[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PESR1XDRQP3S0CATNEESDH":3,"skill-same:01M6PESR1XDRQP3S0CATNEESDH":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6PESR1XDRQP3S0CATNEESDH","omp-plan",null,"OMP-aware strategic planning with interview, direct, consensus, and review modes","r3dlex\u002Foh-my-githubcopilot","r3dlex","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F291373160?v=4","01M6PEFNGGBVB7SHAPWXFFX933","01M6PEFNMNKPP8K3C881MDS722",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fskills\u002Fomp-plan\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30],"plan","omp","omp plan","review","planning","direct","consensus","interview","false","strategic planning","strategic","with","modes","2026-11-10 10:12:30",false,"---\nname: omp-plan\ndescription: OMP-aware strategic planning with interview, direct, consensus, and review modes\ntrigger: \"plan:, \u002Fplan, \u002Fomp:plan, \u002Fomp-plan, --consensus\"\nautoinvoke: false\n---\n\n# Skill: OMP-Plan\n\n## Metadata\n\n| Field | Value |\n|-------|-------|\n| **ID** | `omp-plan` |\n| **Keywords** | `plan:`, `\u002Fplan`, `\u002Fomp:plan`, `\u002Fomp-plan`, `--consensus` |\n| **Tier** | Execution Mode |\n| **Source** | `src\u002Fskills\u002Fomp-plan.mts` |\n\n## Description\n\nStrategic planning mode with optional interview workflow. Supports four modes: Interview (broad requests), Direct (detailed requests), Consensus (iterative Planner\u002FArchitect\u002FCritic loop with RALPLAN-DR structured deliberation), and Review (Critic evaluation of an existing plan). Delays implementation until the plan is approved.\n\n## Interface\n\n```typescript\ninterface SkillInput {\n  trigger: string;\n  args: string[];\n}\n\ninterface SkillOutput {\n  status: \"ok\" | \"error\";\n  message: string;\n}\n\nexport async function activate(input: SkillInput): Promise\u003CSkillOutput>\nexport function deactivate(): void\n```\n\n## Implementation\n\nActivates the `plan` strategic planning mode by spawning `bin\u002Fomp.mjs plan [args]`. No persistent resources are maintained.\n\n---\n\n## Flags\n\n```\nomp-plan [--direct|--consensus|--review] [--interactive] [--deliberate] \u003Ctask description>\n```\n\n| Flag | Description |\n|------|-------------|\n| `--direct` | Skip interview, generate plan immediately |\n| `--consensus` | Run Planner → Architect → Critic loop (RALPLAN-DR) |\n| `--review` | Critic evaluation of an existing plan |\n| `--interactive` | Enable user prompts at draft review and final approval steps (consensus mode) |\n| `--deliberate` | Force deliberate RALPLAN-DR mode: adds pre-mortem + expanded test plan |\n\n---\n\n## Mode Selection\n\n| Mode | Trigger | Behavior |\n|------|---------|----------|\n| Interview | Default for broad requests | Interactive requirements gathering |\n| Direct | `--direct`, or detailed request | Skip interview, generate plan directly |\n| Consensus | `--consensus`, \"ralplan\" | Planner → Architect → Critic loop until agreement with RALPLAN-DR structured deliberation (short by default, `--deliberate` for high-risk); add `--interactive` for user prompts at draft and approval steps |\n| Review | `--review`, \"review this plan\" | Critic evaluation of existing plan |\n\n---\n\n## Interview Mode (broad\u002Fvague requests)\n\n1. **Classify the request**: Broad (vague verbs, no specific files, touches 3+ areas) triggers interview mode\n2. **Ask one focused question** using `AskUserQuestion` for preferences, scope, and constraints\n3. **Gather codebase facts first**: Before asking \"what patterns does your code use?\", explore the codebase to find out, then ask informed follow-up questions\n4. **Build on answers**: Each question builds on the previous answer\n5. **Consult Analyst** for hidden requirements, edge cases, and risks\n6. **Create plan** when the user signals readiness: \"create the plan\", \"I'm ready\", \"make it a work plan\"\n\n**Question Classification**:\n\n| Type | Examples | Action |\n|------|----------|--------|\n| Codebase Fact | \"What patterns exist?\", \"Where is X?\" | Explore first, do not ask user |\n| User Preference | \"Priority?\", \"Timeline?\" | Ask user via AskUserQuestion |\n| Scope Decision | \"Include feature Y?\" | Ask user |\n| Requirement | \"Performance constraints?\" | Ask user |\n\n---\n\n## Direct Mode (detailed requests)\n\n1. **Quick Analysis**: Optional brief Analyst consultation\n2. **Create plan**: Generate comprehensive work plan immediately\n3. **Review** (optional): Critic review if requested\n\n---\n\n## Consensus Mode (`--consensus` \u002F \"ralplan\")\n\n**RALPLAN-DR modes**: **Short** (default, bounded structure) and **Deliberate** (for `--deliberate` or explicit high-risk requests: auth\u002Fsecurity, data migration, destructive\u002Firreversible changes, production incident, compliance\u002FPII, public API breakage). Both modes keep the same Planner → Architect → Critic sequence and the same `AskUserQuestion` gates.\n\n**Consensus mode runs fully automated by default**; add `--interactive` to enable user prompts at draft review (step 2) and final approval (step 6).\n\n### Steps\n\n1. **Planner** creates initial plan and a compact **RALPLAN-DR summary** before any Architect review. The summary **MUST** include:\n   - **Principles** (3-5)\n   - **Decision Drivers** (top 3)\n   - **Viable Options** (>=2) with bounded pros\u002Fcons for each option\n   - If only one viable option remains, an explicit **invalidation rationale** for alternatives that were rejected\n   - In **deliberate mode**: a **pre-mortem** (3 failure scenarios) and an **expanded test plan** covering unit \u002F integration \u002F e2e \u002F observability\n\n2. **User feedback** *(--interactive only)*: If running with `--interactive`, **MUST** use `AskUserQuestion` to present the draft plan **plus the RALPLAN-DR Principles \u002F Decision Drivers \u002F Options summary** with these options:\n   - **Proceed to review** — send to Architect and Critic for evaluation\n   - **Request changes** — return to step 1 with user feedback incorporated\n   - **Skip review** — go directly to final approval (step 6)\n   If NOT running with `--interactive`, automatically proceed to review (step 3).\n\n3. **Architect** reviews for architectural soundness. Adopt the Architect role and review the plan for:\n   - Strongest steelman counterargument (antithesis) against the favored option\n   - At least one meaningful tradeoff tension\n   - A synthesis path when possible\n   - In deliberate mode: explicitly flag principle violations\n   \n   **Wait for this step to complete before proceeding to step 4. Do NOT run steps 3 and 4 in parallel.**\n\n   > Invoke the architect agent to review the plan. If using a sub-agent: \"Adopt the Architect role and review this plan for architectural soundness. Provide the strongest steelman antithesis against the favored option, at least one real tradeoff tension, and a synthesis path where possible.\"\n\n4. **Critic** evaluates against quality criteria. Run only after step 3 is complete.\n   - Verify principle-option consistency\n   - Fair alternative exploration\n   - Risk mitigation clarity\n   - Testable acceptance criteria\n   - Concrete verification steps\n   - In deliberate mode: **MUST** reject missing\u002Fweak pre-mortem or missing\u002Fweak expanded test plan\n\n   > Invoke the critic agent to evaluate the plan. If using a sub-agent: \"Adopt the Critic role and evaluate this plan. Verify principle-option consistency, fair alternative exploration, risk mitigation clarity, testable acceptance criteria, and concrete verification steps. Reject shallow alternatives, driver contradictions, vague risks, or weak verification.\"\n\n5. **Re-review loop** (max 5 iterations): If Critic rejects, execute this closed loop:\n   a. Collect all rejection feedback from Architect + Critic\n   b. Pass feedback to Planner to produce a revised plan\n   c. **Return to Step 3** — Architect reviews the revised plan\n   d. **Return to Step 4** — Critic evaluates the revised plan\n   e. Repeat until Critic approves OR max 5 iterations reached\n   f. If max iterations reached without approval, present the best version to user via `AskUserQuestion` with note that expert consensus was not reached\n\n6. **Apply improvements**: When reviewers approve with improvement suggestions, merge all accepted improvements into the plan file before proceeding. Final consensus output **MUST** include an **ADR** section with: Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups.\n   a. Collect all improvement suggestions from Architect and Critic responses\n   b. Deduplicate and categorize the suggestions\n   c. Update the plan file in `.omp\u002Fplans\u002F` with the accepted improvements\n   d. Note which improvements were applied in a brief changelog section at the end of the plan\n\n7. On Critic approval *(--interactive only)*: If running with `--interactive`, use `AskUserQuestion` to present the plan with these options:\n   - **Approve and implement via team** (Recommended) — proceed to implementation via `omp:team`\n   - **Approve and execute via ralph** — proceed to implementation via `omp:ralph`\n   - **Clear context and implement** — compact the context window first, then start fresh implementation via `omp:ralph` with the saved plan file\n   - **Request changes** — return to step 1 with user feedback\n   - **Reject** — discard the plan entirely\n   If NOT running with `--interactive`, output the final approved plan and stop. Do NOT auto-execute.\n\n8. *(--interactive only)* User chooses via the structured `AskUserQuestion` UI (never ask for approval in plain text).\n\n9. *(--interactive only)* On user approval:\n   - **Approve and implement via team**: Invoke `omp:team` with the approved plan path from `.omp\u002Fplans\u002F` as context. Do NOT implement directly.\n   - **Approve and execute via ralph**: Invoke `omp:ralph` with the approved plan path from `.omp\u002Fplans\u002F` as context. Do NOT implement directly.\n   - **Clear context and implement**: Compact the context window first, then invoke `omp:ralph` with the approved plan path.\n\n---\n\n## RALPLAN-DR Short Mode Workflow\n\nUsed by default in consensus mode. Bounded structure with four mandatory sections:\n\n1. **Principles** (3-5 guiding constraints for this decision)\n2. **Decision Drivers** (top 3 criteria that will determine the best option)\n3. **Viable Options** (>=2) — for each option:\n   - One-sentence description\n   - Pros (2-3 bullets)\n   - Cons (2-3 bullets)\n4. **Invalidation rationale** (if only one viable option remains after analysis)\n\n---\n\n## RALPLAN-DR Deliberate Mode Workflow\n\nEnabled with `--deliberate` or when the request explicitly signals high risk. Adds to the short mode:\n\n- **Pre-mortem**: 3 specific failure scenarios (what could go wrong, how to detect it)\n- **Expanded Test Plan**: unit \u002F integration \u002F e2e \u002F observability layers\n\n---\n\n## Review Mode (`--review`)\n\n1. Read plan file from `.omp\u002Fplans\u002F`\n2. Adopt the Critic role to evaluate the plan (or invoke critic agent)\n3. Return verdict: APPROVED, REVISE (with specific feedback), or REJECT (replanning required)\n\n---\n\n## Plan Output Format\n\nEvery plan includes:\n- Requirements Summary\n- Acceptance Criteria (testable, 90%+ concrete)\n- Implementation Steps (with file references, 80%+ claims cite file\u002Fline)\n- Risks and Mitigations\n- Verification Steps\n- For consensus\u002Fralplan: **RALPLAN-DR summary** (Principles, Decision Drivers, Options)\n- For consensus\u002Fralplan final output: **ADR** (Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups)\n- For deliberate consensus mode: **Pre-mortem (3 scenarios)** and **Expanded Test Plan** (unit\u002Fintegration\u002Fe2e\u002Fobservability)\n\nPlans are saved to `.omp\u002Fplans\u002F`. Drafts go to `.omp\u002Fdrafts\u002F`.\n\n---\n\n## Execution Policy\n\n- Auto-detect interview vs direct mode based on request specificity\n- Ask one question at a time during interviews — never batch multiple questions\n- Gather codebase facts via exploration before asking the user about them\n- Plans must meet quality standards: 80%+ claims cite file\u002Fline, 90%+ criteria are testable\n- Consensus mode runs fully automated by default; add `--interactive` to enable user prompts\n- Consensus mode uses RALPLAN-DR short mode by default; switch to deliberate mode with `--deliberate` or when the request signals high risk\n\n---\n\n## Final Checklist\n\n- [ ] Plan has testable acceptance criteria (90%+ concrete)\n- [ ] Plan references specific files\u002Flines where applicable (80%+ claims)\n- [ ] All risks have mitigations identified\n- [ ] No vague terms without metrics (\"fast\" → \"p99 \u003C 200ms\")\n- [ ] Plan saved to `.omp\u002Fplans\u002F`\n- [ ] In consensus mode: RALPLAN-DR summary includes 3-5 principles, top 3 drivers, and >=2 viable options (or explicit invalidation rationale)\n- [ ] In consensus mode final output: ADR section included (Decision \u002F Drivers \u002F Alternatives considered \u002F Why chosen \u002F Consequences \u002F Follow-ups)\n- [ ] In deliberate consensus mode: pre-mortem (3 scenarios) + expanded test plan (unit\u002Fintegration\u002Fe2e\u002Fobservability) included\n- [ ] In consensus mode with `--interactive`: user explicitly approved before any execution; without `--interactive`: plan output only, no auto-execution\n- [ ] **CRITICAL — Consensus mode agent calls MUST be sequential, never parallel.** Always await Architect review before issuing the Critic evaluation.\n\n---\n\n## Escalation and Stop Conditions\n\n- Stop interviewing when requirements are clear enough to plan — do not over-interview\n- In consensus mode, stop after 5 Planner\u002FArchitect\u002FCritic iterations and present the best version\n- Consensus mode without `--interactive` outputs the final plan and stops; with `--interactive`, requires explicit user approval before any implementation begins\n- If the user says \"just do it\" or \"skip planning\", transition directly to `omp:ralph` for execution — do NOT implement directly in the planning agent\n- Escalate to the user when there are irreconcilable trade-offs that require a business decision\n","# Skill: OMP-Plan\n\n## Metadata\n\n| Field | Value |\n|-------|-------|\n| **ID** | `omp-plan` |\n| **Keywords** | `plan:`, `\u002Fplan`, `\u002Fomp:plan`, `\u002Fomp-plan`, `--consensus` |\n| **Tier** | Execution Mode |\n| **Source** | `src\u002Fskills\u002Fomp-plan.mts` |\n\n## Description\n\nStrategic planning mode with optional interview workflow. Supports four modes: Interview (broad requests), Direct (detailed requests), Consensus (iterative Planner\u002FArchitect\u002FCritic loop with RALPLAN-DR structured deliberation), and Review (Critic evaluation of an existing plan). Delays implementation until the plan is approved.\n\n## Interface\n\n```typescript\ninterface SkillInput {\n  trigger: string;\n  args: string[];\n}\n\ninterface SkillOutput {\n  status: \"ok\" | \"error\";\n  message: string;\n}\n\nexport async function activate(input: SkillInput): Promise\u003CSkillOutput>\nexport function deactivate(): void\n```\n\n## Implementation\n\nActivates the `plan` strategic planning mode by spawning `bin\u002Fomp.mjs plan [args]`. No persistent resources are maintained.\n\n---\n\n## Flags\n\n```\nomp-plan [--direct|--consensus|--review] [--interactive] [--deliberate] \u003Ctask description>\n```\n\n| Flag | Description |\n|------|-------------|\n| `--direct` | Skip interview, generate plan immediately |\n| `--consensus` | Run Planner → Architect → Critic loop (RALPLAN-DR) |\n| `--review` | Critic evaluation of an existing plan |\n| `--interactive` | Enable user prompts at draft review and final approval steps (consensus mode) |\n| `--deliberate` | Force deliberate RALPLAN-DR mode: adds pre-mortem + expanded test plan |\n\n---\n\n## Mode Selection\n\n| Mode | Trigger | Behavior |\n|------|---------|----------|\n| Interview | Default for broad requests | Interactive requirements gathering |\n| Direct | `--direct`, or detailed request | Skip interview, generate plan directly |\n| Consensus | `--consensus`, \"ralplan\" | Planner → Architect → Critic loop until agreement with RALPLAN-DR structured deliberation (short by default, `--deliberate` for high-risk); add `--interactive` for user prompts at draft and approval steps |\n| Review | `--review`, \"review this plan\" | Critic evaluation of existing plan |\n\n---\n\n## Interview Mode (broad\u002Fvague requests)\n\n1. **Classify the request**: Broad (vague verbs, no specific files, touches 3+ areas) triggers interview mode\n2. **Ask one focused question** using `AskUserQuestion` for preferences, scope, and constraints\n3. **Gather codebase facts first**: Before asking \"what patterns does your code use?\", explore the codebase to find out, then ask informed follow-up questions\n4. **Build on answers**: Each question builds on the previous answer\n5. **Consult Analyst** for hidden requirements, edge cases, and risks\n6. **Create plan** when the user signals readiness: \"create the plan\", \"I'm ready\", \"make it a work plan\"\n\n**Question Classification**:\n\n| Type | Examples | Action |\n|------|----------|--------|\n| Codebase Fact | \"What patterns exist?\", \"Where is X?\" | Explore first, do not ask user |\n| User Preference | \"Priority?\", \"Timeline?\" | Ask user via AskUserQuestion |\n| Scope Decision | \"Include feature Y?\" | Ask user |\n| Requirement | \"Performance constraints?\" | Ask user |\n\n---\n\n## Direct Mode (detailed requests)\n\n1. **Quick Analysis**: Optional brief Analyst consultation\n2. **Create plan**: Generate comprehensive work plan immediately\n3. **Review** (optional): Critic review if requested\n\n---\n\n## Consensus Mode (`--consensus` \u002F \"ralplan\")\n\n**RALPLAN-DR modes**: **Short** (default, bounded structure) and **Deliberate** (for `--deliberate` or explicit high-risk requests: auth\u002Fsecurity, data migration, destructive\u002Firreversible changes, production incident, compliance\u002FPII, public API breakage). Both modes keep the same Planner → Architect → Critic sequence and the same `AskUserQuestion` gates.\n\n**Consensus mode runs fully automated by default**; add `--interactive` to enable user prompts at draft review (step 2) and final approval (step 6).\n\n### Steps\n\n1. **Planner** creates initial plan and a compact **RALPLAN-DR summary** before any Architect review. The summary **MUST** include:\n   - **Principles** (3-5)\n   - **Decision Drivers** (top 3)\n   - **Viable Options** (>=2) with bounded pros\u002Fcons for each option\n   - If only one viable option remains, an explicit **invalidation rationale** for alternatives that were rejected\n   - In **deliberate mode**: a **pre-mortem** (3 failure scenarios) and an **expanded test plan** covering unit \u002F integration \u002F e2e \u002F observability\n\n2. **User feedback** *(--interactive only)*: If running with `--interactive`, **MUST** use `AskUserQuestion` to present the draft plan **plus the RALPLAN-DR Principles \u002F Decision Drivers \u002F Options summary** with these options:\n   - **Proceed to review** — send to Architect and Critic for evaluation\n   - **Request changes** — return to step 1 with user feedback incorporated\n   - **Skip review** — go directly to final approval (step 6)\n   If NOT running with `--interactive`, automatically proceed to review (step 3).\n\n3. **Architect** reviews for architectural soundness. Adopt the Architect role and review the plan for:\n   - Strongest steelman counterargument (antithesis) against the favored option\n   - At least one meaningful tradeoff tension\n   - A synthesis path when possible\n   - In deliberate mode: explicitly flag principle violations\n   \n   **Wait for this step to complete before proceeding to step 4. Do NOT run steps 3 and 4 in parallel.**\n\n   > Invoke the architect agent to review the plan. If using a sub-agent: \"Adopt the Architect role and review this plan for architectural soundness. Provide the strongest steelman antithesis against the favored option, at least one real tradeoff tension, and a synthesis path where possible.\"\n\n4. **Critic** evaluates against quality criteria. Run only after step 3 is complete.\n   - Verify principle-option consistency\n   - Fair alternative exploration\n   - Risk mitigation clarity\n   - Testable acceptance criteria\n   - Concrete verification steps\n   - In deliberate mode: **MUST** reject missing\u002Fweak pre-mortem or missing\u002Fweak expanded test plan\n\n   > Invoke the critic agent to evaluate the plan. If using a sub-agent: \"Adopt the Critic role and evaluate this plan. Verify principle-option consistency, fair alternative exploration, risk mitigation clarity, testable acceptance criteria, and concrete verification steps. Reject shallow alternatives, driver contradictions, vague risks, or weak verification.\"\n\n5. **Re-review loop** (max 5 iterations): If Critic rejects, execute this closed loop:\n   a. Collect all rejection feedback from Architect + Critic\n   b. Pass feedback to Planner to produce a revised plan\n   c. **Return to Step 3** — Architect reviews the revised plan\n   d. **Return to Step 4** — Critic evaluates the revised plan\n   e. Repeat until Critic approves OR max 5 iterations reached\n   f. If max iterations reached without approval, present the best version to user via `AskUserQuestion` with note that expert consensus was not reached\n\n6. **Apply improvements**: When reviewers approve with improvement suggestions, merge all accepted improvements into the plan file before proceeding. Final consensus output **MUST** include an **ADR** section with: Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups.\n   a. Collect all improvement suggestions from Architect and Critic responses\n   b. Deduplicate and categorize the suggestions\n   c. Update the plan file in `.omp\u002Fplans\u002F` with the accepted improvements\n   d. Note which improvements were applied in a brief changelog section at the end of the plan\n\n7. On Critic approval *(--interactive only)*: If running with `--interactive`, use `AskUserQuestion` to present the plan with these options:\n   - **Approve and implement via team** (Recommended) — proceed to implementation via `omp:team`\n   - **Approve and execute via ralph** — proceed to implementation via `omp:ralph`\n   - **Clear context and implement** — compact the context window first, then start fresh implementation via `omp:ralph` with the saved plan file\n   - **Request changes** — return to step 1 with user feedback\n   - **Reject** — discard the plan entirely\n   If NOT running with `--interactive`, output the final approved plan and stop. Do NOT auto-execute.\n\n8. *(--interactive only)* User chooses via the structured `AskUserQuestion` UI (never ask for approval in plain text).\n\n9. *(--interactive only)* On user approval:\n   - **Approve and implement via team**: Invoke `omp:team` with the approved plan path from `.omp\u002Fplans\u002F` as context. Do NOT implement directly.\n   - **Approve and execute via ralph**: Invoke `omp:ralph` with the approved plan path from `.omp\u002Fplans\u002F` as context. Do NOT implement directly.\n   - **Clear context and implement**: Compact the context window first, then invoke `omp:ralph` with the approved plan path.\n\n---\n\n## RALPLAN-DR Short Mode Workflow\n\nUsed by default in consensus mode. Bounded structure with four mandatory sections:\n\n1. **Principles** (3-5 guiding constraints for this decision)\n2. **Decision Drivers** (top 3 criteria that will determine the best option)\n3. **Viable Options** (>=2) — for each option:\n   - One-sentence description\n   - Pros (2-3 bullets)\n   - Cons (2-3 bullets)\n4. **Invalidation rationale** (if only one viable option remains after analysis)\n\n---\n\n## RALPLAN-DR Deliberate Mode Workflow\n\nEnabled with `--deliberate` or when the request explicitly signals high risk. Adds to the short mode:\n\n- **Pre-mortem**: 3 specific failure scenarios (what could go wrong, how to detect it)\n- **Expanded Test Plan**: unit \u002F integration \u002F e2e \u002F observability layers\n\n---\n\n## Review Mode (`--review`)\n\n1. Read plan file from `.omp\u002Fplans\u002F`\n2. Adopt the Critic role to evaluate the plan (or invoke critic agent)\n3. Return verdict: APPROVED, REVISE (with specific feedback), or REJECT (replanning required)\n\n---\n\n## Plan Output Format\n\nEvery plan includes:\n- Requirements Summary\n- Acceptance Criteria (testable, 90%+ concrete)\n- Implementation Steps (with file references, 80%+ claims cite file\u002Fline)\n- Risks and Mitigations\n- Verification Steps\n- For consensus\u002Fralplan: **RALPLAN-DR summary** (Principles, Decision Drivers, Options)\n- For consensus\u002Fralplan final output: **ADR** (Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups)\n- For deliberate consensus mode: **Pre-mortem (3 scenarios)** and **Expanded Test Plan** (unit\u002Fintegration\u002Fe2e\u002Fobservability)\n\nPlans are saved to `.omp\u002Fplans\u002F`. Drafts go to `.omp\u002Fdrafts\u002F`.\n\n---\n\n## Execution Policy\n\n- Auto-detect interview vs direct mode based on request specificity\n- Ask one question at a time during interviews — never batch multiple questions\n- Gather codebase facts via exploration before asking the user about them\n- Plans must meet quality standards: 80%+ claims cite file\u002Fline, 90%+ criteria are testable\n- Consensus mode runs fully automated by default; add `--interactive` to enable user prompts\n- Consensus mode uses RALPLAN-DR short mode by default; switch to deliberate mode with `--deliberate` or when the request signals high risk\n\n---\n\n## Final Checklist\n\n- [ ] Plan has testable acceptance criteria (90%+ concrete)\n- [ ] Plan references specific files\u002Flines where applicable (80%+ claims)\n- [ ] All risks have mitigations identified\n- [ ] No vague terms without metrics (\"fast\" → \"p99 \u003C 200ms\")\n- [ ] Plan saved to `.omp\u002Fplans\u002F`\n- [ ] In consensus mode: RALPLAN-DR summary includes 3-5 principles, top 3 drivers, and >=2 viable options (or explicit invalidation rationale)\n- [ ] In consensus mode final output: ADR section included (Decision \u002F Drivers \u002F Alternatives considered \u002F Why chosen \u002F Consequences \u002F Follow-ups)\n- [ ] In deliberate consensus mode: pre-mortem (3 scenarios) + expanded test plan (unit\u002Fintegration\u002Fe2e\u002Fobservability) included\n- [ ] In consensus mode with `--interactive`: user explicitly approved before any execution; without `--interactive`: plan output only, no auto-execution\n- [ ] **CRITICAL — Consensus mode agent calls MUST be sequential, never parallel.** Always await Architect review before issuing the Critic evaluation.\n\n---\n\n## Escalation and Stop Conditions\n\n- Stop interviewing when requirements are clear enough to plan — do not over-interview\n- In consensus mode, stop after 5 Planner\u002FArchitect\u002FCritic iterations and present the best version\n- Consensus mode without `--interactive` outputs the final plan and stops; with `--interactive`, requires explicit user approval before any implementation begins\n- If the user says \"just do it\" or \"skip planning\", transition directly to `omp:ralph` for execution — do NOT implement directly in the planning agent\n- Escalate to the user when there are irreconcilable trade-offs that require a business decision\n",{"name":5,"trigger":36,"autoinvoke":32,"description":7},"plan:, \u002Fplan, \u002Fomp:plan, \u002Fomp-plan, --consensus","main","55294682936bc69473eba70e93ffa88ede018e81","skills\u002Fomp-plan",0,"https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot","https:\u002F\u002Fgithub.com\u002Fr3dlex","2026-10-31 18:57:35",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add r3dlex\u002Foh-my-githubcopilot --skill omp-plan",{"tool":50,"command":51},"bunx","bunx skills add r3dlex\u002Foh-my-githubcopilot --skill omp-plan",{"tool":53,"command":54},"pnpm","pnpm dlx skills add r3dlex\u002Foh-my-githubcopilot --skill omp-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fskills\u002Fomp-plan\u002FSKILL.md",true,[],[59,65,71,77,83,91],{"skillNo":60,"name":61,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":31},"01M6PF2CTFS0AEXQXF2NFYT8J2","wiki","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Fwiki\u002FSKILL.md",[],[61],{"skillNo":66,"name":67,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":31},"01M6PF2BFXJ97M6NKH7N42XZVZ","ultrawork","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Fultrawork\u002FSKILL.md",[],[67],{"skillNo":72,"name":73,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":31},"01M6PF2A38Y1CE5BVJ5HMTMBP6","trace","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Ftrace\u002FSKILL.md",[],[73],{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":31},"01M6PF28P7S19AK5XJA41WS9V8","team","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Fteam\u002FSKILL.md",[],[79],{"skillNo":84,"name":85,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":31},"01M6PF278EADT8W3EWDYA3C2H0","swe-bench","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Fswe-bench\u002FSKILL.md",[],[89,90],"SWE","swe bench",{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":31},"01M6PF25XW1TMP5Z1N89ZVJQDY","swarm","https:\u002F\u002Fgithub.com\u002Fr3dlex\u002Foh-my-githubcopilot\u002Fblob\u002Fmain\u002Fvscode-omp\u002Fresources\u002Ftemplates\u002F.copilot\u002Fskills\u002Fswarm\u002FSKILL.md",[],[93]]