adom-plan — Exhaustive Plan Review

@@ -0,0 +1,54 @@+# adom-plan — Exhaustive Plan Review++End-to-end planning pipeline: expand a sketch into a detailed plan, then stress-test it via adversarial multi-model debate. Uses **ultraplan** when available (harness-level deep expansion), otherwise runs a built-in Opus expansion pass. Then launches **three adversarial pairs** (6 agents: Opus vs Sonnet per category) arguing architecture, implementation, and security from opposite dispositions. A 7th agent red-teams the consensus. Final output is a scored, vetted plan with validation strategies, E2E testing, risk register, and prioritized action items.++**Total agents: up to 8** (1 expansion + 6 debate + 1 red-team consensus).++## How it works++1. **Phase 0** — Locate the plan (plan file, file path argument, or conversation context)+2. **Phase 0.5** — Expand the plan via ultraplan (if available) or built-in Opus expansion agent+3. **Phase 1** — Fetch platform context (wiki catalog, installed skills, recent commits, existing plans)+4. **Phase 2** — Launch 6 adversarial debate agents in parallel (3 pairs):+   - Architecture: Opus advocate vs Sonnet challenger+   - Implementation: Sonnet optimist vs Opus pessimist+   - Security: Sonnet auditor vs Sonnet red-team attacker+5. **Phase 3** — Red-team the consensus with one final Opus agent+6. **Phase 4** — Scored synthesis with scorecard, contested decisions, risk register, E2E strategy, and action items+7. **Phase 5** — Present summary to user++## Key features++- **Adversarial pairing** — two agents argue each category from opposite dispositions, surfacing disagreements a single model would self-censor+- **Multi-model diversity** — Opus reasons conservatively and architecturally; Sonnet is pragmatic and detail-oriented+- **Structured scoring** — 1-5 scale across Feasibility, Maintainability, Platform Leverage, Simplicity; 2+ point deltas auto-flagged+- **Platform awareness** — fetches wiki catalog so agents reference real tools, not hypothetical ones+- **The 30-Day Failure Scenario** — forces concrete, actionable thinking about what will actually go wrong+- **Consensus red-team** — attacks the "safe" decisions everyone agrees on, because the most dangerous risks are the ones nobody flags++## Invocation++```+/adom-plan                          # review the active plan file+/adom-plan path/to/plan.md          # review a specific file+```++## Installation++Bundled with gallia. Available at `~/.claude/skills/adom-plan/` after `install.mjs` runs. The skill consists of two files:++- `SKILL.md` (212 lines) — workflow, phases, synthesis format, guidelines+- `debate-prompts.md` (413 lines) — all 8 agent prompt templates (read on demand during execution)++## Output++The skill appends a **Debate Review Summary** to the plan file containing:++- **Scorecard** — per-section grades (A/B/C/F) with dimensional scores+- **Consensus Decisions** — verified safe items+- **Contested Decisions** — where agents disagreed, with recommendations+- **Fragile Consensus** — items the red-team flagged+- **Risk Register** — consolidated threat table with mitigations+- **Validation & E2E Strategy** — complete test plan+- **The 30-Day Failure Scenario** — the most likely production failure+- **Action Items** — numbered list tagged BLOCKING / RECOMMENDED / NICE-TO-HAVE

@@ -0,0 +1,50 @@+{+  "schema_version": 1,+  "type": "skill",+  "slug": "adom-plan",+  "title": "adom-plan — Exhaustive Plan Review",+  "brief": "One-liner exhaustive planning: expand a sketch via ultraplan or built-in Opus expansion, then stress-test via 6 adversarial debate agents in 3 Opus/Sonnet pairs + red-team consensus attack. Produces s",+  "version": "1.0.0",+  "tags": [],+  "license": "MIT",+  "sample_prompts": [+    {+      "label": "Review plan",+      "prompt": "/adom-plan"+    },+    {+      "label": "Vet this plan",+      "prompt": "vet this plan"+    },+    {+      "label": "Review specific file",+      "prompt": "/adom-plan plans/my-feature.md"+    },+    {+      "label": "Stress-test",+      "prompt": "stress-test the plan"+    },+    {+      "label": "Harden",+      "prompt": "harden the plan"+    }+  ],+  "source_path": "SKILL.md",+  "readme": "# adom-plan — Exhaustive Plan Review\n\nEnd-to-end planning pipeline: expand a sketch into a detailed plan, then stress-test it via adversarial multi-model debate. Uses **ultraplan** when available (harness-level deep expansion), otherwise runs a built-in Opus expansion pass. Then launches **three adversarial pairs** (6 agents: Opus vs Sonnet per category) arguing architecture, implementation, and security from opposite dispositions. A 7th agent red-teams the consensus. Final output is a scored, vetted plan with validation strategies, E2E testing, risk register, and prioritized action items.\n\n**Total agents: up to 8** (1 expansion + 6 debate + 1 red-team consensus).\n\n## How it works\n\n1. **Phase 0** — Locate the plan (plan file, file path argument, or conversation context)\n2. **Phase 0.5** — Expand the plan via ultraplan (if available) or built-in Opus expansion agent\n3. **Phase 1** — Fetch platform context (wiki catalog, installed skills, recent commits, existing plans)\n4. **Phase 2** — Launch 6 adversarial debate agents in parallel (3 pairs):\n   - Architecture: Opus advocate vs Sonnet challenger\n   - Implementation: Sonnet optimist vs Opus pessimist\n   - Security: Sonnet auditor vs Sonnet red-team attacker\n5. **Phase 3** — Red-team the consensus with one final Opus agent\n6. **Phase 4** — Scored synthesis with scorecard, contested decisions, risk register, E2E strategy, and action items\n7. **Phase 5** — Present summary to user\n\n## Key features\n\n- **Adversarial pairing** — two agents argue each category from opposite dispositions, surfacing disagreements a single model would self-censor\n- **Multi-model diversity** — Opus reasons conservatively and architecturally; Sonnet is pragmatic and detail-oriented\n- **Structured scoring** — 1-5 scale across Feasibility, Maintainability, Platform Leverage, Simplicity; 2+ point deltas auto-flagged\n- **Platform awareness** — fetches wiki catalog so agents reference real tools, not hypothetical ones\n- **The 30-Day Failure Scenario** — forces concrete, actionable thinking about what will actually go wrong\n- **Consensus red-team** — attacks the \"safe\" decisions everyone agrees on, because the most dangerous risks are the ones nobody flags\n\n## Invocation\n\n```\n/adom-plan                          # review the active plan file\n/adom-plan path/to/plan.md          # review a specific file\n```\n\n## Installation\n\nBundled with gallia. Available at `~/.claude/skills/adom-plan/` after `install.mjs` runs. The skill consists of two files:\n\n- `SKILL.md` (212 lines) — workflow, phases, synthesis format, guidelines\n- `debate-prompts.md` (413 lines) — all 8 agent prompt templates (read on demand during execution)\n\n## Output\n\nThe skill appends a **Debate Review Summary** to the plan file containing:\n\n- **Scorecard** — per-section grades (A/B/C/F) with dimensional scores\n- **Consensus Decisions** — verified safe items\n- **Contested Decisions** — where agents disagreed, with recommendations\n- **Fragile Consensus** — items the red-team flagged\n- **Risk Register** — consolidated threat table with mitigations\n- **Validation & E2E Strategy** — complete test plan\n- **The 30-Day Failure Scenario** — the most likely production failure\n- **Action Items** — numbered list tagged BLOCKING / RECOMMENDED / NICE-TO-HAVE\n",+  "author": {+    "id": "695820315b5f1e4db2fcf602",+    "name": "Kyle Bergstedt",+    "email": "[email protected]"+  },+  "visibility": {+    "public": true+  },+  "hero": null,+  "discovery_triggers": [],+  "discovery_pitch": null,+  "metadata": {},+  "created_at": "2026-05-28T05:29:33.375Z",+  "updated_at": "2026-05-28T05:29:33.375Z",+  "sub_skills": [],+  "parent_app": null+}\ No newline at end of file