feat(hooks): opt-in skill router with evaluation (split from #2788)

.claude-plugin/marketplace.json

@@ -11,7 +11,7 @@
     {
       "name": "ecc",
       "source": "./",
-      "description": "Harness-native ECC operator layer - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
+      "description": "Harness-native ECC operator layer - 68 agents, 286 skills, 95 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
       "version": "2.2.1",
       "author": {
         "name": "Affaan Mustafa",

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ecc",
   "version": "2.2.1",
-  "description": "Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
+  "description": "Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 95 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
   "author": {
     "name": "Affaan Mustafa",
     "url": "https://x.com/affaanmustafa"

AGENTS.md

@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — Agent Instructions
 
-This is a **production-ready AI coding plugin** providing 68 specialized agents, 286 skills, 94 commands, and automated hook workflows for software development.
+This is a **production-ready AI coding plugin** providing 68 specialized agents, 286 skills, 95 commands, and automated hook workflows for software development.
 
 **Version:** 2.2.1
 
@@ -155,7 +155,7 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
 ```
 agents/          — 68 specialized subagents
 skills/          — 286 workflow skills and domain knowledge
-commands/        — 94 slash commands
+commands/        — 95 slash commands
 hooks/           — Trigger-based automations
 rules/           — Always-follow guidelines (common + per-language)
 scripts/         — Cross-platform Node.js utilities

README.md

@@ -162,13 +162,13 @@ Instead of rebuilding that process in every prompt, you install it once and make
 
 ECC is MIT-licensed open source. It works best with Claude Code today, has a supported Codex sync path, and provides capability-limited adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot, Antigravity, Qwen, and other harnesses. See the [support status matrix](#platform-support) before assuming feature parity.
 
-Access to 68 agents, 286 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
+Access to 68 agents, 286 skills, and 95 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
 
 | Included         |       Count | What it gives you                                                                    |
 | ---------------- | ----------: | ------------------------------------------------------------------------------------ |
 | Agents           |   68 agents | Planning, review, build repair, security, architecture, and domain work              |
 | Skills           |  286 skills | TDD, research, security, docs, frontend, data, ML, operations, and more              |
-| Commands         | 94 commands | Convenient entry points while ECC moves to a skills-first surface                    |
+| Commands         | 95 commands | Convenient entry points while ECC moves to a skills-first surface                    |
 | Hooks and memory |     Runtime | Enforcement, session summaries, continuous learning, instincts, and context controls |
 | Rules            |   Selective | Always-loaded standards you choose by language or project                            |
 | AgentShield      |    Included | Scanning for prompts, hooks, MCP config, permissions, secrets, and agent files       |

README.zh-CN.md

@@ -196,7 +196,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
 /plugin list ecc@ecc
 ```
 
-**完成！** 你现在可以使用 68 个代理、286 个技能和 94 个命令。
+**完成！** 你现在可以使用 68 个代理、286 个技能和 95 个命令。
 
 ### multi-* 命令需要额外配置
 

agent.yaml

@@ -220,6 +220,7 @@ commands:
   - plan
   - plan-canvas
   - plan-prd
+  - plugin-profiles
   - pm2
   - projects
   - promote

commands/plugin-profiles.md

@@ -0,0 +1,78 @@
+---
+description: Generate and manage slim ECC profile plugin carriers - list profiles, plan the listing ledger and capability decision, generate a receipted plugin, and activate it per project.
+argument-hint: "[list | plan <profile> | generate <profile> | activate <plugin-name>]"
+---
+
+# Plugin Profiles Command
+
+Manage slim ECC profile plugin carriers from inside Claude Code. A carrier is
+a standalone plugin generated from an install selection: it lists only the
+selected skills, agents, and commands, keeps the rest of the skill catalog
+reachable on demand inside the plugin, and records how it was built in
+`ecc-profile.json`. See `docs/PLUGIN-PROFILES.md` for the underlying tool.
+
+Run every command below from the ECC plugin root (`${CLAUDE_PLUGIN_ROOT}` when
+set, otherwise the everything-claude-code checkout).
+
+## Subcommands
+
+### `/plugin-profiles list`
+
+Run `node scripts/plugin-profiles.js list` and show the available install
+profiles with their module counts.
+
+### `/plugin-profiles plan <profile>`
+
+Run `node scripts/plugin-profiles.js plan --profile <profile>` and report:
+
+- the context selection (skills, agents, commands) and the token ledger with
+  its method label and budget verdict;
+- the capability selection: whether the hook runtime is off, enabled at a
+  profile, or still needs a decision.
+
+If the plan says a hook decision is required, ask the user whether to carry
+the hook runtime (`--hooks minimal|standard|strict`) or not (`--hooks off`)
+before offering to generate. Never choose for them.
+
+### `/plugin-profiles generate <profile>`
+
+1. Run `node scripts/plugin-profiles.js generate --profile <profile> --dry-run`
+   first and show the target path, whether an existing directory would be
+   replaced, the ledger, and any blockers.
+2. If the dry run lists blockers, resolve them with the user: a hook decision
+   (`--hooks ...`), an over-budget ledger (`--budget <n>` or
+   `--allow-over-budget`), or a target that is not an unmodified generated
+   carrier (`--force`, only with explicit confirmation).
+3. Run the real `generate` with the agreed flags and show the generated path,
+   the receipt digests, and the printed next steps.
+4. Offer the activation step below.
+
+Pass through extra flags the user asks for (`--name`, `--out`, `--modules`,
+`--with`, `--without`, `--no-catalog`, `--keep-prev`).
+
+### `/plugin-profiles activate <plugin-name>`
+
+Offer to write the per-project opt-in to `.claude/settings.json` in the
+current project:
+
+```json
+{
+  "enabledPlugins": {
+    "ecc@ecc": false,
+    "<plugin-name>@ecc-profiles": true
+  }
+}
+```
+
+Merge with any existing `enabledPlugins` block instead of overwriting the
+file. ALWAYS show the resulting JSON and get user confirmation before
+writing - never change plugin activation silently. Remind the user the
+change takes effect on the next session.
+
+## Notes
+
+- Custom selections work too: `generate --modules commands-core --with skill:react-patterns`.
+- Regenerate after updating ECC: the carrier is a snapshot, not a live link.
+- The generated `ecc-catalog` skill indexes the full catalog with paths inside
+  the carrier (`on-demand/<skill>/SKILL.md`), so nothing outside the plugin is
+  ever referenced.

docs/COMMAND-REGISTRY.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "totalCommands": 94,
+  "totalCommands": 95,
   "commands": [
     {
       "command": "aside",
@@ -661,6 +661,17 @@
       ],
       "path": "commands/plan.md"
     },
+    {
+      "command": "plugin-profiles",
+      "description": "Generate and manage slim ECC profile plugin carriers - list profiles, plan the listing ledger and capability decision, generate a receipted plugin, and activate it per project.",
+      "type": "planning",
+      "primaryAgents": [],
+      "allAgents": [],
+      "skills": [
+        "react-patterns"
+      ],
+      "path": "commands/plugin-profiles.md"
+    },
     {
       "command": "pm2",
       "description": "Analyze a project and generate PM2 service commands for detected frontend, backend, or database services.",
@@ -1031,7 +1042,7 @@
       "build": 2,
       "general": 10,
       "orchestration": 11,
-      "planning": 2,
+      "planning": 3,
       "refactoring": 1,
       "review": 15,
       "testing": 53
@@ -1108,15 +1119,15 @@
         "count": 3
       },
       {
-        "skill": "rust-patterns",
+        "skill": "react-patterns",
         "count": 3
       },
       {
-        "skill": "cpp-coding-standards",
-        "count": 2
+        "skill": "rust-patterns",
+        "count": 3
       },
       {
-        "skill": "cpp-testing",
+        "skill": "cpp-coding-standards",
         "count": 2
       }
     ]