fix(council): address PR #134 review findings

- Delete souls/ directory — content already inlined in agents/*.md
- Fix "four-model" → "five-agent" across all files
- Fix haiku model ID: haiku-4-5 → haiku-4-5-20251001 in README
- Update plugin counts: 7→8 plugins, 22→23 commands, 5→6 skills, 9→14 agents
- Remove souls/ references from README, marketplace.json, plugin.json, CHANGELOG
- Fix dispatch flow description in SKILL.md and commands/council.md
- Fix clarity escalation rule: "incorporate" → "surface verbatim, do not fill"
- Add BLOAT_FLAG procedure to haiku-janitor and captain escalation rules
- Add agents declaration to plugin.json (later removed — invalid schema field)

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

Author: ANcpLua

.claude-plugin/marketplace.json

@@ -46,7 +46,7 @@
     },
     {
       "name": "council",
-      "description": "Four-model council: Opus captain decomposes and synthesizes, three Sonnet specialists run in parallel (researcher, synthesizer, clarity), Haiku janitor cleans output. Each agent identity lives in a soul CLAUDE.md — passive context, zero activation cost.",
+      "description": "Five-agent council: Opus captain decomposes and synthesizes, researcher + synthesizer run in parallel, clarity checks their output, Haiku janitor flags bloat. Each agent identity is inlined in its agent file — passive context, zero activation cost.",
       "version": "1.0.0",
       "source": "./plugins/council"
     },

CHANGELOG.md

@@ -8,7 +8,7 @@ and the project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ### Added
 
-- **`plugins/council`**: New plugin — four-model council (opus-captain, sonnet-researcher, sonnet-synthesizer, sonnet-clarity, haiku-janitor). Each agent identity defined in a soul file (`souls/`) loaded as passive context. Inspired by Grok 4.20's multi-agent architecture. Invoke via `/council [task]`.
+- **`plugins/council`**: New plugin — five-agent council (opus-captain, sonnet-researcher, sonnet-synthesizer, sonnet-clarity, haiku-janitor). Each agent identity inlined directly in its `agents/*.md` file as passive context. Researcher + synthesizer run in parallel; clarity reads their raw output; haiku-janitor flags bloat; captain removes cuts. Inspired by Grok 4.20's multi-agent architecture. Invoke via `/council [task]`.
 
 ### Changed
 

CLAUDE.md

@@ -104,7 +104,7 @@ but NOT conversation history. All context must be in the spawn prompt.
 See `docs/ARCHITECTURE.md` for the complete repository layout, plugin structure, and ecosystem diagram.
 
 Key paths:
-- Plugins: `plugins/<name>/` — 7 plugins (22 commands, 5 skills, 9 agents)
+- Plugins: `plugins/<name>/` — 8 plugins (23 commands, 6 skills, 14 agents)
 - Rules (auto-loaded): `.claude/rules/`
 - Plugin registry: `.claude-plugin/marketplace.json`
 - Docs: `docs/` (ARCHITECTURE.md, QUICK-REFERENCE.md, WORKFLOWS.md, PLUGINS.md, ENGINEERING-PRINCIPLES.md)

Claude Code Agent Teams: 10+ Use Cases with Copy-Paste Prompts.md

@@ -35,7 +35,7 @@ ancplua-claude-plugins/
 │       ├── claude-code-review.yml # Claude formal PR review
 │       └── trigger-docs.yml     # Triggers ancplua-docs rebuild on push to main
 │
-├── plugins/                     # 7 plugins (22 commands, 5 skills, 9 agents)
+├── plugins/                     # 8 plugins (23 commands, 6 skills, 14 agents)
 │   ├── exodia/                  # Multi-agent orchestration (9 commands + 2 skills: eight-gates, hades)
 │   ├── metacognitive-guard/     # Cognitive amplification + commit integrity + CI
 │   ├── otelwiki/                # OpenTelemetry documentation + auto-sync

docs/ARCHITECTURE.md

@@ -1,7 +1,7 @@
 {
   "name": "council",
   "version": "1.0.0",
-  "description": "Four-model council: Opus captain coordinates three Sonnet specialists (researcher, synthesizer, clarity) plus a Haiku janitor. Each agent identity lives in its soul CLAUDE.md — passive context, zero activation cost.",
+  "description": "Five-agent council: Opus captain decomposes and synthesizes, researcher + synthesizer run in parallel, clarity checks their output, Haiku janitor flags bloat. Each agent identity is inlined in its agent file — passive context, zero activation cost.",
   "author": {
     "name": "ANcpLua",
     "email": ""

plugins/council/.claude-plugin/plugin.json

@@ -1,10 +1,11 @@
 # council
 
-Four-model council for complex tasks. Opus captain. Three Sonnet specialists. Haiku janitor.
+Five-agent council for complex tasks. Opus captain. Three Sonnet specialists. Haiku janitor.
 
-Inspired by Grok 4.20's 4-agent architecture — same mechanism, adapted for Claude: each agent's identity
-lives in its soul file (`souls/`), loaded as passive context. No activation cost. No "should I use this
-skill?" decision. The agent *is* its soul from token 1.
+Inspired by Grok 4.20's multi-agent architecture — same mechanism, adapted for Claude: each agent's
+identity is defined directly in its `agents/*.md` file as inline content, loaded as passive context
+from token 1. No activation cost. No "should I use this skill?" decision. The agent *is* its
+definition.
 
 ## Agents
 
@@ -13,8 +14,8 @@ skill?" decision. The agent *is* its soul from token 1.
 | `opus-captain` | claude-opus-4-6 | Decomposes task, dispatches specialists, synthesizes final answer |
 | `sonnet-researcher` | claude-sonnet-4-6 | Evidence, sources, verification — never speculates |
 | `sonnet-synthesizer` | claude-sonnet-4-6 | Logic, code, math — shows all work |
-| `sonnet-clarity` | claude-sonnet-4-6 | Gaps, assumptions, misalignment — blind-spot detection |
-| `haiku-janitor` | claude-haiku-4-5 | Removes filler and redundancy from final output |
+| `sonnet-clarity` | claude-sonnet-4-6 | Gaps, assumptions, misalignment — runs after researcher + synthesizer |
+| `haiku-janitor` | claude-haiku-4-5-20251001 | Flags bloat, returns CUTS list — captain removes |
 
 ## Usage
 
@@ -24,20 +25,18 @@ skill?" decision. The agent *is* its soul from token 1.
 
 ## How identity works
 
-Each agent loads its soul file on start — a dense CLAUDE.md that defines who it is, what it values,
-what it never does, and how it formats output. This is the passive context pattern: the identity is
-always present, not retrieved.
+Each agent file contains its full behavioral identity inline — values, protocol, output format, and
+what it never does. This is the passive context pattern: the identity is always present, not retrieved.
 
 Compare to Grok 4.20: same base model, four times, different system prompts. This is the same thing —
-same Sonnet base, different soul files.
+same Sonnet base, different agent definitions.
 
 ## Structure
 
 ```text
 council/
 ├── .claude-plugin/plugin.json
-├── agents/           # Agent definitions with model assignments
-├── souls/            # CLAUDE.md soul files — the actual identities
+├── agents/           # Agent definitions with inlined identity + model assignments
 │   ├── opus-captain.md
 │   ├── sonnet-researcher.md
 │   ├── sonnet-synthesizer.md

plugins/council/README.md

@@ -1,6 +1,6 @@
 ---
 description: >-
-  Invoke the four-model council on any complex task. Opus captain decomposes and synthesizes.
+  Invoke the five-agent council on any complex task. Opus captain decomposes and synthesizes.
   Researcher and synthesizer run in parallel. Clarity reads their raw output.
   Haiku janitor flags bloat. Captain removes cuts and delivers.
 ---