chore: sync marketplace artifacts with README

Author: github-actions[bot]

.agents/plugins/marketplace.json

@@ -60,7 +60,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Multi-agent codebase knowledge graph generator with context-aware planning and automatic scope management \u2014 turns codebases into coherent agent workspaces."
+      "description": "Multi-agent codebase knowledge graph generator with context-aware planning and automatic scope management — turns codebases into coherent agent workspaces."
     },
     {
       "name": "bringyour-migration-auditor",
@@ -88,7 +88,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "AI code reviews grounded in six classic engineering books \u2014 decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality).",
+      "description": "AI code reviews grounded in six classic engineering books — decay risk diagnostics with book citations, severity labels, and four analysis modes (PR review, architecture audit, tech debt, test quality).",
       "icon": "./plugins/hyhmrright/brooks-lint/assets/logo.svg"
     },
     {
@@ -133,7 +133,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "223 production-ready skills, 23 agents, and 298 Python tools across 9 domains \u2014 engineering, marketing, product, compliance, and more."
+      "description": "223 production-ready skills, 23 agents, and 298 Python tools across 9 domains — engineering, marketing, product, compliance, and more."
     },
     {
       "name": "claude-octopus",
@@ -161,7 +161,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Analyze git history to understand a codebase before reading any code \u2014 auto-scales by repo size and cross-references hotspots with bug magnets to surface high-risk files, bus factor, and team momentum."
+      "description": "Analyze git history to understand a codebase before reading any code — auto-scales by repo size and cross-references hotspots with bug magnets to surface high-risk files, bus factor, and team momentum."
     },
     {
       "name": "ateam",
@@ -305,7 +305,8 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Token-lean triage-driven workflow skills for coding agents: design, planning, TDD, debugging, review, worktree, subagents, and release. 10\u201340\u00d7 cheaper per skill than comparable frameworks while preserving full workflow discipline."
+      "description": "Token-lean triage-driven workflow skills for coding agents: design, planning, TDD, debugging, review, worktree, subagents, and release. 10–40× cheaper per skill than comparable frameworks while preserving full workflow discipline.",
+      "icon": "./plugins/ouonet/praxis/assets/logo-mark.svg"
     },
     {
       "name": "codex-project-autopilot",
@@ -349,7 +350,8 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Session orchestration for Claude Code, Codex, and Cursor IDE \u2014 structured planning, wave-based execution, VCS integration (GitLab + GitHub), quality gates, and clean session close-out with issue tracking."
+      "description": "Session orchestration for Claude Code, Codex, and Cursor IDE — structured planning, wave-based execution, VCS integration (GitLab + GitHub), quality gates, and clean session close-out with issue tracking.",
+      "icon": "./plugins/Kanevry/session-orchestrator/assets/icon.svg"
     },
     {
       "name": "spec-driven",
@@ -363,7 +365,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Three-phase Requirements \u2192 Design \u2192 Tasks workflow for Claude Code and Codex \u2014 EARS notation acceptance criteria, autonomous execution loop, cross-spec dependencies, and post-implementation acceptance testing."
+      "description": "Three-phase Requirements → Design → Tasks workflow for Claude Code and Codex — EARS notation acceptance criteria, autonomous execution loop, cross-spec dependencies, and post-implementation acceptance testing."
     },
     {
       "name": "stark",
@@ -434,7 +436,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Role-based team delivery framework \u2014 Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode."
+      "description": "Role-based team delivery framework — Tech Lead-orchestrated 8-role system with 195+ skills, 27 specialist agents, 80+ commands, hooks, and ECC harness for Claude Code, Codex, and OpenCode."
     },
     {
       "name": "tool-advisor",
@@ -491,7 +493,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Development & Workflow",
-      "description": "Developer personality portrait generator \u2014 analyzes AI conversation history to produce MBTI type (16 color themes), capability radar, developer rating, 3-dimension famous match, and a persona skill that lets any AI \"think like you\"."
+      "description": "Developer personality portrait generator — analyzes AI conversation history to produce MBTI type (16 color themes), capability radar, developer rating, 3-dimension famous match, and a persona skill that lets any AI \"think like you\"."
     },
     {
       "name": "writers-loop",
@@ -849,7 +851,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Tools & Integrations",
-      "description": "Decentralized e-commerce skills \u2014 deploy self-hosted stores, import products from Shopify/Amazon, configure custom domains and Telegram bots, set up Tor privacy, and manage your store via MCP."
+      "description": "Decentralized e-commerce skills — deploy self-hosted stores, import products from Shopify/Amazon, configure custom domains and Telegram bots, set up Tor privacy, and manage your store via MCP."
     },
     {
       "name": "morning-ai",
@@ -979,7 +981,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Tools & Integrations",
-      "description": "Russian text quality \u2014 ~1,040 rules for typography, info-style, editorial, UX writing, and business correspondence."
+      "description": "Russian text quality — ~1,040 rules for typography, info-style, editorial, UX writing, and business correspondence."
     },
     {
       "name": "rust-reverse-engineering",
@@ -1007,7 +1009,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Tools & Integrations",
-      "description": "Build websites from Markdown via MCP \u2014 22 tools for creating pages, generating content, validating, running SEO audits, configuring settings, and deploying static sites to Cloudflare Pages."
+      "description": "Build websites from Markdown via MCP — 22 tools for creating pages, generating content, validating, running SEO audits, configuring settings, and deploying static sites to Cloudflare Pages."
     },
     {
       "name": "n8n-mcp-synta-codex",
@@ -1065,7 +1067,7 @@
         "authentication": "ON_INSTALL"
       },
       "category": "Tools & Integrations",
-      "description": "Strip AI writing patterns from text output \u2014 removes filler phrases, hedging language, and generic constructs to produce cleaner written content. Install: `npm install -g unslop`."
+      "description": "Strip AI writing patterns from text output — removes filler phrases, hedging language, and generic constructs to produce cleaner written content. Install: `npm install -g unslop`."
     },
     {
       "name": "upwork-autopilot",

plugins/AUN-PN/unity-agent-workflows/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "unity-agent-workflows",
-  "version": "0.3.4",
+  "version": "0.4.0",
   "description": "Codex skill for safer Unity AI agent workflows, runtime-owner proof, runtime numeric proof, multi-agent scope ownership, and Unity game development automation.",
   "author": {
     "name": "AUN-PN"
@@ -24,7 +24,7 @@
   "interface": {
     "displayName": "Unity Workflows",
     "shortDescription": "Safer AI workflows for Unity 2D projects",
-    "longDescription": "Use Teach first. Teach creates or refreshes UNITY_STRUCTURE.md for the current Unity 2D project, then agents use disciplined repo discovery, runtime-owner proof, runtime numeric proof for repeated visible-output failures, overlay/dim source-bound checks, guided state-step guards, multi-agent scope ownership, project-derived routing, UI and scene safety, validation, and cleanup proof before editing.",
+    "longDescription": "Use Teach first when onboarding a new Unity 2D project or when UNITY_STRUCTURE maps are missing or stale. For normal tasks, agents read existing structure maps only when relevant, then use disciplined repo discovery, runtime-owner proof, runtime numeric proof for repeated visible-output failures, overlay/dim source-bound checks, guided state-step guards, multi-agent scope ownership, project-derived routing, UI and scene safety, validation, and cleanup proof before editing.",
     "developerName": "AUN-PN",
     "category": "Coding",
     "capabilities": ["Read", "Write"],

plugins/AUN-PN/unity-agent-workflows/README.md

@@ -35,6 +35,8 @@ This plugin gives the agent a stricter workflow for Unity 2D projects:
 - prove runtime-visible owner chains before UI, HUD, scene, prefab, or gameplay edits
 - route new C# responsibility to existing project owners instead of broad folders
 - keep UI/safe-area/TMP/coordinate-space work tied to the real runtime hierarchy
+- load deep reference files only when the current task needs them
+- ask before spawning sub-agents unless the user already requested them in the same turn
 - validate with the smallest useful check and report residual risk honestly
 - require reference proof before cleanup or deletion
 
@@ -74,12 +76,12 @@ flowchart TD
 Step details:
 
 1. **User input**: a Unity task, screenshot, stack trace, feature request, cleanup request, or validation request enters the agent.
-2. **Skill trigger**: the skill runs from an explicit `$unity-agent-workflows` prompt or an implicit Unity 2D workflow match.
-3. **Read context**: the agent reads project rules, dirty state, structure maps, and only relevant docs.
+2. **Skill trigger**: the skill runs from an explicit `$unity-agent-workflows` prompt or an implicit Unity 2D repo task that needs editing, validation, routing, runtime proof, state proof, asmdef/module safety, cleanup, or multi-agent coordination.
+3. **Read context**: the agent reads `AGENTS.md` if present, `git status --short`, existing `UNITY_STRUCTURE.md` plus only the focused map that matches the task, and only relevant docs.
 4. **Classify task**: the request is routed as visible output, state flow, content, architecture, cleanup, or validation.
-5. **Load references**: `SKILL.md` selects the required reference files instead of loading every rule.
+5. **Load references**: `SKILL.md` selects the required reference files instead of loading every rule. `unity-validation.md` and `workflow-recipes.md` are deferred until validation/recipe context needs them.
 6. **Proof loop**: if owner chain, overlay/dim source-bound proof, runtime numeric proof, or guided state-flow proof is missing, the agent loops back to inspect or probe runtime data.
-7. **Lock scope**: the main agent names `Files allowed to touch`, `Files explicitly not touched`, and multi-agent ownership before workers patch.
+7. **Lock scope**: the main agent names `Files allowed to touch`, `Files explicitly not touched`, and multi-agent ownership before workers patch. Sub-agents are not spawned until the user approves, unless the user already asked for them in the same turn.
 8. **Patch**: edit the smallest safe file set only after proof is complete.
 9. **Validation loop**: failed validation returns to proof/patch; missing runtime proof returns a probe plan instead of another guess.
 10. **Close out**: report changed files, proof, validation, and residual risk.
@@ -177,7 +179,7 @@ Inside a Unity 2D repo, invoke the skill:
 $unity-agent-workflows. Teach
 ```
 
-`Teach` is a Codex skill instruction, not an npm CLI command. When the agent follows it, it creates or refreshes a short structure index and focused maps only where useful:
+`Teach` is a Codex skill instruction, not an npm CLI command. Use it when onboarding a new Unity project, when `UNITY_STRUCTURE*` maps are missing or stale, or when the user explicitly requests a structure refresh. When the agent follows it, it creates or refreshes a short structure index and focused maps only where useful:
 
 ```text
 UNITY_STRUCTURE.md
@@ -195,7 +197,7 @@ Use $unity-agent-workflows.
 Do not edit yet. Inspect the project structure and report the proposed UNITY_STRUCTURE map plan.
 ```
 
-Later tasks should read only `UNITY_STRUCTURE.md` plus the focused map that matches the work.
+Later tasks should read only `UNITY_STRUCTURE.md` plus the focused map that matches the work. They should not run `Teach` again unless a needed map is missing or stale.
 
 | Task                                                                 | Read                                                  |
 | -------------------------------------------------------------------- | ----------------------------------------------------- |
@@ -224,6 +226,7 @@ The visible bug was a repeated FTUE Stage 5 Sentinel install focus mismatch. A n
 What the plugin changed:
 
 - Treat the issue as a repeated visible-output failure.
+- Ask before spawning sub-agents unless the user already requested them in the same turn.
 - Keep sub-agents read-only until the main agent locks scope.
 - Require runtime numeric proof before another focus/position patch.
 - Check that the final focus target is the visible `ADD` button, not the ship area.
@@ -275,15 +278,15 @@ If that chain is incomplete, the agent should inspect deeper or ask one focused
 | Overlay/dim source bounds | reject overlay, mask, blocker, or spotlight surfaces as source bounds unless an explicit marker proves target |
 | Coordinate conversion     | keep world, local, screen, viewport, canvas, camera, and safe-area spaces explicit                            |
 | Guided state flows        | separate shown/clicked/opened/selected/equipped/claimed/completed/persisted before marking completion        |
-| Multi-agent work          | lock Routing Card, file ownership, runtime proof, and checker gates before parallel worker patches            |
+| Multi-agent work          | ask before spawning, then lock Routing Card, file ownership, runtime proof, and checker gates before patches  |
 | C# routing                | derive folders, namespaces, `.asmdef` files, dependency direction, and owner modules                          |
 | Content changes           | prefer existing data/config surfaces when the project has them                                                |
 | Validation                | use the smallest useful check and report exact command output                                                 |
 | Cleanup                   | prove unused status through code refs, YAML/GUID refs, Resources/addressables paths, and runtime reachability |
 
 ## Reference Files
 
-The main [SKILL.md](SKILL.md) stays short. Deeper workflow rules live in `references/` and are loaded only when the task needs them.
+The main [SKILL.md](SKILL.md) stays short. Deeper workflow rules live in `references/` and are loaded only when the task needs them. This table is a catalog, not a preload list; agents should follow `SKILL.md` Required References and each reference file's own `Read` / `Load Extra Detail` guidance.
 
 | File                                                                                   | Purpose                                                                      |
 | -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
@@ -306,13 +309,11 @@ The main [SKILL.md](SKILL.md) stays short. Deeper workflow rules live in `refere
 For this repository:
 
 ```bash
-npm run validate
 npm run sync:mcpmarket
+npm run validate
 npm run pack:dry-run
 ```
 
-`npm run validate` checks package metadata, plugin manifests, mirrored skill payloads, README workflow coverage, reference links, JavaScript syntax, runtime numeric proof triggers, overlay/dim source-bound gates, guided state-flow gates, and multi-agent scope triggers.
-
 `npm run sync:mcpmarket` mirrors `SKILL.md`, `references/`, and `agents/` into:
 
 ```text
@@ -321,6 +322,8 @@ skills/unity-agent-workflows/
 plugins/unity-agent-workflows/skills/unity-agent-workflows/
 ```
 
+`npm run validate` checks package metadata, plugin manifests, mirrored skill payloads, README workflow coverage, reference links, JavaScript syntax, runtime numeric proof triggers, overlay/dim source-bound gates, guided state-flow gates, and multi-agent scope triggers.
+
 For Unity projects using the skill, Unity Editor, Play Mode, Game view, device tests, batchmode builds, and project logs remain the authoritative validation path. Bee `.rsp` or direct Unity-bundled Roslyn checks are best-effort local compile smoke tests and can be stale after Unity regenerates project artifacts.
 
 ## Repository Layout

plugins/AUN-PN/unity-agent-workflows/package.json

@@ -1,6 +1,6 @@
 {
   "name": "unity-agent-workflows",
-  "version": "0.3.4",
+  "version": "0.4.0",
   "description": "Codex skill and npx installer for safer Unity AI agent workflows, runtime owner proof, and Unity game development automation.",
   "bin": {
     "unity-agent-workflows": "bin/unity-agent-workflows.js"