feat(exodia): promote eight-gates from command to skill with per-gate templates

Moves eight-gates from a single 412-line command to a skill directory with
SKILL.md orchestrator + 8 per-gate specialist templates, following the hades
pattern. Each gate has a narrow job with its own entry/exit conditions, agent
prompts, and output schemas.

Reviewer fixes applied: expanded allowed-tools, SSOT references instead of
duplication, .smart/ gitignore safety, fixed undefined shell functions in
gate-02, fixed $(cat ...) references in gate-04/06, added context injection
instructions for subagent prompts in gate-05/07.

Counts: 22→21 commands, 4→5 skills across all metadata files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: ANcpLua

.claude-plugin/marketplace.json

@@ -5,7 +5,7 @@
     "url": "https://github.com/ANcpLua"
   },
   "metadata": {
-    "description": "Claude Code plugin marketplace: 7 plugins, 22 commands, 4 skills, 9 agents. Multi-agent orchestration, cognitive amplification, OpenTelemetry docs, and .NET build enforcement."
+    "description": "Claude Code plugin marketplace: 7 plugins, 21 commands, 5 skills, 9 agents. Multi-agent orchestration, cognitive amplification, OpenTelemetry docs, and .NET build enforcement."
   },
   "plugins": [
     {
@@ -46,7 +46,7 @@
     },
     {
       "name": "exodia",
-      "description": "Multi-agent workflow orchestration (9 commands + hades skill): fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, eight-gates.",
+      "description": "Multi-agent workflow orchestration (8 commands + 2 skills: eight-gates, hades): fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review.",
       "version": "2.0.0",
       "source": "./plugins/exodia"
     }

CHANGELOG.md

@@ -6,9 +6,13 @@ and the project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
+### Changed
+
+- **exodia `eight-gates` promoted from command to skill**: Moved from `commands/eight-gates.md` (412 lines) to `skills/eight-gates/` (SKILL.md + 8 per-gate templates in `templates/`). Follows the hades pattern — supporting files enable specialist agent prompts per gate without bloating the main skill. Reviewer fixes applied: expanded `allowed-tools`, SSOT references instead of duplication, `.smart/` gitignore safety, fixed undefined shell functions in gate-02, fixed `$(cat ...)` references in gate-04/06, added context injection instructions for subagent prompts in gate-05/07. Counts: 22→21 commands, 4→5 skills
+
 ### Added
 
-- **exodia `eight-gates` command**: Progressive discipline orchestration — 8 named gates (Kaimon→Shimon) composing scope, context loading (Yin), parallel MAP (Yang), checkpointing (Senzu), bounded reflection (Ralph Loop), reduce, TDD execution, and Hakai cleanup. Includes budget tracking, idempotent resume from any gate, TTL sessions, artifact caching, and decision logging. Composes mega-swarm (MAP), fix pipelines (EXECUTE), and hades (HAKAI) into a unified flow
+- **exodia `eight-gates` skill**: Progressive discipline orchestration — 8 named gates (Kaimon→Shimon) composing scope, context loading (Yin), parallel MAP (Yang), checkpointing (Senzu), bounded reflection (Ralph Loop), reduce, TDD execution, and Hakai cleanup. Includes budget tracking, idempotent resume from any gate, TTL sessions, artifact caching, and decision logging. Composes mega-swarm (MAP), fix pipelines (EXECUTE), and hades (HAKAI) into a unified flow
 - **`checkpoint.sh` smart script**: Gate checkpoint management — init, save, load, verify (idempotent), list. Append-only JSONL storage with key=value metadata per gate
 - **`session-state.sh` smart script**: TTL session state + artifact cache + decision log. Create sessions with expiry, cache expensive computations, log decisions with reasons, extend/expire sessions
 - **`.eight-gates/` gitignore entry**: Session-local runtime directory (checkpoints, artifacts, decisions)

CLAUDE.md

@@ -122,8 +122,8 @@ ancplua-claude-plugins/
 │   ├── copilot-instructions.md
 │   └── workflows/               # CI, review, auto-merge
 │
-├── plugins/                     # 7 plugins (22 commands, 4 skills, 9 agents)
-│   ├── exodia/                  # Multi-agent orchestration — 9 commands + hades skill
+├── plugins/                     # 7 plugins (21 commands, 5 skills, 9 agents)
+│   ├── exodia/                  # Multi-agent orchestration — 8 commands + 2 skills (eight-gates, hades)
 │   ├── metacognitive-guard/     # Cognitive amplification + commit integrity + CI
 │   ├── otelwiki/                # OpenTelemetry docs + sync
 │   ├── hookify/                 # User-configurable hooks
@@ -225,7 +225,7 @@ IF zero-tolerance cleanup needed
 
 When multi-agent orchestration is needed, use these IF/THEN patterns:
 
-- **IF maximum discipline orchestration** THEN use `eight-gates` command (8 gates, composes all others)
+- **IF maximum discipline orchestration** THEN use `eight-gates` skill (8 gates, composes all others)
 - **IF fixing P1/P2/P3 bug** THEN use `fix` skill (8 agents standard, 16 maximum)
 - **IF need multiple solution perspectives** THEN use `tournament` skill (N competitors)
 - **IF complex debugging first** THEN use `deep-think` skill before fix

README.md

@@ -2,13 +2,13 @@
 
 > **CCC** — Claude, Copilot, CodeRabbit. The holy trinity. And two of them are Claude in a trenchcoat.
 
-Claude Code plugin marketplace. 7 plugins, 22 commands, 4 skills, 9 agents, 18 scripts, 5 hook configs.
+Claude Code plugin marketplace. 7 plugins, 21 commands, 5 skills, 9 agents, 18 scripts, 5 hook configs.
 
 ## Plugins
 
 | Plugin | Version | Description |
 |--------|---------|-------------|
-| **exodia** | 2.0.0 | Multi-agent orchestration (9 commands + hades skill): fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, eight-gates |
+| **exodia** | 2.0.0 | Multi-agent orchestration (8 commands + 2 skills: eight-gates, hades): fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review |
 | **metacognitive-guard** | 0.4.0 | Cognitive amplification: epistemic hooks, commit integrity, CI verification, competitive review, deep analysis, deep-thinking agents |
 | **otelwiki** | 1.0.6 | OpenTelemetry docs with auto-sync and semantic convention validation |
 | **hookify** | 0.2.0 | User-configurable hooks from .local.md files |
@@ -31,7 +31,7 @@ Tri-AI review system: Claude, Copilot, CodeRabbit all review PRs independently.
 
 ```text
 plugins/
-├── exodia/                  # multi-agent orchestration (9 commands + hades cleanup skill)
+├── exodia/                  # multi-agent orchestration (8 commands + 2 skills: eight-gates, hades)
 ├── metacognitive-guard/     # struggle detection + deep-think + commit integrity + CI verification
 ├── otelwiki/                # OTel docs + sync
 ├── hookify/                 # user-configurable hooks

docs/AGENTS.md

@@ -23,4 +23,5 @@ Spawn agents via the Task tool with `subagent_type` matching the agent identifie
 The separation of concerns:
 - **Plugins** encode reusable behavior and skills
 - **Agents** orchestrate plugins and execute workflows
-- **Exodia commands** compose agents into multi-agent pipelines (9 commands + hades skill, 22 commands total across all plugins)
+- **Exodia** composes agents into multi-agent pipelines
+  (8 commands + 2 skills: eight-gates, hades; 21 commands total)

docs/ARCHITECTURE.md

@@ -35,8 +35,8 @@ ancplua-claude-plugins/
 │       ├── claude-code-review.yml # Claude formal PR review
 │       └── dependabot.yml       # Dependency update config
 │
-├── plugins/                     # 7 plugins (22 commands, 4 skills, 9 agents)
-│   ├── exodia/                  # Multi-agent orchestration (9 commands + hades skill)
+├── plugins/                     # 7 plugins (21 commands, 5 skills, 9 agents)
+│   ├── exodia/                  # Multi-agent orchestration (8 commands + 2 skills: eight-gates, hades)
 │   ├── metacognitive-guard/     # Cognitive amplification + commit integrity + CI
 │   ├── otelwiki/                # OpenTelemetry documentation + auto-sync
 │   ├── hookify/                 # User-configurable rule-based hooks
@@ -122,7 +122,7 @@ CI mirrors the same checks via `.github/workflows/ci.yml`.
 
 | Plugin | Responsibility |
 |--------|----------------|
-| `exodia` | Multi-agent orchestration (9 commands + hades skill) |
+| `exodia` | Multi-agent orchestration (8 commands + 2 skills: eight-gates, hades) |
 | `metacognitive-guard` | Cognitive amplification, commit integrity, CI verification |
 | `feature-dev` | Guided feature development + code review |
 | `otelwiki` | OpenTelemetry documentation + sync |

plugins/exodia/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "exodia",
   "version": "2.0.0",
-  "description": "Multi-agent workflow orchestration: fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, hades (Smart cleanup with audit trail).",
+  "description": "Multi-agent workflow orchestration: 8 commands (fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review) + 2 skills (eight-gates, hades).",
   "author": {
     "name": "AncpLua",
     "url": "https://github.com/ANcpLua"

plugins/exodia/CLAUDE.md

@@ -1,12 +1,11 @@
 # exodia
 
-Multi-agent workflow orchestration. 9 commands + 1 skill (hades), unlimited parallel agents.
+Multi-agent workflow orchestration. 8 commands + 2 skills (eight-gates, hades), unlimited parallel agents.
 
 ## Commands (in commands/)
 
 | Command | Agents | Use When |
 |---------|--------|----------|
-| `eight-gates` | 1-30+ | Maximum disciplined orchestration — 8 progressive gates with checkpointing, budget tracking, Hakai guarantee |
 | `turbo-fix` | 13 | P0 critical bugs |
 | `fix` | 8-16 | Any bug fix (configurable parallelism) |
 | `fix-pipeline` | 7 | Fixing audit findings systematically |
@@ -16,10 +15,11 @@ Multi-agent workflow orchestration. 9 commands + 1 skill (hades), unlimited para
 | `batch-implement` | N+2 | Multiple similar items in parallel |
 | `red-blue-review` | 3+N+1 | Adversarial security/quality review |
 
-## Skill (in skills/ — uses hooks/argument-hint)
+## Skills (in skills/ — uses hooks/argument-hint)
 
 | Skill | Agents | Use When |
 |-------|--------|----------|
+| `eight-gates` | 1-30+ | Maximum disciplined orchestration — 8 progressive gates with checkpointing, budget tracking, Hakai guarantee |
 | `hades` | 12 (3x4) | Smart cleanup with audit trail (Smart IDs, ledger, permits) |
 
 ## Smart Infrastructure

plugins/exodia/README.md

@@ -1,12 +1,11 @@
 # exodia v2.0.0
 
-Multi-agent workflow orchestration. 9 commands + 1 skill (hades).
+Multi-agent workflow orchestration. 8 commands + 2 skills (eight-gates, hades).
 
 ## Commands
 
 | Command | Agents | Pattern | Best For |
 |---------|--------|---------|----------|
-| `/exodia:eight-gates` | 1-30+ | Progressive discipline | Maximum orchestration with checkpointing + Hakai |
 | `/exodia:turbo-fix` | 13 | Phased pipeline | P0 critical bugs |
 | `/exodia:fix` | 8-16 | Configurable pipeline | Any bug fix |
 | `/exodia:fix-pipeline` | 7 | Systematic pipeline | Audit findings |
@@ -16,10 +15,11 @@ Multi-agent workflow orchestration. 9 commands + 1 skill (hades).
 | `/exodia:batch-implement` | N+2 | Template + parallel | Similar items |
 | `/exodia:red-blue-review` | 3+N | Adversarial | Security review |
 
-## Skill (uses hooks/argument-hint)
+## Skills (uses hooks/argument-hint)
 
 | Skill | Agents | Pattern | Best For |
 |-------|--------|---------|----------|
+| `exodia:eight-gates` | 1-30+ | Progressive discipline | Maximum orchestration with checkpointing + Hakai |
 | `exodia:hades` | 12 (3x4) | Smart cleanup | Audited elimination |
 
 ## Typical Workflow