern/information the executor should extract\n  - Bad: `src/utils.ts` (vague, which utils? why?)\n  - Good: `src/utils/validation.ts:sanitizeInput()` - Use this sanitization pattern for user input\n\n  **Acceptance Criteria**:\n\n  > **AGENT-EXECUTABLE VERIFICATION ONLY** - No human action permitted.\n  > Every criterion MUST be verifiable by running a command or using a tool.\n\n  **If TDD (tests enabled):**\n  - [ ] Test file created: src/auth/login.test.ts\n  - [ ] bun test src/auth/login.test.ts \u2192 PASS (3 tests, 0 failures)\n\n  **QA Scenarios (MANDATORY - task is INCOMPLETE without these):**\n\n  > **This is NOT optional. A task without QA scenarios WILL BE REJECTED.**\n  >\n  > Write scenario tests that verify the ACTUAL BEHAVIOR of what you built.\n  > Minimum: 1 happy path + 1 failure/edge case per task.\n  > Each scenario = exact tool + exact steps + exact assertions + evidence path.\n  >\n  > **The executing agent MUST run these scenarios after implementation.**\n  > **The orchestrator WILL verify evidence files exist before marking task complete.**\n\n  \\`\\`\\`\n  Scenario: [Happy path - what SHOULD work]\n    Tool: [Playwright / interactive_bash / Bash (curl)]\n    Preconditions: [Exact setup state]\n    Steps:\n      1. [Exact action - specific command/selector/endpoint, no vagueness]\n      2. [Next action - with expected intermediate state]\n      3. [Assertion - exact expected value, not \"verify it works\"]\n    Expected Result: [Concrete, observable, binary pass/fail]\n    Failure Indicators: [What specifically would mean this failed]\n    Evidence: .sisyphus/evidence/task-{N}-{scenario-slug}.{ext}\n\n  Scenario: [Failure/edge case - what SHOULD fail gracefully]\n    Tool: [same format]\n    Preconditions: [Invalid input / missing dependency / error state]\n    Steps:\n      1. [Trigger the error condition]\n      2. [Assert error is handled correctly]\n    Expected Result: [Graceful failure with correct error message/code]\n    Evidence: .sisyphus/evidence/task-{N}-{scenario-slug}-error.{ext}\n  \\`\\`\\`\n\n  > **Specificity requirements - every scenario MUST use:**\n  > - **Selectors**: Specific CSS selectors (`.login-button`, not \"the login button\")\n  > - **Data**: Concrete test data (`\"test@example.com\"`, not `\"[email]\"`)\n  > - **Assertions**: Exact values (`text contains \"Welcome back\"`, not \"verify it works\")\n  > - **Timing**: Wait conditions where relevant (`timeout: 10s`)\n  > - **Negative**: At least ONE failure/error scenario per task\n  >\n  > **Anti-patterns (your scenario is INVALID if it looks like this):**\n  > - \u274C \"Verify it works correctly\" - HOW? What does \"correctly\" mean?\n  > - \u274C \"Check the API returns data\" - WHAT data? What fields? What values?\n  > - \u274C \"Test the component renders\" - WHERE? What selector? What content?\n  > - \u274C Any scenario without an evidence path\n\n  **Evidence to Capture:**\n  - [ ] Each evidence file named: task-{N}-{scenario-slug}.{ext}\n  - [ ] Screenshots for UI, terminal output for CLI, response bodies for API\n\n  **Commit**: YES | NO (groups with N)\n  - Message: `type(scope): desc`\n  - Files: `path/to/file`\n  - Pre-commit: `test command`\n\n---\n\n## Final Verification Wave (MANDATORY \u2014 after ALL implementation tasks)\n\n> 4 review agents run in PARALLEL. ALL must APPROVE. Present consolidated results to user and get explicit \"okay\" before completing.\n>\n> **Do NOT auto-proceed after verification. Wait for user's explicit approval before marking work complete.**\n> **Never mark F1-F4 as checked before getting user's okay.** Rejection or user feedback -> fix -> re-run -> present again -> wait for okay.\n\n- [ ] F1. **Plan Compliance Audit** \u2014 `oracle`\n  Read the plan end-to-end. For each \"Must Have\": verify implementation exists (read file, curl endpoint, run command). For each \"Must NOT Have\": search codebase for forbidden patterns \u2014 reject with file:line if found. Check evidence files exist in .sisyphus/evidence/. Compare deliverables against plan.\n  Output: `Must Have [N/N] | Must NOT Have [N/N] | Tasks [N/N] | VERDICT: APPROVE/REJECT`\n\n- [ ] F2. **Code Quality Review** \u2014 `unspecified-high`\n  Run `tsc --noEmit` + linter + `bun test`. Review all changed files for: `as any`/`@ts-ignore`, empty catches, console.log in prod, commented-out code, unused imports. Check AI slop: excessive comments, over-abstraction, generic names (data/result/item/temp).\n  Output: `Build [PASS/FAIL] | Lint [PASS/FAIL] | Tests [N pass/N fail] | Files [N clean/N issues] | VERDICT`\n\n- [ ] F3. **Real Manual QA** \u2014 `unspecified-high` (+ `playwright` skill if UI)\n  Start from clean state. Execute EVERY QA scenario from EVERY task \u2014 follow exact steps, capture evidence. Test cross-task integration (features working together, not isolation). Test edge cases: empty state, invalid input, rapid actions. Save to `.sisyphus/evidence/final-qa/`.\n  Output: `Scenarios [N/N pass] | Integration [N/N] | Edge Cases [N tested] | VERDICT`\n\n- [ ] F4. **Scope Fidelity Check** \u2014 `deep`\n  For each task: read \"What to do\", read actual diff (git log/diff). Verify 1:1 \u2014 everything in spec was built (no missing), nothing beyond spec was built (no creep). Check \"Must NOT do\" compliance. Detect cross-task contamination: Task N touching Task M's files. Flag unaccounted changes.\n  Output: `Tasks [N/N compliant] | Contamination [CLEAN/N issues] | Unaccounted [CLEAN/N files] | VERDICT`\n\n---\n\n## Commit Strategy\n\n- **1**: `type(scope): desc` - file.ts, npm test\n\n---\n\n## Success Criteria\n\n### Verification Commands\n```bash\ncommand  # Expected: output\n```\n\n### Final Checklist\n- [ ] All \"Must Have\" present\n- [ ] All \"Must NOT Have\" absent\n- [ ] All tests pass\n```\n\n---\n";
+export declare const PROMETHEUS_PLAN_TEMPLATE = "## Plan Structure\n\nGenerate plan to: `.omo/plans/{name}.md`\n\n```markdown\n# {Plan Title}\n\n## TL;DR\n\n> **Quick Summary**: [1-2 sentences capturing the core objective and approach]\n> \n> **Deliverables**: [Bullet list of concrete outputs]\n> - [Output 1]\n> - [Output 2]\n> \n> **Estimated Effort**: [Quick | Short | Medium | Large | XL]\n> **Parallel Execution**: [YES - N waves | NO - sequential]\n> **Critical Path**: [Task X \u2192 Task Y \u2192 Task Z]\n\n---\n\n## Context\n\n### Original Request\n[User's initial description]\n\n### Interview Summary\n**Key Discussions**:\n- [Point 1]: [User's decision/preference]\n- [Point 2]: [Agreed approach]\n\n**Research Findings**:\n- [Finding 1]: [Implication]\n- [Finding 2]: [Recommendation]\n\n### Metis Review\n**Identified Gaps** (addressed):\n- [Gap 1]: [How resolved]\n- [Gap 2]: [How resolved]\n\n---\n\n## Work Objectives\n\n### Core Objective\n[1-2 sentences: what we're achieving]\n\n### Concrete Deliverables\n- [Exact file/endpoint/feature]\n\n### Definition of Done\n- [ ] [Verifiable condition with command]\n\n### Must Have\n- [Non-negotiable requirement]\n\n### Must NOT Have (Guardrails)\n- [Explicit exclusion from Metis review]\n- [AI slop pattern to avoid]\n- [Scope boundary]\n\n---\n\n## Verification Strategy (MANDATORY)\n\n> **ZERO HUMAN INTERVENTION** - ALL verification is agent-executed. No exceptions.\n> Acceptance criteria requiring \"user manually tests/confirms\" are FORBIDDEN.\n\n### Test Decision\n- **Infrastructure exists**: [YES/NO]\n- **Automated tests**: [TDD / Tests-after / None]\n- **Framework**: [bun test / vitest / jest / pytest / none]\n- **If TDD**: Each task follows RED (failing test) \u2192 GREEN (minimal impl) \u2192 REFACTOR\n\n### QA Policy\nEvery task MUST include agent-executed QA scenarios (see TODO template below).\nEvidence saved to `.omo/evidence/task-{N}-{scenario-slug}.{ext}`.\n\n- **Frontend/UI**: Use Playwright (playwright skill) - Navigate, interact, assert DOM, screenshot\n- **TUI/CLI**: Use interactive_bash (tmux) - Run command, send keystrokes, validate output\n- **API/Backend**: Use Bash (curl) - Send requests, assert status + response fields\n- **Library/Module**: Use Bash (bun/node REPL) - Import, call functions, compare output\n\n---\n\n## Execution Strategy\n\n### Parallel Execution Waves\n\n> Maximize throughput by grouping independent tasks into parallel waves.\n> Each wave completes before the next begins.\n> Target: 5-8 tasks per wave. Fewer than 3 per wave (except final) = under-splitting.\n\n```\nWave 1 (Start Immediately - foundation + scaffolding):\n\u251C\u2500\u2500 Task 1: Project scaffolding + config [quick]\n\u251C\u2500\u2500 Task 2: Design system tokens [quick]\n\u251C\u2500\u2500 Task 3: Type definitions [quick]\n\u251C\u2500\u2500 Task 4: Schema definitions [quick]\n\u251C\u2500\u2500 Task 5: Storage interface + in-memory impl [quick]\n\u251C\u2500\u2500 Task 6: Auth middleware [quick]\n\u2514\u2500\u2500 Task 7: Client module [quick]\n\nWave 2 (After Wave 1 - core modules, MAX PARALLEL):\n\u251C\u2500\u2500 Task 8: Core business logic (depends: 3, 5, 7) [deep]\n\u251C\u2500\u2500 Task 9: API endpoints (depends: 4, 5) [unspecified-high]\n\u251C\u2500\u2500 Task 10: Secondary storage impl (depends: 5) [unspecified-high]\n\u251C\u2500\u2500 Task 11: Retry/fallback logic (depends: 8) [deep]\n\u251C\u2500\u2500 Task 12: UI layout + navigation (depends: 2) [visual-engineering]\n\u251C\u2500\u2500 Task 13: API client + hooks (depends: 4) [quick]\n\u2514\u2500\u2500 Task 14: Telemetry middleware (depends: 5, 10) [unspecified-high]\n\nWave 3 (After Wave 2 - integration + UI):\n\u251C\u2500\u2500 Task 15: Main route combining modules (depends: 6, 11, 14) [deep]\n\u251C\u2500\u2500 Task 16: UI data visualization (depends: 12, 13) [visual-engineering]\n\u251C\u2500\u2500 Task 17: Deployment config A (depends: 15) [quick]\n\u251C\u2500\u2500 Task 18: Deployment config B (depends: 15) [quick]\n\u251C\u2500\u2500 Task 19: Deployment config C (depends: 15) [quick]\n\u2514\u2500\u2500 Task 20: UI request log + build (depends: 16) [visual-engineering]\n\nWave FINAL (After ALL tasks \u2014 4 parallel reviews, then user okay):\n\u251C\u2500\u2500 Task F1: Plan compliance audit (oracle)\n\u251C\u2500\u2500 Task F2: Code quality review (unspecified-high)\n\u251C\u2500\u2500 Task F3: Real manual QA (unspecified-high)\n\u2514\u2500\u2500 Task F4: Scope fidelity check (deep)\n-> Present results -> Get explicit user okay\n\nCritical Path: Task 1 \u2192 Task 5 \u2192 Task 8 \u2192 Task 11 \u2192 Task 15 \u2192 Task 21 \u2192 F1-F4 \u2192 user okay\nParallel Speedup: ~70% faster than sequential\nMax Concurrent: 7 (Waves 1 & 2)\n```\n\n### Dependency Matrix (abbreviated - show ALL tasks in your generated plan)\n\n- **1-7**: - - 8-14, 1\n- **8**: 3, 5, 7 - 11, 15, 2\n- **11**: 8 - 15, 2\n- **14**: 5, 10 - 15, 2\n- **15**: 6, 11, 14 - 17-19, 21, 3\n- **21**: 15 - 23, 24, 4\n\n> This is abbreviated for reference. YOUR generated plan must include the FULL matrix for ALL tasks.\n\n### Agent Dispatch Summary\n\n- **1**: **7** - T1-T4 \u2192 `quick`, T5 \u2192 `quick`, T6 \u2192 `quick`, T7 \u2192 `quick`\n- **2**: **7** - T8 \u2192 `deep`, T9 \u2192 `unspecified-high`, T10 \u2192 `unspecified-high`, T11 \u2192 `deep`, T12 \u2192 `visual-engineering`, T13 \u2192 `quick`, T14 \u2192 `unspecified-high`\n- **3**: **6** - T15 \u2192 `deep`, T16 \u2192 `visual-engineering`, T17-T19 \u2192 `quick`, T20 \u2192 `visual-engineering`\n- **4**: **4** - T21 \u2192 `deep`, T22 \u2192 `unspecified-high`, T23 \u2192 `deep`, T24 \u2192 `git`\n- **FINAL**: **4** - F1 \u2192 `oracle`, F2 \u2192 `unspecified-high`, F3 \u2192 `unspecified-high`, F4 \u2192 `deep`\n\n---\n\n## TODOs\n\n> Implementation + Test = ONE Task. Never separate.\n> EVERY task MUST have: Recommended Agent Profile + Parallelization info + QA Scenarios.\n> **A task WITHOUT QA Scenarios is INCOMPLETE. No exceptions.**\n\n- [ ] 1. [Task Title]\n\n  **What to do**:\n  - [Clear implementation steps]\n  - [Test cases to cover]\n\n  **Must NOT do**:\n  - [Specific exclusions from guardrails]\n\n  **Recommended Agent Profile**:\n  > Select category + skills based on task domain. Justify each choice.\n  - **Category**: `[visual-engineering | ultrabrain | artistry | quick | unspecified-low | unspecified-high | writing]`\n    - Reason: [Why this category fits the task domain]\n  - **Skills**: [`skill-1`, `skill-2`]\n    - `skill-1`: [Why needed - domain overlap explanation]\n    - `skill-2`: [Why needed - domain overlap explanation]\n  - **Skills Evaluated but Omitted**:\n    - `omitted-skill`: [Why domain doesn't overlap]\n\n  **Parallelization**:\n  - **Can Run In Parallel**: YES | NO\n  - **Parallel Group**: Wave N (with Tasks X, Y) | Sequential\n  - **Blocks**: [Tasks that depend on this task completing]\n  - **Blocked By**: [Tasks this depends on] | None (can start immediately)\n\n  **References** (CRITICAL - Be Exhaustive):\n\n  > The executor has NO context from your interview. References are their ONLY guide.\n  > Each reference must answer: \"What should I look at and WHY?\"\n\n  **Pattern References** (existing code to follow):\n  - `src/services/auth.ts:45-78` - Authentication flow pattern (JWT creation, refresh token handling)\n\n  **API/Type References** (contracts to implement against):\n  - `src/types/user.ts:UserDTO` - Response shape for user endpoints\n\n  **Test References** (testing patterns to follow):\n  - `src/__tests__/auth.test.ts:describe(\"login\")` - Test structure and mocking patterns\n\n  **External References** (libraries and frameworks):\n  - Official docs: `https://zod.dev/?id=basic-usage` - Zod validation syntax\n\n  **WHY Each Reference Matters** (explain the relevance):\n  - Don't just list files - explain what pattern/information the executor should extract\n  - Bad: `src/utils.ts` (vague, which utils? why?)\n  - Good: `src/utils/validation.ts:sanitizeInput()` - Use this sanitization pattern for user input\n\n  **Acceptance Criteria**:\n\n  > **AGENT-EXECUTABLE VERIFICATION ONLY** - No human action permitted.\n  > Every criterion MUST be verifiable by running a command or using a tool.\n\n  **If TDD (tests enabled):**\n  - [ ] Test file created: src/auth/login.test.ts\n  - [ ] bun test src/auth/login.test.ts \u2192 PASS (3 tests, 0 failures)\n\n  **QA Scenarios (MANDATORY - task is INCOMPLETE without these):**\n\n  > **This is NOT optional. A task without QA scenarios WILL BE REJECTED.**\n  >\n  > Write scenario tests that verify the ACTUAL BEHAVIOR of what you built.\n  > Minimum: 1 happy path + 1 failure/edge case per task.\n  > Each scenario = exact tool + exact steps + exact assertions + evidence path.\n  >\n  > **The executing agent MUST run these scenarios after implementation.**\n  > **The orchestrator WILL verify evidence files exist before marking task complete.**\n\n  \\`\\`\\`\n  Scenario: [Happy path - what SHOULD work]\n    Tool: [Playwright / interactive_bash / Bash (curl)]\n    Preconditions: [Exact setup state]\n    Steps:\n      1. [Exact action - specific command/selector/endpoint, no vagueness]\n      2. [Next action - with expected intermediate state]\n      3. [Assertion - exact expected value, not \"verify it works\"]\n    Expected Result: [Concrete, observable, binary pass/fail]\n    Failure Indicators: [What specifically would mean this failed]\n    Evidence: .omo/evidence/task-{N}-{scenario-slug}.{ext}\n\n  Scenario: [Failure/edge case - what SHOULD fail gracefully]\n    Tool: [same format]\n    Preconditions: [Invalid input / missing dependency / error state]\n    Steps:\n      1. [Trigger the error condition]\n      2. [Assert error is handled correctly]\n    Expected Result: [Graceful failure with correct error message/code]\n    Evidence: .omo/evidence/task-{N}-{scenario-slug}-error.{ext}\n  \\`\\`\\`\n\n  > **Specificity requirements - every scenario MUST use:**\n  > - **Selectors**: Specific CSS selectors (`.login-button`, not \"the login button\")\n  > - **Data**: Concrete test data (`\"test@example.com\"`, not `\"[email]\"`)\n  > - **Assertions**: Exact values (`text contains \"Welcome back\"`, not \"verify it works\")\n  > - **Timing**: Wait conditions where relevant (`timeout: 10s`)\n  > - **Negative**: At least ONE failure/error scenario per task\n  >\n  > **Anti-patterns (your scenario is INVALID if it looks like this):**\n  > - \u274C \"Verify it works correctly\" - HOW? What does \"correctly\" mean?\n  > - \u274C \"Check the API returns data\" - WHAT data? What fields? What values?\n  > - \u274C \"Test the component renders\" - WHERE? What selector? What content?\n  > - \u274C Any scenario without an evidence path\n\n  **Evidence to Capture:**\n  - [ ] Each evidence file named: task-{N}-{scenario-slug}.{ext}\n  - [ ] Screenshots for UI, terminal output for CLI, response bodies for API\n\n  **Commit**: YES | NO (groups with N)\n  - Message: `type(scope): desc`\n  - Files: `path/to/file`\n  - Pre-commit: `test command`\n\n---\n\n## Final Verification Wave (MANDATORY \u2014 after ALL implementation tasks)\n\n> 4 review agents run in PARALLEL. ALL must APPROVE. Present consolidated results to user and get explicit \"okay\" before completing.\n>\n> **Do NOT auto-proceed after verification. Wait for user's explicit approval before marking work complete.**\n> **Never mark F1-F4 as checked before getting user's okay.** Rejection or user feedback -> fix -> re-run -> present again -> wait for okay.\n\n- [ ] F1. **Plan Compliance Audit** \u2014 `oracle`\n  Read the plan end-to-end. For each \"Must Have\": verify implementation exists (read file, curl endpoint, run command). For each \"Must NOT Have\": search codebase for forbidden patterns \u2014 reject with file:line if found. Check evidence files exist in .omo/evidence/. Compare deliverables against plan.\n  Output: `Must Have [N/N] | Must NOT Have [N/N] | Tasks [N/N] | VERDICT: APPROVE/REJECT`\n\n- [ ] F2. **Code Quality Review** \u2014 `unspecified-high`\n  Run `tsc --noEmit` + linter + `bun test`. Review all changed files for: `as any`/`@ts-ignore`, empty catches, console.log in prod, commented-out code, unused imports. Check AI slop: excessive comments, over-abstraction, generic names (data/result/item/temp).\n  Output: `Build [PASS/FAIL] | Lint [PASS/FAIL] | Tests [N pass/N fail] | Files [N clean/N issues] | VERDICT`\n\n- [ ] F3. **Real Manual QA** \u2014 `unspecified-high` (+ `playwright` skill if UI)\n  Start from clean state. Execute EVERY QA scenario from EVERY task \u2014 follow exact steps, capture evidence. Test cross-task integration (features working together, not isolation). Test edge cases: empty state, invalid input, rapid actions. Save to `.omo/evidence/final-qa/`.\n  Output: `Scenarios [N/N pass] | Integration [N/N] | Edge Cases [N tested] | VERDICT`\n\n- [ ] F4. **Scope Fidelity Check** \u2014 `deep`\n  For each task: read \"What to do\", read actual diff (git log/diff). Verify 1:1 \u2014 everything in spec was built (no missing), nothing beyond spec was built (no creep). Check \"Must NOT do\" compliance. Detect cross-task contamination: Task N touching Task M's files. Flag unaccounted changes.\n  Output: `Tasks [N/N compliant] | Contamination [CLEAN/N issues] | Unaccounted [CLEAN/N files] | VERDICT`\n\n---\n\n## Commit Strategy\n\n- **1**: `type(scope): desc` - file.ts, npm test\n\n---\n\n## Success Criteria\n\n### Verification Commands\n```bash\ncommand  # Expected: output\n```\n\n### Final Checklist\n- [ ] All \"Must Have\" present\n- [ ] All \"Must NOT Have\" absent\n- [ ] All tests pass\n```\n\n---\n";

package/dist/config/schema/team-mode.d.ts

@@ -1,5 +1,5 @@
 import { z } from "zod";
-/** Team Mode config - see .sisyphus/plans/team-mode.md (D-01/D-25). */
+/** Team Mode config - see .omo/plans/team-mode.md (D-01/D-25). */
 export declare const TeamModeConfigSchema: z.ZodObject<{
     enabled: z.ZodDefault<z.ZodBoolean>;
     tmux_visualization: z.ZodDefault<z.ZodBoolean>;

package/dist/features/background-agent/error-classifier.d.ts

@@ -3,6 +3,7 @@ export declare function isAbortedSessionError(error: unknown): boolean;
 export declare function getErrorText(error: unknown): string;
 export declare function extractErrorName(error: unknown): string | undefined;
 export declare function extractErrorMessage(error: unknown): string | undefined;
+export declare function extractErrorStatusCode(error: unknown): number | undefined;
 interface EventPropertiesLike {
     [key: string]: unknown;
 }

package/dist/features/background-agent/fallback-retry-handler.d.ts

@@ -1,11 +1,25 @@
 import type { BackgroundTask } from "./types";
 import type { ConcurrencyManager } from "./concurrency";
 import type { OpencodeClient, QueueItem } from "./constants";
+import { log, readConnectedProvidersCache, readProviderModelsCache } from "../../shared";
+import { shouldRetryError, getNextFallback, hasMoreFallbacks, selectFallbackProvider } from "../../shared/model-error-classifier";
+import { transformModelForProvider } from "../../shared/provider-model-id-transform";
+export type FallbackRetryHandlerDeps = {
+    log: typeof log;
+    readProviderModelsCache: typeof readProviderModelsCache;
+    readConnectedProvidersCache: typeof readConnectedProvidersCache;
+    shouldRetryError: typeof shouldRetryError;
+    getNextFallback: typeof getNextFallback;
+    hasMoreFallbacks: typeof hasMoreFallbacks;
+    selectFallbackProvider: typeof selectFallbackProvider;
+    transformModelForProvider: typeof transformModelForProvider;
+};
 export declare function tryFallbackRetry(args: {
     task: BackgroundTask;
     errorInfo: {
         name?: string;
         message?: string;
+        statusCode?: number;
     };
     source: string;
     concurrencyManager: ConcurrencyManager;
@@ -21,4 +35,5 @@ export declare function tryFallbackRetry(args: {
         failedError?: string;
         nextModel: string;
     }) => void;
+    deps?: Partial<FallbackRetryHandlerDeps>;
 }): Promise<boolean>;

package/dist/features/background-agent/manager.d.ts

@@ -1,10 +1,10 @@
 import type { PluginInput } from "@opencode-ai/plugin";
+import type { BackgroundTaskConfig, TmuxConfig } from "../../config/schema";
 import type { ModelFallbackControllerAccessor } from "../../hooks/model-fallback";
-import type { BackgroundTask, LaunchInput, ResumeInput } from "./types";
-import { TaskHistory } from "./task-history";
 import { log } from "../../shared";
-import type { BackgroundTaskConfig, TmuxConfig } from "../../config/schema";
 import { type SubagentSpawnContext } from "./subagent-spawn-limits";
+import { TaskHistory } from "./task-history";
+import type { BackgroundTask, LaunchInput, ResumeInput } from "./types";
 interface EventProperties {
     sessionID?: string;
     info?: {
@@ -56,8 +56,7 @@ export declare class BackgroundManager {
     private completedTaskSummaries;
     private idleDeferralTimers;
     private notificationQueueByParent;
-    private pendingParentWakes;
-    private pendingParentWakeTimers;
+    private readonly parentWakeNotifier;
     private observedOutputSessions;
     private observedIncompleteTodosBySession;
     private rootDescendantCounts;
@@ -86,6 +85,8 @@ export declare class BackgroundManager {
     private removeTask;
     private archiveCompletedTask;
     private updateTaskParent;
+    private captureResumeTaskSnapshot;
+    private restoreTaskAfterSkippedResume;
     private removeTaskFromParentIndex;
     launch(input: LaunchInput): Promise<BackgroundTask>;
     private processKey;
@@ -113,17 +114,20 @@ export declare class BackgroundManager {
     resume(input: ResumeInput): Promise<BackgroundTask>;
     private checkSessionTodos;
     private markSessionOutputObserved;
+    private clearDispatchedParentWake;
+    private requeueDispatchedParentWake;
     private clearSessionOutputObserved;
     private clearSessionTodoObservation;
     private hasOutputSignalFromPart;
     handleEvent(event: Event): void;
+    private interruptTaskFromAsyncPromptFailure;
     private handleSessionErrorEvent;
     private tryFallbackRetry;
     markForNotification(task: BackgroundTask): void;
     getPendingNotifications(sessionID: string): BackgroundTask[];
     clearNotifications(sessionID: string): void;
     queuePendingNotification(sessionID: string | undefined, notification: string): void;
-    injectPendingNotificationsIntoChatMessage(output: {
+    injectPendingNotificationsIntoChatMessage(_output: {
         parts: Array<{
             type: string;
             text?: string;
@@ -172,11 +176,10 @@ export declare class BackgroundManager {
      */
     private tryCompleteTask;
     private notifyParentSession;
+    private resolveParentWakePromptContext;
     private isSessionActive;
     private queuePendingParentWake;
     private flushPendingParentWake;
-    private schedulePendingParentWakeFlush;
-    private clearPendingParentWakeTimer;
     private hasRunningTasks;
     private pruneStaleTasksAndNotifications;
     private checkAndInterruptStaleTasks;

package/dist/features/background-agent/parent-wake-notifier.d.ts

@@ -0,0 +1,74 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+type OpencodeClient = PluginInput["client"];
+export type ParentWakePromptContext = {
+    agent?: string;
+    model?: {
+        providerID: string;
+        modelID: string;
+    };
+    variant?: string;
+    tools?: Record<string, boolean>;
+};
+export type PendingParentWake = {
+    promptContext: ParentWakePromptContext;
+    notifications: string[];
+    shouldReply: boolean;
+    dispatchedAt?: number;
+    toolCallDeferralStartedAt?: number;
+};
+type ParentWakeNotifierDeps = {
+    client: OpencodeClient;
+    directory: string;
+    enqueueNotificationForParent: (parentSessionID: string | undefined, operation: () => Promise<void>) => Promise<void>;
+};
+type ParentWakeNotifierOptions = {
+    pendingRetryMs: number;
+    acceptedMessageSkewMs: number;
+    toolCallDeferMaxMs: number;
+    failureRequeueWindowMs: number;
+    /**
+     * If the latest message in the parent session is a `user` message added
+     * within this window, the parent-wake injection is deferred. Prevents the
+     * race where a parent-wake `dispatchInternalPrompt` collides with a fresh
+     * user prompt, which on macOS/Electron has triggered native SIGABRT crashes
+     * inside OpenCode's `@parcel/watcher` TSFN callback path. See issue #4120.
+     */
+    userMessageInProgressWindowMs: number;
+};
+export declare class ParentWakeNotifier {
+    private readonly deps;
+    private readonly options;
+    private pendingParentWakes;
+    private pendingParentWakeTimers;
+    private dispatchedParentWakes;
+    private dispatchedParentWakeTimers;
+    constructor(deps: ParentWakeNotifierDeps, options: ParentWakeNotifierOptions);
+    getPendingParentWakes(): Map<string, PendingParentWake>;
+    getPendingParentWakeTimers(): Map<string, ReturnType<typeof setTimeout>>;
+    getDispatchedParentWakes(): Map<string, PendingParentWake>;
+    getDispatchedParentWakeTimers(): Map<string, ReturnType<typeof setTimeout>>;
+    queuePendingParentWake(sessionID: string, notification: string, promptContext: ParentWakePromptContext, shouldReply: boolean, delayMs?: number): void;
+    flushPendingParentWake(sessionID: string): Promise<void>;
+    clearDispatchedParentWake(sessionID: string): void;
+    requeueDispatchedParentWake(sessionID: string, reason: string): Promise<boolean>;
+    schedulePendingParentWakeFlush(sessionID: string, delayMs?: number): void;
+    clearPendingParentWakeTimer(sessionID: string): void;
+    shutdown(): void;
+    private isSessionActive;
+    private resolveParentWakePromptContext;
+    private cloneParentWake;
+    private trackDispatchedParentWake;
+    private loadParentWakeSessionMessages;
+    private getParentWakeMessageRole;
+    private getParentWakeMessageFinish;
+    private getParentWakeMessageCreatedAt;
+    private parentWakePartIsWaitingOnTool;
+    private latestAssistantTurnIsWaitingOnTools;
+    private parentWakeMessageHasOutput;
+    private parentWakeMessageContainsNotification;
+    private isUserMessageInProgress;
+    private shouldDeferParentWakeForSessionHistory;
+    private hasAcceptedMessageAfterDispatchedParentWake;
+    private requeueWake;
+}
+export {};

package/dist/features/background-agent/process-cleanup.d.ts

@@ -2,6 +2,8 @@
 export declare function __disableScheduledForcedExitForTesting(): void;
 /** @internal test-only */
 export declare function __enableScheduledForcedExitForTesting(): void;
+/** @internal test-only seam: exposes the error normalizer used by registerErrorEvent. */
+export declare function describeProcessCleanupError(error: unknown): Record<string, unknown>;
 interface CleanupTarget {
     shutdown(): void | Promise<void>;
 }

package/dist/features/background-agent/session-route.d.ts

@@ -0,0 +1,12 @@
+import type { PluginInput } from "@opencode-ai/plugin";
+import { promptWithModelSuggestionRetry } from "../../shared";
+type OpencodeClient = PluginInput["client"];
+type PromptAsyncArgs = Parameters<OpencodeClient["session"]["promptAsync"]>[0];
+type PromptRetryClient = Parameters<typeof promptWithModelSuggestionRetry>[0];
+type PromptRetryArgs = Parameters<typeof promptWithModelSuggestionRetry>[1];
+type SessionMessagesArgs = Parameters<OpencodeClient["session"]["messages"]>[0];
+export declare function routeSessionPrompt(args: PromptAsyncArgs, directory: string): PromptAsyncArgs;
+export declare function promptAsyncInDirectory(client: OpencodeClient, args: PromptAsyncArgs, directory: string): Promise<unknown>;
+export declare function promptWithRetryInDirectory(client: PromptRetryClient, args: PromptRetryArgs, directory: string): Promise<void>;
+export declare function messagesInDirectory(client: OpencodeClient, args: SessionMessagesArgs, directory: string): Promise<unknown>;
+export {};

package/dist/features/background-agent/spawner.d.ts

@@ -1,6 +1,6 @@
-import type { BackgroundTask, LaunchInput, ResumeInput } from "./types";
-import type { OpencodeClient, OnSubagentSessionCreated, QueueItem } from "./constants";
 import type { ConcurrencyManager } from "./concurrency";
+import type { OnSubagentSessionCreated, OpencodeClient, QueueItem } from "./constants";
+import type { BackgroundTask, LaunchInput, ResumeInput } from "./types";
 export declare const FALLBACK_AGENT = "general";
 export declare function isAgentNotFoundError(error: unknown): boolean;
 export declare function buildFallbackBody(originalBody: Record<string, unknown>, fallbackAgent: string, options?: {

package/dist/features/background-agent/task-registry.d.ts

@@ -0,0 +1,6 @@
+import type { BackgroundTask } from "./types";
+export declare function rememberBackgroundTask(task: BackgroundTask): void;
+export declare function archiveBackgroundTask(task: BackgroundTask): void;
+export declare function getRegisteredBackgroundTask(taskID: string): BackgroundTask | undefined;
+export declare function forgetBackgroundTask(taskID: string): void;
+export declare function clearBackgroundTaskRegistryForTesting(): void;

package/dist/features/background-agent/types.d.ts

@@ -64,6 +64,8 @@ export interface BackgroundTask {
     parentAgent?: string;
     /** Parent session's tool restrictions for notification prompts */
     parentTools?: Record<string, boolean>;
+    skillContent?: string;
+    sessionPermission?: SessionPermissionRule[];
     /** Marks if the task was launched from an unstable agent/category */
     isUnstableAgent?: boolean;
     /** Category used for this task (e.g., 'quick', 'visual-engineering') */

package/dist/features/boulder-state/constants.d.ts

@@ -1,10 +1,10 @@
 /**
  * Boulder State Constants
  */
-export declare const BOULDER_DIR = ".sisyphus";
+export declare const BOULDER_DIR = ".omo";
 export declare const BOULDER_FILE = "boulder.json";
-export declare const BOULDER_STATE_PATH = ".sisyphus/boulder.json";
+export declare const BOULDER_STATE_PATH = ".omo/boulder.json";
 export declare const NOTEPAD_DIR = "notepads";
-export declare const NOTEPAD_BASE_PATH = ".sisyphus/notepads";
+export declare const NOTEPAD_BASE_PATH = ".omo/notepads";
 /** Prometheus plan directory pattern */
-export declare const PROMETHEUS_PLANS_DIR = ".sisyphus/plans";
+export declare const PROMETHEUS_PLANS_DIR = ".omo/plans";

package/dist/features/boulder-state/storage.d.ts

@@ -21,7 +21,7 @@ export declare function upsertTaskSessionState(directory: string, input: {
 }): BoulderState | null;
 /**
  * Find Prometheus plan files for this project.
- * Prometheus stores plans at: {project}/.sisyphus/plans/{name}.md
+ * Prometheus stores plans at: {project}/.omo/plans/{name}.md
  */
 export declare function findPrometheusPlans(directory: string): string[];
 /**

package/dist/features/builtin-commands/templates/init-deep.d.ts

@@ -1 +1 @@
-export declare const INIT_DEEP_TEMPLATE = "# /init-deep\n\nGenerate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.\n\n## Usage\n\n```\n/init-deep                      # Update mode: modify existing + create new where warranted\n/init-deep --create-new         # Read existing \u2192 remove all \u2192 regenerate from scratch\n/init-deep --max-depth=2        # Limit directory depth (default: 3)\n```\n\n---\n\n## Workflow (High-Level)\n\n1. **Discovery + Analysis** (concurrent)\n   - Fire background explore agents immediately\n   - Main session: bash structure + LSP codemap + read existing AGENTS.md\n2. **Score & Decide** - Determine AGENTS.md locations from merged findings\n3. **Generate** - Root first, then subdirs in parallel\n4. **Review** - Deduplicate, trim, validate\n\n<critical>\n**TodoWrite ALL phases. Mark in_progress \u2192 completed in real-time.**\n```\nTodoWrite([\n  { id: \"discovery\", content: \"Fire explore agents + LSP codemap + read existing\", status: \"pending\", priority: \"high\" },\n  { id: \"scoring\", content: \"Score directories, determine locations\", status: \"pending\", priority: \"high\" },\n  { id: \"generate\", content: \"Generate AGENTS.md files (root + subdirs)\", status: \"pending\", priority: \"high\" },\n  { id: \"review\", content: \"Deduplicate, validate, trim\", status: \"pending\", priority: \"medium\" }\n])\n```\n</critical>\n\n---\n\n## Phase 1: Discovery + Analysis (Concurrent)\n\n**Mark \"discovery\" as in_progress.**\n\n### Fire Background Explore Agents IMMEDIATELY\n\nDon't wait-these run async while main session works.\n\n```\n// Fire all at once, collect results later\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore project structure\", run_in_background=true, prompt=\"Project structure: PREDICT standard patterns for detected language \u2192 REPORT deviations only\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find entry points\", run_in_background=true, prompt=\"Entry points: FIND main files \u2192 REPORT non-standard organization\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find conventions\", run_in_background=true, prompt=\"Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) \u2192 REPORT project-specific rules\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find anti-patterns\", run_in_background=true, prompt=\"Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments \u2192 LIST forbidden patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore build/CI\", run_in_background=true, prompt=\"Build/CI: FIND .github/workflows, Makefile \u2192 REPORT non-standard patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find test patterns\", run_in_background=true, prompt=\"Test patterns: FIND test configs, test structure \u2192 REPORT unique conventions\")\n```\n\n<dynamic-agents>\n**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:\n\n| Factor | Threshold | Additional Agents |\n|--------|-----------|-------------------|\n| **Total files** | >100 | +1 per 100 files |\n| **Total lines** | >10k | +1 per 10k lines |\n| **Directory depth** | \u22654 | +2 for deep exploration |\n| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |\n| **Monorepo** | detected | +1 per package/workspace |\n| **Multiple languages** | >1 | +1 per language |\n\n```bash\n# Measure project scale first\ntotal_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)\ntotal_lines=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" -o -name \"*.go\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')\nlarge_files=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')\nmax_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)\n```\n\nExample spawning:\n```\n// 500 files, 50k lines, depth 6, 15 large files \u2192 spawn 5+5+2+1 = 13 additional agents\ntask(subagent_type=\"explore\", load_skills=[], description=\"Analyze large files\", run_in_background=true, prompt=\"Large file analysis: FIND files >500 lines, REPORT complexity hotspots\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore deep modules\", run_in_background=true, prompt=\"Deep modules at depth 4+: FIND hidden patterns, internal conventions\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find shared utilities\", run_in_background=true, prompt=\"Cross-cutting concerns: FIND shared utilities across directories\")\n// ... more based on calculation\n```\n</dynamic-agents>\n\n### Main Session: Concurrent Analysis\n\n**While background agents run**, main session does:\n\n#### 1. Bash Structural Analysis\n```bash\n# Directory depth + file counts\nfind . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c\n\n# Files per directory (top 30)\nfind . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30\n\n# Code concentration by extension\nfind . -type f \\( -name \"*.py\" -o -name \"*.ts\" -o -name \"*.tsx\" -o -name \"*.js\" -o -name \"*.go\" -o -name \"*.rs\" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20\n\n# Existing AGENTS.md / CLAUDE.md\nfind . -type f \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" \\) -not -path '*/node_modules/*' 2>/dev/null\n```\n\n#### 2. Read Existing AGENTS.md\n```\nFor each existing file found:\n  Read(filePath=file)\n  Extract: key insights, conventions, anti-patterns\n  Store in EXISTING_AGENTS map\n```\n\nIf `--create-new`: Read all existing first (preserve context) \u2192 then delete all \u2192 regenerate.\n\n#### 3. LSP Codemap (if available)\n```\nLspServers()  # Check availability\n\n# Entry points (parallel)\nLspDocumentSymbols(filePath=\"src/index.ts\")\nLspDocumentSymbols(filePath=\"main.py\")\n\n# Key symbols (parallel)\nLspWorkspaceSymbols(filePath=\".\", query=\"class\")\nLspWorkspaceSymbols(filePath=\".\", query=\"interface\")\nLspWorkspaceSymbols(filePath=\".\", query=\"function\")\n\n# Centrality for top exports\nLspFindReferences(filePath=\"...\", line=X, character=Y)\n```\n\n**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.\n\n### Collect Background Results\n\n```\n// After main session analysis done, collect all task results\nfor each task_id: background_output(task_id=\"...\")\n```\n\n**Merge: bash + LSP + existing + explore findings. Mark \"discovery\" as completed.**\n\n---\n\n## Phase 2: Scoring & Location Decision\n\n**Mark \"scoring\" as in_progress.**\n\n### Scoring Matrix\n\n| Factor | Weight | High Threshold | Source |\n|--------|--------|----------------|--------|\n| File count | 3x | >20 | bash |\n| Subdir count | 2x | >5 | bash |\n| Code ratio | 2x | >70% | bash |\n| Unique patterns | 1x | Has own config | explore |\n| Module boundary | 2x | Has index.ts/__init__.py | bash |\n| Symbol density | 2x | >30 symbols | LSP |\n| Export count | 2x | >10 exports | LSP |\n| Reference centrality | 3x | >20 refs | LSP |\n\n### Decision Rules\n\n| Score | Action |\n|-------|--------|\n| **Root (.)** | ALWAYS create |\n| **>15** | Create AGENTS.md |\n| **8-15** | Create if distinct domain |\n| **<8** | Skip (parent covers) |\n\n### Output\n```\nAGENTS_LOCATIONS = [\n  { path: \".\", type: \"root\" },\n  { path: \"src/hooks\", score: 18, reason: \"high complexity\" },\n  { path: \"src/api\", score: 12, reason: \"distinct domain\" }\n]\n```\n\n**Mark \"scoring\" as completed.**\n\n---\n\n## Phase 3: Generate AGENTS.md\n\n**Mark \"generate\" as in_progress.**\n\n<critical>\n**File Writing Rule**: If AGENTS.md already exists at the target path \u2192 use `Edit` tool. If it does NOT exist \u2192 use `Write` tool.\nNEVER use Write to overwrite an existing file. ALWAYS check existence first via `Read` or discovery results.\n</critical>\n\n### Root AGENTS.md (Full Treatment)\n\n```markdown\n# PROJECT KNOWLEDGE BASE\n\n**Generated:** {TIMESTAMP}\n**Commit:** {SHORT_SHA}\n**Branch:** {BRANCH}\n\n## OVERVIEW\n{1-2 sentences: what + core stack}\n\n## STRUCTURE\n\\`\\`\\`\n{root}/\n\u251C\u2500\u2500 {dir}/    # {non-obvious purpose only}\n\u2514\u2500\u2500 {entry}\n\\`\\`\\`\n\n## WHERE TO LOOK\n| Task | Location | Notes |\n|------|----------|-------|\n\n## CODE MAP\n{From LSP - skip if unavailable or project <10 files}\n\n| Symbol | Type | Location | Refs | Role |\n|--------|------|----------|------|------|\n\n## CONVENTIONS\n{ONLY deviations from standard}\n\n## ANTI-PATTERNS (THIS PROJECT)\n{Explicitly forbidden here}\n\n## UNIQUE STYLES\n{Project-specific}\n\n## COMMANDS\n\\`\\`\\`bash\n{dev/test/build}\n\\`\\`\\`\n\n## NOTES\n{Gotchas}\n```\n\n**Quality gates**: 50-150 lines, no generic advice, no obvious info.\n\n### Subdirectory AGENTS.md (Parallel)\n\nLaunch writing tasks for each location:\n\n```\nfor loc in AGENTS_LOCATIONS (except root):\n  task(category=\"writing\", load_skills=[], run_in_background=false, description=\"Generate AGENTS.md\", prompt=\\`\n    Generate AGENTS.md for: ${loc.path}\n    - Reason: ${loc.reason}\n    - 30-80 lines max\n    - NEVER repeat parent content\n    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS\n  \\`)\n```\n\n**Wait for all. Mark \"generate\" as completed.**\n\n---\n\n## Phase 4: Review & Deduplicate\n\n**Mark \"review\" as in_progress.**\n\nFor each generated file:\n- Remove generic advice\n- Remove parent duplicates\n- Trim to size limits\n- Verify telegraphic style\n\n**Mark \"review\" as completed.**\n\n---\n\n## Final Report\n\n```\n=== init-deep Complete ===\n\nMode: {update | create-new}\n\nFiles:\n  [OK] ./AGENTS.md (root, {N} lines)\n  [OK] ./src/hooks/AGENTS.md ({N} lines)\n\nDirs Analyzed: {N}\nAGENTS.md Created: {N}\nAGENTS.md Updated: {N}\n\nHierarchy:\n  ./AGENTS.md\n  \u2514\u2500\u2500 src/hooks/AGENTS.md\n```\n\n---\n\n## Anti-Patterns\n\n- **Static agent count**: MUST vary agents based on project size/depth\n- **Sequential execution**: MUST parallel (explore + LSP concurrent)\n- **Ignoring existing**: ALWAYS read existing first, even with --create-new\n- **Over-documenting**: Not every dir needs AGENTS.md\n- **Redundancy**: Child never repeats parent\n- **Generic content**: Remove anything that applies to ALL projects\n- **Verbose style**: Telegraphic or die";
+export declare const INIT_DEEP_TEMPLATE = "# /init-deep\n\nGenerate hierarchical AGENTS.md files. Root + complexity-scored subdirectories.\n\n## Usage\n\n```\n/init-deep                      # Update mode: modify existing + create new where warranted\n/init-deep --create-new         # Read existing \u2192 remove all \u2192 regenerate from scratch\n/init-deep --max-depth=2        # Limit directory depth (default: 3)\n```\n\n---\n\n## Workflow (High-Level)\n\n1. **Discovery + Analysis** (concurrent)\n   - Fire background explore agents immediately\n   - Main session: bash structure + LSP codemap + read existing AGENTS.md\n2. **Score & Decide** - Determine AGENTS.md locations from merged findings\n3. **Generate** - Root first, then subdirs in parallel\n4. **Review** - Deduplicate, trim, validate\n\n<critical>\n**TodoWrite ALL phases. Mark in_progress \u2192 completed in real-time.**\n```\nTodoWrite([\n  { id: \"discovery\", content: \"Fire explore agents + LSP codemap + read existing\", status: \"pending\", priority: \"high\" },\n  { id: \"scoring\", content: \"Score directories, determine locations\", status: \"pending\", priority: \"high\" },\n  { id: \"generate\", content: \"Generate AGENTS.md files (root + subdirs)\", status: \"pending\", priority: \"high\" },\n  { id: \"review\", content: \"Deduplicate, validate, trim\", status: \"pending\", priority: \"medium\" }\n])\n```\n</critical>\n\n---\n\n## Phase 1: Discovery + Analysis (Concurrent)\n\n**Mark \"discovery\" as in_progress.**\n\n### Fire Background Explore Agents IMMEDIATELY\n\nDon't wait-these run async while main session works.\n\n```\n// Fire all at once, collect results later\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore project structure\", run_in_background=true, prompt=\"Project structure: PREDICT standard patterns for detected language \u2192 REPORT deviations only\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find entry points\", run_in_background=true, prompt=\"Entry points: FIND main files \u2192 REPORT non-standard organization\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find conventions\", run_in_background=true, prompt=\"Conventions: FIND config files (.eslintrc, pyproject.toml, .editorconfig) \u2192 REPORT project-specific rules\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find anti-patterns\", run_in_background=true, prompt=\"Anti-patterns: FIND 'DO NOT', 'NEVER', 'ALWAYS', 'DEPRECATED' comments \u2192 LIST forbidden patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore build/CI\", run_in_background=true, prompt=\"Build/CI: FIND .github/workflows, Makefile \u2192 REPORT non-standard patterns\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find test patterns\", run_in_background=true, prompt=\"Test patterns: FIND test configs, test structure \u2192 REPORT unique conventions\")\n```\n\n<dynamic-agents>\n**DYNAMIC AGENT SPAWNING**: After bash analysis, spawn ADDITIONAL explore agents based on project scale:\n\n| Factor | Threshold | Additional Agents |\n|--------|-----------|-------------------|\n| **Total files** | >100 | +1 per 100 files |\n| **Total lines** | >10k | +1 per 10k lines |\n| **Directory depth** | \u22654 | +2 for deep exploration |\n| **Large files (>500 lines)** | >10 files | +1 for complexity hotspots |\n| **Monorepo** | detected | +1 per package/workspace |\n| **Multiple languages** | >1 | +1 per language |\n\n```bash\n# Measure project scale first\ntotal_files=$(find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | wc -l)\ntotal_lines=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" -o -name \"*.go\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | tail -1 | awk '{print $1}')\nlarge_files=$(find . -type f \\( -name \"*.ts\" -o -name \"*.py\" \\) -not -path '*/node_modules/*' -exec wc -l {} + 2>/dev/null | awk '$1 > 500 {count++} END {print count+0}')\nmax_depth=$(find . -type d -not -path '*/node_modules/*' -not -path '*/.git/*' | awk -F/ '{print NF}' | sort -rn | head -1)\n```\n\nExample spawning:\n```\n// 500 files, 50k lines, depth 6, 15 large files \u2192 spawn 5+5+2+1 = 13 additional agents\ntask(subagent_type=\"explore\", load_skills=[], description=\"Analyze large files\", run_in_background=true, prompt=\"Large file analysis: FIND files >500 lines, REPORT complexity hotspots\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Explore deep modules\", run_in_background=true, prompt=\"Deep modules at depth 4+: FIND hidden patterns, internal conventions\")\ntask(subagent_type=\"explore\", load_skills=[], description=\"Find shared utilities\", run_in_background=true, prompt=\"Cross-cutting concerns: FIND shared utilities across directories\")\n// ... more based on calculation\n```\n</dynamic-agents>\n\n### Main Session: Concurrent Analysis\n\n**While background agents run**, main session does:\n\n#### 1. Bash Structural Analysis\n```bash\n# Directory depth + file counts\nfind . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c\n\n# Files per directory (top 30)\nfind . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30\n\n# Code concentration by extension\nfind . -type f \\( -name \"*.py\" -o -name \"*.ts\" -o -name \"*.tsx\" -o -name \"*.js\" -o -name \"*.go\" -o -name \"*.rs\" \\) -not -path '*/node_modules/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20\n\n# Existing AGENTS.md / CLAUDE.md\nfind . -type f \\( -name \"AGENTS.md\" -o -name \"CLAUDE.md\" \\) -not -path '*/node_modules/*' 2>/dev/null\n```\n\n#### 2. Read Existing AGENTS.md\n```\nFor each existing file found:\n  Read(filePath=file)\n  Extract: key insights, conventions, anti-patterns\n  Store in EXISTING_AGENTS map\n```\n\nIf `--create-new`: Read all existing first (preserve context) \u2192 then delete all \u2192 regenerate.\n\n#### 3. LSP Codemap (if available)\n```\nLspServers()  # Check availability\n\n# Entry points (parallel)\nLspDocumentSymbols(filePath=\"src/index.ts\")\nLspDocumentSymbols(filePath=\"main.py\")\n\n# Key symbols (parallel)\nLspWorkspaceSymbols(filePath=\".\", query=\"class\")\nLspWorkspaceSymbols(filePath=\".\", query=\"interface\")\nLspWorkspaceSymbols(filePath=\".\", query=\"function\")\n\n# Centrality for top exports\nLspFindReferences(filePath=\"...\", line=X, character=Y)\n```\n\n**LSP Fallback**: If unavailable, rely on explore agents + AST-grep.\n\n### Collect Background Results\n\n```\n// After main session analysis done, collect all task results\nfor each background task ID (`bg_...`): background_output(task_id=\"bg_...\")\n```\n\n**Merge: bash + LSP + existing + explore findings. Mark \"discovery\" as completed.**\n\n---\n\n## Phase 2: Scoring & Location Decision\n\n**Mark \"scoring\" as in_progress.**\n\n### Scoring Matrix\n\n| Factor | Weight | High Threshold | Source |\n|--------|--------|----------------|--------|\n| File count | 3x | >20 | bash |\n| Subdir count | 2x | >5 | bash |\n| Code ratio | 2x | >70% | bash |\n| Unique patterns | 1x | Has own config | explore |\n| Module boundary | 2x | Has index.ts/__init__.py | bash |\n| Symbol density | 2x | >30 symbols | LSP |\n| Export count | 2x | >10 exports | LSP |\n| Reference centrality | 3x | >20 refs | LSP |\n\n### Decision Rules\n\n| Score | Action |\n|-------|--------|\n| **Root (.)** | ALWAYS create |\n| **>15** | Create AGENTS.md |\n| **8-15** | Create if distinct domain |\n| **<8** | Skip (parent covers) |\n\n### Output\n```\nAGENTS_LOCATIONS = [\n  { path: \".\", type: \"root\" },\n  { path: \"src/hooks\", score: 18, reason: \"high complexity\" },\n  { path: \"src/api\", score: 12, reason: \"distinct domain\" }\n]\n```\n\n**Mark \"scoring\" as completed.**\n\n---\n\n## Phase 3: Generate AGENTS.md\n\n**Mark \"generate\" as in_progress.**\n\n<critical>\n**File Writing Rule**: If AGENTS.md already exists at the target path \u2192 use `Edit` tool. If it does NOT exist \u2192 use `Write` tool.\nNEVER use Write to overwrite an existing file. ALWAYS check existence first via `Read` or discovery results.\n</critical>\n\n### Root AGENTS.md (Full Treatment)\n\n```markdown\n# PROJECT KNOWLEDGE BASE\n\n**Generated:** {TIMESTAMP}\n**Commit:** {SHORT_SHA}\n**Branch:** {BRANCH}\n\n## OVERVIEW\n{1-2 sentences: what + core stack}\n\n## STRUCTURE\n\\`\\`\\`\n{root}/\n\u251C\u2500\u2500 {dir}/    # {non-obvious purpose only}\n\u2514\u2500\u2500 {entry}\n\\`\\`\\`\n\n## WHERE TO LOOK\n| Task | Location | Notes |\n|------|----------|-------|\n\n## CODE MAP\n{From LSP - skip if unavailable or project <10 files}\n\n| Symbol | Type | Location | Refs | Role |\n|--------|------|----------|------|------|\n\n## CONVENTIONS\n{ONLY deviations from standard}\n\n## ANTI-PATTERNS (THIS PROJECT)\n{Explicitly forbidden here}\n\n## UNIQUE STYLES\n{Project-specific}\n\n## COMMANDS\n\\`\\`\\`bash\n{dev/test/build}\n\\`\\`\\`\n\n## NOTES\n{Gotchas}\n```\n\n**Quality gates**: 50-150 lines, no generic advice, no obvious info.\n\n### Subdirectory AGENTS.md (Parallel)\n\nLaunch writing tasks for each location:\n\n```\nfor loc in AGENTS_LOCATIONS (except root):\n  task(category=\"writing\", load_skills=[], run_in_background=false, description=\"Generate AGENTS.md\", prompt=\\`\n    Generate AGENTS.md for: ${loc.path}\n    - Reason: ${loc.reason}\n    - 30-80 lines max\n    - NEVER repeat parent content\n    - Sections: OVERVIEW (1 line), STRUCTURE (if >5 subdirs), WHERE TO LOOK, CONVENTIONS (if different), ANTI-PATTERNS\n  \\`)\n```\n\n**Wait for all. Mark \"generate\" as completed.**\n\n---\n\n## Phase 4: Review & Deduplicate\n\n**Mark \"review\" as in_progress.**\n\nFor each generated file:\n- Remove generic advice\n- Remove parent duplicates\n- Trim to size limits\n- Verify telegraphic style\n\n**Mark \"review\" as completed.**\n\n---\n\n## Final Report\n\n```\n=== init-deep Complete ===\n\nMode: {update | create-new}\n\nFiles:\n  [OK] ./AGENTS.md (root, {N} lines)\n  [OK] ./src/hooks/AGENTS.md ({N} lines)\n\nDirs Analyzed: {N}\nAGENTS.md Created: {N}\nAGENTS.md Updated: {N}\n\nHierarchy:\n  ./AGENTS.md\n  \u2514\u2500\u2500 src/hooks/AGENTS.md\n```\n\n---\n\n## Anti-Patterns\n\n- **Static agent count**: MUST vary agents based on project size/depth\n- **Sequential execution**: MUST parallel (explore + LSP concurrent)\n- **Ignoring existing**: ALWAYS read existing first, even with --create-new\n- **Over-documenting**: Not every dir needs AGENTS.md\n- **Redundancy**: Child never repeats parent\n- **Generic content**: Remove anything that applies to ALL projects\n- **Verbose style**: Telegraphic or die";

package/dist/features/builtin-commands/templates/start-work.d.ts

@@ -1 +1 @@
-export declare const START_WORK_TEMPLATE = "You are starting a Sisyphus work session.\n\n## ARGUMENTS\n\n- `/start-work [plan-name] [--worktree <path>]`\n  - `plan-name` (optional): name or partial match of the plan to start\n  - `--worktree <path>` (optional): absolute path to an existing git worktree to work in\n    - If specified and valid: hook pre-sets worktree_path in boulder.json\n    - If specified but invalid: you must run `git worktree add <path> <branch>` first\n    - If omitted: work directly in the current project directory (no worktree)\n\n## WHAT TO DO\n\n1. **Find available plans**: Search for Prometheus-generated plan files at `.sisyphus/plans/`\n\n2. **Check for active boulder state**: Read `.sisyphus/boulder.json` if it exists\n\n3. **Decision logic**:\n   - If multiple active works are listed in your context:\n     - This means boulder.json has more than one work with status: `active` or `paused`\n     - Use the Question tool to ask the user which plan to resume\n     - Resume by running `/start-work {plan-name}` for the selected plan\n     - If the user says \"start a new plan\", continue with cold-start auto-selection logic\n   - If exactly one active work is listed and the user did not name a plan:\n     - Auto-resume that single active work\n   - If no active plan OR plan is complete:\n     - List available plan files\n     - If ONE plan: auto-select it\n     - If MULTIPLE plans: show list with timestamps, ask user to select\n\n4. **Worktree Setup** (ONLY when `--worktree` was explicitly specified and `worktree_path` not already set in boulder.json):\n   1. `git worktree list --porcelain` - see available worktrees\n   2. Create: `git worktree add <absolute-path> <branch-or-HEAD>`\n   3. Update boulder.json to add `\"worktree_path\": \"<absolute-path>\"`\n   4. All work happens inside that worktree directory\n\n5. **Create/Update boulder.json**:\n   ```json\n   {\n     \"active_plan\": \"/absolute/path/to/plan.md\",\n     \"started_at\": \"ISO_TIMESTAMP\",\n     \"session_ids\": [\"session_id_1\", \"session_id_2\"],\n     \"plan_name\": \"plan-name\",\n     \"worktree_path\": \"/absolute/path/to/git/worktree\"\n   }\n   ```\n\n6. **Read the plan file** and start executing tasks according to atlas workflow\n\n## OUTPUT FORMAT\n\nWhen listing plans for selection:\n```\nAvailable Work Plans\n\nCurrent Time: {ISO timestamp}\nSession ID: {current session id}\n\n1. [plan-name-1.md] - Modified: {date} - Progress: 3/10 tasks\n2. [plan-name-2.md] - Modified: {date} - Progress: 0/5 tasks\n\nWhich plan would you like to work on? (Enter number or plan name)\n```\n\nWhen resuming existing work:\n```\nResuming Work Session\n\nActive Plan: {plan-name}\nProgress: {completed}/{total} tasks\nSessions: {count} (appending current session)\nWorktree: {worktree_path}\n\nReading plan and continuing from last incomplete task...\n```\n\nWhen auto-selecting single plan:\n```\nStarting Work Session\n\nPlan: {plan-name}\nSession ID: {session_id}\nStarted: {timestamp}\nWorktree: {worktree_path}\n\nReading plan and beginning execution...\n```\n\n## CRITICAL\n\n- The session_id is injected by the hook - use it directly\n- Always update boulder.json BEFORE starting work\n- If worktree_path is set in boulder.json, all work happens inside that worktree directory\n- Read the FULL plan file before delegating any tasks\n- Follow atlas delegation protocols (7-section format)\n\n## TASK BREAKDOWN (MANDATORY)\n\nAfter reading the plan file, you MUST decompose every plan task into granular, implementation-level sub-steps and register ALL of them as task/todo items BEFORE starting any work.\n\n**How to break down**:\n- Each plan checkbox item (e.g., `- [ ] Add user authentication`) must be split into concrete, actionable sub-tasks\n- Sub-tasks should be specific enough that each one touches a clear set of files/functions\n- Include: file to modify, what to change, expected behavior, and how to verify\n- Do NOT leave any task vague - \"implement feature X\" is NOT acceptable; \"add validateToken() to src/auth/middleware.ts that checks JWT expiry and returns 401\" IS acceptable\n\n**Example breakdown**:\nPlan task: `- [ ] Add rate limiting to API`\n\u2192 Todo items:\n  1. Create `src/middleware/rate-limiter.ts` with sliding window algorithm (max 100 req/min per IP)\n  2. Add RateLimiter middleware to `src/app.ts` router chain, before auth middleware\n  3. Add rate limit headers (X-RateLimit-Limit, X-RateLimit-Remaining) to response in `rate-limiter.ts`\n  4. Add test: verify 429 response after exceeding limit in `src/middleware/rate-limiter.test.ts`\n  5. Add test: verify headers are present on normal responses\n\nRegister these as task/todo items so progress is tracked and visible throughout the session.\n\n## WORKTREE COMPLETION\n\nWhen working in a worktree (`worktree_path` is set in boulder.json) and ALL plan tasks are complete:\n1. Commit all remaining changes in the worktree\n2. **Sync .sisyphus state back**: Copy `.sisyphus/` from the worktree to the main repo before removal.\n   This is CRITICAL when `.sisyphus/` is gitignored - state written during worktree execution would otherwise be lost.\n   ```bash\n   cp -r <worktree-path>/.sisyphus/* <main-repo>/.sisyphus/ 2>/dev/null || true\n   ```\n3. Switch to the main working directory (the original repo, NOT the worktree)\n4. Merge the worktree branch into the current branch: `git merge <worktree-branch>`\n5. If merge succeeds, clean up: `git worktree remove <worktree-path>`\n6. Remove the boulder.json state\n\nThis is the DEFAULT behavior when `--worktree` was used. Skip merge only if the user explicitly instructs otherwise (e.g., asks to create a PR instead).";
+export declare const START_WORK_TEMPLATE = "You are starting a Sisyphus work session.\n\n## ARGUMENTS\n\n- `/start-work [plan-name] [--worktree <path>]`\n  - `plan-name` (optional): name or partial match of the plan to start\n  - `--worktree <path>` (optional): absolute path to an existing git worktree to work in\n    - If specified and valid: hook pre-sets worktree_path in boulder.json\n    - If specified but invalid: you must run `git worktree add <path> <branch>` first\n    - If omitted: work directly in the current project directory (no worktree)\n\n## WHAT TO DO\n\n1. **Find available plans**: Search for Prometheus-generated plan files at `.omo/plans/`\n\n2. **Check for active boulder state**: Read `.omo/boulder.json` if it exists\n\n3. **Decision logic**:\n   - If multiple active works are listed in your context:\n     - This means boulder.json has more than one work with status: `active` or `paused`\n     - Use the Question tool to ask the user which plan to resume\n     - Resume by running `/start-work {plan-name}` for the selected plan\n     - If the user says \"start a new plan\", continue with cold-start auto-selection logic\n   - If exactly one active work is listed and the user did not name a plan:\n     - Auto-resume that single active work\n   - If no active plan OR plan is complete:\n     - List available plan files\n     - If ONE plan: auto-select it\n     - If MULTIPLE plans: show list with timestamps, ask user to select\n\n4. **Worktree Setup** (ONLY when `--worktree` was explicitly specified and `worktree_path` not already set in boulder.json):\n   1. `git worktree list --porcelain` - see available worktrees\n   2. Create: `git worktree add <absolute-path> <branch-or-HEAD>`\n   3. Update boulder.json to add `\"worktree_path\": \"<absolute-path>\"`\n   4. All work happens inside that worktree directory\n\n5. **Create/Update boulder.json**:\n   ```json\n   {\n     \"active_plan\": \"/absolute/path/to/plan.md\",\n     \"started_at\": \"ISO_TIMESTAMP\",\n     \"session_ids\": [\"session_id_1\", \"session_id_2\"],\n     \"plan_name\": \"plan-name\",\n     \"worktree_path\": \"/absolute/path/to/git/worktree\"\n   }\n   ```\n\n6. **Read the plan file** and start executing tasks according to atlas workflow\n\n## OUTPUT FORMAT\n\nWhen listing plans for selection:\n```\nAvailable Work Plans\n\nCurrent Time: {ISO timestamp}\nSession ID: {current session id}\n\n1. [plan-name-1.md] - Modified: {date} - Progress: 3/10 tasks\n2. [plan-name-2.md] - Modified: {date} - Progress: 0/5 tasks\n\nWhich plan would you like to work on? (Enter number or plan name)\n```\n\nWhen resuming existing work:\n```\nResuming Work Session\n\nActive Plan: {plan-name}\nProgress: {completed}/{total} tasks\nSessions: {count} (appending current session)\nWorktree: {worktree_path}\n\nReading plan and continuing from last incomplete task...\n```\n\nWhen auto-selecting single plan:\n```\nStarting Work Session\n\nPlan: {plan-name}\nSession ID: {session_id}\nStarted: {timestamp}\nWorktree: {worktree_path}\n\nReading plan and beginning execution...\n```\n\n## CRITICAL\n\n- The session_id is injected by the hook - use it directly\n- Always update boulder.json BEFORE starting work\n- If worktree_path is set in boulder.json, all work happens inside that worktree directory\n- Read the FULL plan file before delegating any tasks\n- Follow atlas delegation protocols (7-section format)\n\n## TASK BREAKDOWN (MANDATORY)\n\nAfter reading the plan file, you MUST decompose every plan task into granular, implementation-level sub-steps and register ALL of them as task/todo items BEFORE starting any work.\n\n**How to break down**:\n- Each plan checkbox item (e.g., `- [ ] Add user authentication`) must be split into concrete, actionable sub-tasks\n- Sub-tasks should be specific enough that each one touches a clear set of files/functions\n- Include: file to modify, what to change, expected behavior, and how to verify\n- Do NOT leave any task vague - \"implement feature X\" is NOT acceptable; \"add validateToken() to src/auth/middleware.ts that checks JWT expiry and returns 401\" IS acceptable\n\n**Example breakdown**:\nPlan task: `- [ ] Add rate limiting to API`\n\u2192 Todo items:\n  1. Create `src/middleware/rate-limiter.ts` with sliding window algorithm (max 100 req/min per IP)\n  2. Add RateLimiter middleware to `src/app.ts` router chain, before auth middleware\n  3. Add rate limit headers (X-RateLimit-Limit, X-RateLimit-Remaining) to response in `rate-limiter.ts`\n  4. Add test: verify 429 response after exceeding limit in `src/middleware/rate-limiter.test.ts`\n  5. Add test: verify headers are present on normal responses\n\nRegister these as task/todo items so progress is tracked and visible throughout the session.\n\n## WORKTREE COMPLETION\n\nWhen working in a worktree (`worktree_path` is set in boulder.json) and ALL plan tasks are complete:\n1. Commit all remaining changes in the worktree\n2. **Sync .omo state back**: Copy `.omo/` from the worktree to the main repo before removal.\n   This is CRITICAL when `.omo/` is gitignored - state written during worktree execution would otherwise be lost.\n   ```bash\n   cp -r <worktree-path>/.omo/* <main-repo>/.omo/ 2>/dev/null || true\n   ```\n3. Switch to the main working directory (the original repo, NOT the worktree)\n4. Merge the worktree branch into the current branch: `git merge <worktree-branch>`\n5. If merge succeeds, clean up: `git worktree remove <worktree-path>`\n6. Remove the boulder.json state\n\nThis is the DEFAULT behavior when `--worktree` was used. Skip merge only if the user explicitly instructs otherwise (e.g., asks to create a PR instead).";

package/dist/features/context-injector/injector.d.ts

@@ -1,5 +1,5 @@
-import type { ContextCollector } from "./collector";
 import type { Message, Part } from "@opencode-ai/sdk";
+import type { ContextCollector } from "./collector";
 interface OutputPart {
     type: string;
     text?: string;

package/dist/features/opencode-skill-loader/git-master-template-injection.d.ts

@@ -1,2 +1,20 @@
 import { type GitMasterConfig } from "../../config/schema";
+import { type ShellType } from "../../shared/shell-env";
+/**
+ * Parse a bash-format env prefix string ("VAR=value VAR2=value2") into a Record.
+ * Only handles simple KEY=VALUE pairs (no quoting needed since assertValidGitEnvPrefix
+ * already validates the format is shell-safe alphanumeric assignments).
+ */
+export declare function parseBashEnvPrefix(prefix: string): Record<string, string>;
+/**
+ * Build the shell-aware command prefix for git commands.
+ * Uses the shared shell detection and env prefix builder to emit correct syntax
+ * for PowerShell ($env:VAR='value';), cmd (set VAR="value" &&),
+ * csh (setenv VAR value;), or unix (VAR=value).
+ *
+ * For unix shells, we use the inline VAR=value prefix style (not export) to match
+ * the original behavior where the env var applies only to the immediately following command.
+ * For csh/tcsh, we use setenv syntax since csh does not support inline VAR=value.
+ */
+export declare function buildShellAwareGitPrefix(bashPrefix: string, shellType?: ShellType): string;
 export declare function injectGitMasterConfig(template: string, config?: GitMasterConfig): string;

package/dist/features/run-continuation-state/constants.d.ts

@@ -1 +1 @@
-export declare const CONTINUATION_MARKER_DIR = ".sisyphus/run-continuation";
+export declare const CONTINUATION_MARKER_DIR = ".omo/run-continuation";

package/dist/features/team-mode/team-layout-tmux/resolve-caller-tmux-session.d.ts

@@ -1,7 +1,9 @@
+import type { TmuxCommandResult } from "../../../shared/tmux";
 type ResolvedCallerTmuxSession = {
     sessionId: string;
     paneId: string;
     windowTarget: string;
 };
-export declare function resolveCallerTmuxSession(tmuxPath: string): Promise<ResolvedCallerTmuxSession | null>;
+type RunTmuxCommand = (tmuxPath: string, args: string[]) => Promise<TmuxCommandResult>;
+export declare function resolveCallerTmuxSession(tmuxPath: string, callerPaneId?: string | undefined, runCommand?: RunTmuxCommand): Promise<ResolvedCallerTmuxSession | null>;
 export {};

package/dist/features/team-mode/tools/lifecycle-test-fixture.d.ts

@@ -13,7 +13,7 @@ export declare const createTeamRunMock: import("bun:test").Mock<(spec: TeamSpec,
     teamName: string;
     specSource: "user" | "project";
     createdAt: number;
-    status: "deleted" | "failed" | "active" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
+    status: "active" | "failed" | "deleted" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
     members: {
         name: string;
         agentType: "leader" | "general-purpose";
@@ -108,7 +108,7 @@ export declare const loadTeamSpecMock: import("bun:test").Mock<() => Promise<{
 export declare const listActiveTeamsMock: import("bun:test").Mock<() => Promise<{
     teamRunId: string;
     teamName: string;
-    status: "deleted" | "failed" | "active" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
+    status: "active" | "failed" | "deleted" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
     memberCount: number;
     scope: "user" | "project";
 }[]>>;
@@ -118,7 +118,7 @@ export declare const loadRuntimeStateMock: import("bun:test").Mock<(teamRunId: s
     teamName: string;
     specSource: "user" | "project";
     createdAt: number;
-    status: "deleted" | "failed" | "active" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
+    status: "active" | "failed" | "deleted" | "creating" | "shutdown_requested" | "deleting" | "orphaned";
     members: {
         name: string;
         agentType: "leader" | "general-purpose";

package/dist/features/team-mode/tools/messaging.d.ts

@@ -23,6 +23,7 @@ export type LiveDeliveryClient = {
                 directory: string;
             };
         }): Promise<unknown>;
+        status?: () => Promise<unknown>;
     };
 };
 export type TeamSendMessageToolDeps = {

package/dist/features/team-mode/types.d.ts

@@ -255,9 +255,9 @@ export declare const RuntimeStateSchema: z.ZodObject<{
     }>;
     createdAt: z.ZodNumber;
     status: z.ZodEnum<{
-        deleted: "deleted";
-        failed: "failed";
         active: "active";
+        failed: "failed";
+        deleted: "deleted";
         creating: "creating";
         shutdown_requested: "shutdown_requested";
         deleting: "deleting";

package/dist/features/tmux-subagent/attachable-session-status.d.ts

@@ -1,4 +1,4 @@
-declare const ATTACHABLE_SESSION_STATUSES: readonly ["idle", "running"];
+declare const ATTACHABLE_SESSION_STATUSES: readonly ["idle", "running", "busy"];
 export type AttachableSessionStatus = (typeof ATTACHABLE_SESSION_STATUSES)[number];
 export declare function isAttachableSessionStatus(status: string | undefined): status is AttachableSessionStatus;
 export {};

package/dist/features/tmux-subagent/manager.d.ts

@@ -2,6 +2,7 @@ import type { PluginInput } from "@opencode-ai/plugin";
 import type { TmuxConfig } from "../../config/schema";
 import type { WindowState } from "./types";
 import * as sharedModule from "../../shared";
+import { executeActions, executeAction } from "./action-executor";
 type OpencodeClient = PluginInput["client"];
 interface SessionCreatedEvent {
     type: string;
@@ -21,6 +22,8 @@ export interface TmuxUtilDeps {
         client: OpencodeClient;
         sessionId: string;
     }) => Promise<boolean>;
+    executeActions: typeof executeActions;
+    executeAction: typeof executeAction;
     log: typeof sharedModule.log;
 }
 export declare class TmuxSessionManager {
@@ -47,6 +50,7 @@ export declare class TmuxSessionManager {
     private isolatedContainerNullStateCount;
     private staleSweepCompleted;
     private staleSweepInProgress;
+    private isolatedSessionManagerId;
     constructor(ctx: PluginInput, tmuxConfig: TmuxConfig, deps?: Partial<TmuxUtilDeps>);
     private isEnabled;
     private isIsolated;
@@ -61,8 +65,10 @@ export declare class TmuxSessionManager {
     private cleanupIsolatedContainerAfterSessionDeletion;
     private markSessionClosePending;
     private queryWindowStateSafely;
+    private activateTrackedSessionPane;
     private windowStateContainsPane;
     private finalizeForceRemoveCandidate;
+    private canAutoActivatePane;
     private closeTrackedSessionPane;
     private finalizeTrackedSessionClose;
     private closeTrackedSession;

package/dist/features/tmux-subagent/pane-state-parser.d.ts

@@ -2,6 +2,8 @@ import type { TmuxPaneInfo } from "./types";
 type ParsedPaneState = {
     windowWidth: number;
     windowHeight: number;
+    windowActive: boolean;
+    sessionAttached: boolean;
     panes: TmuxPaneInfo[];
 };
 export declare function parsePaneStateOutput(stdout: string): ParsedPaneState | null;

package/dist/features/tmux-subagent/polling-manager.d.ts

@@ -1,13 +1,16 @@
 import type { OpencodeClient } from "../../tools/delegate-task/types";
-import type { TrackedSession } from "./types";
+import type { TrackedSession, WindowState } from "./types";
 export declare class TmuxPollingManager {
     private client;
     private sessions;
     private closeSessionById;
     private retryPendingCloses?;
+    private getWindowState?;
+    private activateSessionPane?;
+    private canActivatePane;
     private pollInterval?;
     private pollingInFlight;
-    constructor(client: OpencodeClient, sessions: Map<string, TrackedSession>, closeSessionById: (sessionId: string) => Promise<void>, retryPendingCloses?: (() => Promise<void>) | undefined);
+    constructor(client: OpencodeClient, sessions: Map<string, TrackedSession>, closeSessionById: (sessionId: string) => Promise<void>, retryPendingCloses?: (() => Promise<void>) | undefined, getWindowState?: (() => Promise<WindowState | null>) | undefined, activateSessionPane?: ((tracked: TrackedSession) => Promise<boolean>) | undefined, canActivatePane?: (state: WindowState) => boolean);
     handleEvent(event: {
         type: string;
         properties?: Record<string, unknown>;
@@ -16,4 +19,5 @@ export declare class TmuxPollingManager {
     stopPolling(): void;
     private pollSessions;
     private getEventSessionId;
+    private activateFocusedPanes;
 }

package/dist/features/tmux-subagent/types.d.ts

@@ -2,6 +2,8 @@ export interface TrackedSession {
     sessionId: string;
     paneId: string;
     description: string;
+    attachActivated: boolean;
+    attachActivatedAt?: Date;
     createdAt: Date;
     lastSeenAt: Date;
     closePending: boolean;
@@ -25,6 +27,8 @@ export interface TmuxPaneInfo {
 export interface WindowState {
     windowWidth: number;
     windowHeight: number;
+    windowActive?: boolean;
+    sessionAttached?: boolean;
     mainPane: TmuxPaneInfo | null;
     agentPanes: TmuxPaneInfo[];
 }