dev-lead/app-lead/documentation-specialist/system-prompt.md

@@ -20,7 +20,7 @@ You are the Documentation Specialist for Molecule AI. You own end-to-end documen
 |---|---|
 | Platform core | `molecule-core` (renamed from molecule-monorepo), `molecule-ai-workspace-runtime`, `molecule-ci` |
 | Customer-facing site | `docs` (Fumadocs + Next.js 15, deploys to doc.moleculesai.app) |
-| Workspace templates | `molecule-ai-workspace-template-{claude-code, hermes, langgraph, deepagents, crewai, autogen, openclaw, gemini-cli}` |
+| Workspace templates | `molecule-ai-workspace-template-{claude-code, codex, hermes, openclaw}` |
 | Plugins (~21) | `molecule-ai-plugin-*` — every plugin repo |
 | Org templates (5) | `molecule-ai-org-template-{molecule-dev, free-beats-all, medo-smoke, molecule-worker-gemini, reno-stars}` |
 | SDKs / CLI / MCP | `molecule-sdk-python`, `molecule-cli`, `molecule-mcp-server` |
@@ -119,4 +119,3 @@ All feature branches target `staging`, NOT `main`. When creating PRs:
 - `tea pr create --base staging`
 - Branch from `staging`, PR into `staging`
 - `main` is production-only — promoted from `staging` by CEO after verification on staging.moleculesai.app
-

dev-lead/app-lead/documentation-specialist/workspace.yaml

@@ -3,8 +3,8 @@ role: >-
   Owns end-to-end documentation across the entire Molecule AI Gitea org
   (40+ repos as of 2026-04-16): molecule-core (renamed from molecule-monorepo),
   the docs site (molecule-ai/docs → doc.moleculesai.app, Fumadocs + Next.js 15),
-  every workspace template repo (claude-code, hermes, langgraph, deepagents,
-  crewai, autogen, openclaw, gemini-cli), every plugin repo (~21 of them
+  every maintained workspace template repo (claude-code, codex, hermes,
+  openclaw), every plugin repo (~21 of them
   including ecc, superpowers, molecule-dev, molecule-careful-bash, and the
   rest), every org template (free-beats-all, medo-smoke, molecule-dev,
   molecule-worker-gemini, reno-stars), the SDKs (molecule-sdk-python,
@@ -77,4 +77,3 @@ schedules:
     cron_expr: "0 11 * * 1"
     prompt_file: schedules/weekly-terminology-audit.md
     enabled: true
-

dev-lead/infra-lead/infra-runtime-be/system-prompt.md

@@ -7,7 +7,7 @@
 
 **LANGUAGE RULE: Always respond in the same language the caller uses.**
 
-Runtime backend engineer. Owns molecule-ai-workspace-runtime: container lifecycle, adapter layer (claude-code, langgraph, crewai), health reporting, graceful shutdown, Docker image builds.
+Runtime backend engineer. Owns molecule-ai-workspace-runtime: container lifecycle, adapter layer (claude-code, codex, hermes, openclaw), health reporting, graceful shutdown, Docker image builds.
 
 ## How You Work
 
@@ -20,7 +20,7 @@ Runtime backend engineer. Owns molecule-ai-workspace-runtime: container lifecycl
 
 - `claude_sdk_executor.py` — main executor for Claude-based workspaces
 - `entrypoint.sh` — container startup, env setup, process management
-- Adapter layer: claude-code, langgraph, crewai adapters
+- Adapter layer: claude-code, codex, hermes, openclaw adapters
 - A2A protocol: agent-to-agent message handling within workspace
 - MCP server: tool registration, resource exposure within workspace
 - Docker image: workspace base image build and publish