fea: Introduce Lola package manager

.github/gemini-review-prompt.md

@@ -18,7 +18,7 @@ Check the diff against the project rules injected in PROJECT RULES REFERENCE (fr
 - **Skill invocation**: use `/skill-name` slash format, never call MCP tools directly
 - **Human-in-the-Loop**: required for create/delete/modify/restore/execute ops, not for read-only
 - **New packs**: must add pack name to `PACK_DIRS` in `scripts/validate_structure.py`; `docs/data.json` must NOT be committed
-- **Build reminder**: if skills, agents, or `.mcp.json` changed, remind author to run `make validate`
+- **Build reminder**: if skills, agents, or `mcps.json` changed, remind author to run `make validate`
 
 ### 3. Code Quality Issues
 Any bugs, security concerns, logic errors, or broken links (with file:line references).

.github/pull_request_template.md

@@ -17,7 +17,7 @@
 - [ ] New agent
 - [ ] New pack
 - [ ] Update existing skill / agent
-- [ ] MCP server config (`.mcp.json`)
+- [ ] MCP server config (`mcps.json`)
 - [ ] Docs / README
 - [ ] CI / tooling
 

.github/workflows/README.md

@@ -157,7 +157,7 @@ The workflow will:
 
 **Repository structure validation (`make validate`):**
 - ✅ Collection directory structure and naming conventions
-- ✅ Required files presence (README.md, .mcp.json, etc.)
+- ✅ Required files presence (README.md, mcps.json, etc.)
 - ✅ Plugin metadata completeness
 - ✅ MCP server configurations
 
@@ -199,7 +199,7 @@ The workflow will fail and provide:
 3. Reference to SKILL_DESIGN_PRINCIPLES.md
 
 **Common validation errors**:
-- Missing required collection files (README.md, .mcp.json)
+- Missing required collection files (README.md, mcps.json)
 - Invalid MCP server configuration syntax
 - Skills not following design principles (see SKILL_DESIGN_PRINCIPLES.md)
 - Missing documentation in collections

.gitleaks.toml

@@ -11,9 +11,9 @@ useDefault = true
 # Custom rules for project-specific patterns
 [[rules]]
 id = "mcp-hardcoded-credentials"
-description = "Hardcoded credentials in .mcp.json files (must use ${ENV_VAR} pattern)"
+description = "Hardcoded credentials in mcps.json files (must use ${ENV_VAR} pattern)"
 regex = '''["'](?:LIGHTSPEED_CLIENT_ID|LIGHTSPEED_CLIENT_SECRET|API_KEY|SECRET|TOKEN|PASSWORD)["']\s*:\s*["'][^"']{8,}["']'''
-path = '''\.mcp\.json$'''
+path = '''\.(mcp|mcps)\.json$'''
 tags = ["mcp", "credentials"]
 
 [[rules]]

CLAUDE.md

@@ -19,23 +19,25 @@ agentic-collections/
 
 ### Agentic Pack Architecture
 
+Packs follow the [Lola](https://github.com/RedHatProductSecurity/lola) package manager format. Install via `lola install -f <pack-name>` from the marketplace.
+
 Each pack follows this structure:
 ```
 <pack-name>/
 ├── CLAUDE.md            # Claude Code instruction routing (persona, skills, rules)
 ├── README.md            # Pack description, persona, target marketplaces
-├── .claude-plugin/      # Claude Code plugin metadata
-│   └── plugin.json      # Name, version, description, author, license
-├── .mcp.json           # MCP server configurations (uses env vars for credentials)
-├── skills/             # Specialized task executors (including orchestration skills)
+├── mcps.json            # MCP server configurations (uses env vars for credentials)
+├── skills/              # Specialized task executors (including orchestration skills)
 │   └── <skill>/
-│       └── SKILL.md    # Skill definition with YAML frontmatter
-└── docs/               # AI-optimized knowledge base (rh-sre only currently)
-    ├── INDEX.md        # Documentation map and AI discovery guide
-    ├── SOURCES.md      # Official Red Hat source attributions
-    └── .ai-index/      # Semantic indexing for token optimization
+│       └── SKILL.md     # Skill definition with YAML frontmatter
+└── docs/                # AI-optimized knowledge base (rh-sre only currently)
+    ├── INDEX.md         # Documentation map and AI discovery guide
+    ├── SOURCES.md       # Official Red Hat source attributions
+    └── .ai-index/       # Semantic indexing for token optimization
 ```
 
+Optional (not required for Lola): `.claude-plugin/plugin.json` — Claude Code plugin metadata if you publish this pack through the Claude Code plugin format in addition to Lola.
+
 ## Working with Agentic Collections
 
 ### Skills
@@ -72,7 +74,7 @@ Each pack follows this structure:
 
 ### MCP Server Integration
 
-MCP servers are configured in `<pack>/.mcp.json`:
+MCP servers are configured in `<pack>/mcps.json`:
 ```json
 {
   "mcpServers": {
@@ -153,9 +155,10 @@ last_updated: YYYY-MM-DD
 2. Add `README.md` with description, persona, marketplaces
 3. Add `CLAUDE.md` with persona, skill-first rule, intent routing table, MCP servers, and global rules (see [rh-ai-engineer/CLAUDE.md](rh-ai-engineer/CLAUDE.md) for reference)
 4. Create `skills/` directory
-5. Optional: Add `.claude-plugin/plugin.json` for Claude Code
-6. Optional: Add `.mcp.json` for MCP server integrations
-7. Update main `README.md` table with link
+5. Add `mcps.json` when the pack integrates MCP servers (use `${VAR}` for secrets)
+6. Register the pack in [`marketplace/rh-agentic-collection.yml`](marketplace/rh-agentic-collection.yml) so `lola install -f <pack-name>` can resolve it
+7. Optional: Add `.claude-plugin/plugin.json` only if publishing via Claude Code’s plugin mechanism
+8. Update main `README.md` table with link
 
 ### Adding a Skill
 
@@ -244,7 +247,7 @@ When creating new collections, follow the pattern that best matches your needs:
 ### Security & Configuration
 5. **Environment variables for secrets** - Never hardcode credentials
 6. **Never expose credential values** - Check env vars are set, but NEVER print their values in output
-7. **MCP server integration** - Use `.mcp.json` with environment variable references
+7. **MCP server integration** - Use `mcps.json` with environment variable references
 
 ### Documentation & Quality
 8. **Official sources only** - Document all sources in SOURCES.md

Makefile

@@ -5,7 +5,7 @@ help:
 	@echo ""
 	@echo "Available targets:"
 	@echo "  install                       - Install Python dependencies (requires uv)"
-	@echo "  validate                      - Validate pack structure (plugin.json, .mcp.json, frontmatter)"
+	@echo "  validate                      - Validate pack structure (mcps.json, CLAUDE.md, frontmatter; plugin.json if present)"
 	@echo "  validate-skill-design         - Validate all skills (use PACK=rh-sre for a specific pack)"
 	@echo "  validate-skill-design-changed - Validate only changed skills (staged + unstaged, for local dev)"
 	@echo "  generate    - Generate docs/data.json"