feat(meridian): GitHub Copilot support for subagent tools (0.10.6)

.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "meridian",
   "description": "Research-first workflows, ruthless code review, orchestrator-led reasoning, and opaque subagent isolation for the entire development lifecycle.",
-  "version": "0.10.5",
+  "version": "0.10.6",
   "author": {
     "name": "KodingDev"
   },

.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "meridian",
   "description": "Research-first workflows, ruthless code review, orchestrator-led reasoning, and opaque subagent isolation for the entire development lifecycle.",
-  "version": "0.10.5",
+  "version": "0.10.6",
   "author": {
     "name": "KodingDev"
   },

README.md

@@ -53,6 +53,10 @@ Install from the [Cursor plugin marketplace](https://cursor.com/marketplace), or
 
 Hooks are Node scripts (`node ./hooks/*.mjs`) — no Git Bash or shell polyglot required. Session orientation injects via `additional_context` on `sessionStart`. If hooks fail silently, check View → Output → **Hooks** and restart Cursor after updating the plugin.
 
+### GitHub Copilot CLI
+
+Copilot CLI installs the same plugin via its `/plugin` commands and loads the skills and subagents directly. Subagent `tools` are declared as YAML arrays of Claude tool names (`[Read, Grep, Glob, Bash, …]`); Copilot resolves these case-insensitively to its own primitives (`read`, `search`, `execute`, `web`), so the agents get full file/search/shell/web access rather than the bare baseline.
+
 Hook tests: `node --test test/meridian-hooks.test.mjs`
 
 ## Credit

agents/research.md

@@ -1,7 +1,7 @@
 ---
 name: research
 description: Verify external-API/library/protocol facts against live documentation. Returns facts and source URLs, never reasoning chains or hedging. Used by the research skill to isolate doc-fetching from orchestrator context.
-tools: WebFetch, WebSearch, Read, Grep, Glob
+tools: [WebFetch, WebSearch, Read, Grep, Glob]
 ---
 
 # Research Agent

agents/reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: reviewer
 description: Code review subagent. Receives a diff plus dimensions and returns classified findings (material-gap | prose-clarity | implementation-detail) with a verdict. Never edits.
-tools: Read, Grep, Glob, Bash
+tools: [Read, Grep, Glob, Bash]
 ---
 
 # Reviewer Agent

agents/triangulate.md

@@ -1,7 +1,7 @@
 ---
 name: triangulate
 description: Multi-source verification subagent. Reads candidate sources, returns a Ground Truth Audit with confidence label and a concrete falsifier. Used by the triangulate skill to isolate heavy verification reading from orchestrator context.
-tools: Read, Grep, Glob, Bash, WebFetch, WebSearch
+tools: [Read, Grep, Glob, Bash, WebFetch, WebSearch]
 ---
 
 # Triangulate Agent