Introduced AAP server in SRE plugins

.claude-plugin/marketplace.json

@@ -18,7 +18,7 @@
       },
       "source": "./rh-sre",
       "category": "sre",
-      "agents": "./agents/remediator.md",
+      "agents": [],
       "skills": "./skills"
     },
     {

.claude/skills/skill-linter/scripts/validate-skill.sh

@@ -61,14 +61,15 @@ pass "SKILL.md exists"
 # 3. Extract frontmatter
 CONTENT=$(cat "$SKILL_FILE")
 
-# Check for frontmatter delimiters
-if ! echo "$CONTENT" | head -1 | grep -q '^---$'; then
+# Check for frontmatter delimiters (read from file to avoid broken pipe with set -o pipefail)
+FIRST_LINE=$(head -1 "$SKILL_FILE")
+if [ "$FIRST_LINE" != "---" ]; then
   fail "Missing frontmatter opening delimiter (---)"
   exit 2
 fi
 
-# Find closing delimiter (skip first line)
-CLOSING_LINE=$(echo "$CONTENT" | tail -n +2 | grep -n '^---$' | head -1 | cut -d: -f1)
+# Find closing delimiter (skip first line) - use awk to avoid broken pipe (head -1 exits early)
+CLOSING_LINE=$(awk 'NR>1 && /^---$/{print NR-1; exit}' "$SKILL_FILE")
 if [ -z "$CLOSING_LINE" ]; then
   fail "Missing frontmatter closing delimiter (---)"
   exit 2
@@ -172,7 +173,7 @@ if [ -n "$TOOLS" ]; then
 fi
 # FAIL if YAML multi-line array detected (allowed-tools:\n  - item)
 if echo "$FRONTMATTER" | grep -q '^allowed-tools:$'; then
-  NEXT_LINE=$(echo "$FRONTMATTER" | grep -A1 '^allowed-tools:$' | tail -1)
+  NEXT_LINE=$(echo "$FRONTMATTER" | grep -A1 '^allowed-tools:$' | sed -n '2p')
   if echo "$NEXT_LINE" | grep -qE '^[[:space:]]*-[[:space:]]'; then
     fail "allowed-tools must be space-delimited, not YAML array"
   fi
@@ -215,15 +216,15 @@ fi
 # 10. Content analysis - strip fenced code blocks for checks that need prose-only content
 CONTENT_NO_FENCES=$(awk '/^```/{skip=!skip; next} !skip{print}' "$SKILL_FILE")
 
-# 10a. Check for ASCII art outside fenced code blocks (WARN)
-if echo "$CONTENT_NO_FENCES" | grep -qE '[─│┌┐└┘├┤┬┴┼╭╮╯╰═║╔╗╚╝╠╣╦╩╬↑↓←→↔⇒⇐⇔▲▼◄►]{3,}'; then
+# 10a. Check for ASCII art outside fenced code blocks (WARN) - grep (no -q) reads full input to avoid broken pipe
+if grep -E '[─│┌┐└┘├┤┬┴┼╭╮╯╰═║╔╗╚╝╠╣╦╩╬↑↓←→↔⇒⇐⇔▲▼◄►]{3,}' <<< "$CONTENT_NO_FENCES" > /dev/null; then
   warn "ASCII art detected outside code blocks - use plain lists or tables"
 else
   pass "No ASCII art outside code blocks"
 fi
 
 # 10b. Check for persona statements outside fenced code blocks (FAIL)
-if echo "$CONTENT_NO_FENCES" | grep -qiE '^[[:space:]]*You are (a|an|the) '; then
+if grep -iE '^[[:space:]]*You are (a|an|the) ' <<< "$CONTENT_NO_FENCES" > /dev/null; then
   fail "Persona statement detected ('You are a/an/the...') - use Audience/Goal framing"
 else
   pass "No persona statements"

.gitattributes

@@ -0,0 +1,6 @@
+# Enforce LF line endings for text files (prevents CRLF issues in CI)
+* text=auto eol=lf
+*.md text eol=lf
+*.sh text eol=lf
+*.yml text eol=lf
+*.yaml text eol=lf

CLAUDE.md

@@ -26,9 +26,7 @@ Each pack follows this structure:
 ├── .claude-plugin/      # Claude Code plugin metadata
 │   └── plugin.json      # Name, version, description, author, license
 ├── .mcp.json           # MCP server configurations (uses env vars for credentials)
-├── agents/             # Multi-step workflow orchestrators
-│   └── <agent>.md      # Agent definition with YAML frontmatter
-├── skills/             # Specialized task executors
+├── skills/             # Specialized task executors (including orchestration skills)
 │   └── <skill>/
 │       └── SKILL.md    # Skill definition with YAML frontmatter
 └── docs/               # AI-optimized knowledge base (rh-sre only currently)
@@ -39,7 +37,7 @@ Each pack follows this structure:
 
 ## Working with Agentic Collections
 
-### Skills vs Agents
+### Skills
 
 **Skills** (`skills/<skill-name>/SKILL.md`):
 - Single-purpose task executors
@@ -48,14 +46,7 @@ Each pack follows this structure:
 - Structure: YAML frontmatter + implementation guide
 - Example: `cve-impact` (CVE risk assessment), `playbook-generator` (Ansible generation)
 
-**Agents** (`agents/<agent>.md`):
-- Multi-step workflow orchestrators
-- Delegate to multiple skills in sequence
-- Invoked via the `Task` tool with `subagent_type`
-- Structure: YAML frontmatter + workflow definition
-- Example: `remediator` (orchestrates 5 skills for end-to-end CVE remediation)
-
-**Key Pattern**: Agents orchestrate skills; skills encapsulate tools. Never call MCP tools directly - always go through skills.
+**Key Pattern**: Skills encapsulate tools; orchestration skills invoke other skills. Never call MCP tools directly - always go through skills. For end-to-end CVE remediation, use the `/remediation` skill which orchestrates 6 specialized skills.
 
 ## Skill and Agent Requirements
 
@@ -151,7 +142,6 @@ last_updated: YYYY-MM-DD
 
 ### Files
 - Skills: `skills/<skill-name>/SKILL.md` (uppercase SKILL.md)
-- Agents: `agents/<agent-name>.md` (lowercase, no folder)
 - Docs: Lowercase with dashes, categorized by directory
 
 ## Development Workflow
@@ -163,8 +153,7 @@ last_updated: YYYY-MM-DD
 3. Create `skills/` directory
 4. Optional: Add `.claude-plugin/plugin.json` for Claude Code
 5. Optional: Add `.mcp.json` for MCP server integrations
-6. Optional: Add `agents/` for multi-step workflows
-7. Update main `README.md` table with link
+6. Update main `README.md` table with link
 
 ### Adding a Skill
 
@@ -221,7 +210,7 @@ last_updated: YYYY-MM-DD
 
 The `rh-sre` pack is the most complete implementation, demonstrating:
 - Full skill orchestration (10 skills)
-- Agent-based workflows (remediator agent)
+- Orchestration skills (remediation skill orchestrates 6 skills)
 - AI-optimized documentation system
 - MCP server integration
 - Red Hat Lightspeed platform integration
@@ -245,7 +234,7 @@ When creating new collections, follow the pattern that best matches your needs:
 
 ### Core Architecture
 1. **Skills encapsulate tools** - Never call MCP tools directly; always invoke skills
-2. **Agents orchestrate skills** - Complex workflows delegate to specialized skills
+2. **Orchestration skills invoke other skills** - Complex workflows delegate to specialized skills; agents orchestrate skills
 3. **agentskills.io compliance** - All skills follow the official specification
 4. **Progressive disclosure** - Load docs incrementally based on task needs
 

SKILL_DESIGN_PRINCIPLES.md

@@ -86,6 +86,7 @@ Delegate to skills, not raw MCP tools.
 
 **✅ Complete Example:**
 ```yaml
+---
 description: |
   Analyze CVE impact without remediation.
 
@@ -94,7 +95,10 @@ description: |
   - "Show CVEs affecting systems"
   - User mentions "CVEs", "vulnerabilities"
 
-  NOT for remediation (use remediator agent instead).
+  NOT for remediation actions (use remediation skill instead).
+model: inherit        # Root: Runtime configuration required before skill execution
+color: blue           # Root: UX - IDE sidebar/terminal theme
+---
 ```
 
 **Rationale**: Minimizes token usage at initialization; prevents skill misuse.
@@ -105,7 +109,53 @@ description: |
 
 Every skill MUST include complete Dependencies section.
 
-**Required Structure:**
+**Standard Color Values** (Cursor, Claude Code):
+
+| Color | Use Case |
+|-------|----------|
+| blue, cyan | Analysis, read-only |
+| green | Success, deployment |
+| yellow | Caution, validation |
+| red | Critical, security, remediation |
+| magenta | Creative, generation |
+
+## 4. Skill-to-Skill Invocation Standard
+
+**Standard format**: Use the slash format `/skill-name` when one skill or agent invokes another.
+
+```markdown
+**How to invoke**: Execute the `/mcp-lightspeed-validator` skill
+**Action**: Execute the `/mcp-aap-validator` skill
+```
+
+**❌ Avoid** - Skill tool format (inconsistent):
+```markdown
+Use the Skill tool:
+  skill: "mcp-lightspeed-validator"
+```
+
+**✅ Use** - Slash format (consistent across rh-sre):
+```markdown
+Execute the `/mcp-lightspeed-validator` skill
+Invoke the `/playbook-executor` skill
+```
+
+**Applies to**:
+- Skill → skill (remediation invokes `/cve-validation`, `/playbook-generator`, etc.)
+- Skill → skill prerequisites (cve-validation invokes `/mcp-lightspeed-validator`)
+- Skill → skill delegation (playbook-generator delegates to `/playbook-executor`)
+
+**Rationale**: Single format across agent and skill invocations improves consistency and reduces confusion.
+
+## 5. Dependencies Declaration
+
+Every skill MUST include a **Dependencies** section listing:
+- **Skills**: Other skills this skill may invoke
+- **MCP Tools**: Specific tools from MCP servers
+- **MCP Servers**: Required MCP server names
+- **Documentation**: Reference docs for context
+
+**Required Format**:
 ```markdown
 ## Dependencies
 
@@ -126,9 +176,7 @@ Every skill MUST include complete Dependencies section.
 
 **Rationale**: Makes dependencies explicit for debugging and troubleshooting.
 
----
-
-### 5. Human-in-the-Loop Requirements
+## 6. Human-in-the-Loop Requirements
 
 Skills performing critical operations MUST require explicit confirmation.
 
@@ -152,15 +200,21 @@ Skills performing critical operations MUST require explicit confirmation.
 2. **Typed Confirmation**
    - Ask: "Type exact resource name to confirm: <name>"
    - Verify exact match, cancel if mismatch
-   - Ask: "Type 'DELETE' to proceed"
-   - Only proceed on exact match
+  - Ask: "Type 'DELETE' to proceed"
+  - Only proceed on exact match
 ```
 
 **Rationale**: Prevents unintended automation; maintains user control; reduces accidental data loss.
 
----
+**When to Use**:
+- Playbook execution (ansible-mcp-server)
+- System modifications (package updates, config changes)
+- Multi-system operations (batch remediation)
+- Data deletion or irreversible actions
+
+## 7. Mandatory Skill Sections
 
-### 6. Mandatory Skill Sections
+Every skill MUST include these sections in order:
 
 **Required Section Order:**
 1. YAML frontmatter
@@ -219,7 +273,7 @@ See Principle #7 for details.
 
 ---
 
-### 7. MCP Server Availability Verification
+## 8. MCP Server Availability Verification
 
 Prerequisites MUST include verification and human notification protocol.
 

docs/app.js

@@ -130,7 +130,7 @@ function createPackCard(pack) {
     }
 
     const titleText = document.createElement('span');
-    titleText.textContent = pack.plugin.name || pack.name;
+    titleText.textContent = pack.plugin.title || pack.plugin.name || pack.name;
     h3.appendChild(titleText);
 
     div.appendChild(h3);
@@ -360,10 +360,11 @@ function handleSearch(event) {
 
     // Filter packs
     const filteredPacks = allPacks.filter(pack => {
-        // Search in pack name, description, skills, agents
+        // Search in pack name, title, description, skills, agents
         const searchText = [
             pack.name,
             pack.plugin.name,
+            pack.plugin.title,
             pack.plugin.description,
             ...pack.skills.map(s => s.name + ' ' + s.description),
             ...pack.agents.map(a => a.name + ' ' + a.description)
@@ -451,7 +452,7 @@ function showPackDetails(packName) {
     titleGroup.className = 'modal-title-group';
 
     const h2 = document.createElement('h2');
-    h2.textContent = pack.plugin.name || pack.name;
+    h2.textContent = pack.plugin?.title || pack.plugin?.name || pack.name;
     titleGroup.appendChild(h2);
 
     // Owner subtitle
@@ -512,6 +513,29 @@ function showPackDetails(packName) {
         header.appendChild(desc);
     }
 
+    // Plugin name field (if different from title)
+    if (pack.plugin.name && pack.plugin.name !== pack.plugin.title) {
+        const pluginNameDiv = document.createElement('div');
+        pluginNameDiv.style.marginTop = '1rem';
+        pluginNameDiv.style.fontSize = '0.9rem';
+        pluginNameDiv.style.color = 'var(--text-muted)';
+
+        const label = document.createElement('strong');
+        label.textContent = 'Plugin name: ';
+        label.style.color = 'var(--text-primary)';
+        pluginNameDiv.appendChild(label);
+
+        const nameCode = document.createElement('code');
+        nameCode.textContent = pack.plugin.name;
+        nameCode.style.backgroundColor = 'rgba(238, 0, 0, 0.1)';
+        nameCode.style.padding = '0.25rem 0.5rem';
+        nameCode.style.borderRadius = '4px';
+        nameCode.style.fontSize = '0.85rem';
+        pluginNameDiv.appendChild(nameCode);
+
+        header.appendChild(pluginNameDiv);
+    }
+
     details.appendChild(header);
 
     // Create modal body

docs/plugins.json

@@ -0,0 +1,17 @@
+{
+  "rh-sre": {
+    "title": "Red Hat SRE Agentic Skills Collection"
+  },
+  "rh-virt": {
+    "title": "Red Hat OpenShift Virtualization Agentic Collection"
+  },
+  "rh-developer": {
+    "title": "Red Hat Developer Agentic Skills Collection"
+  },
+  "ocp-admin": {
+    "title": "Red Hat OpenShift Administration Agentic Skills Collection"
+  },
+  "rh-support-engineer": {
+    "title": "Red Hat Support Engineer Agentic Skills Collection"
+  }
+}

ocp-admin/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
-  "name": "OpenShift Administration Agentic Skills Collection",
+  "name": "ocp-admin",
   "version": "1.0.0",
   "description": "Automation capabilities for OpenShift Container Platform cluster management, workload orchestration, security policies, and operational tasks.",
   "author": {

rh-sre/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
-  "name": "Red Hat SRE Agentic Skills Collection",
+  "name": "rh-sre",
   "version": "1.0.0",
   "description": "Site reliability engineering tools and automation for managing Red Hat platforms and infrastructure.",
   "author": {

rh-sre/.mcp.json

@@ -25,26 +25,18 @@
     },
     "aap-mcp-job-management": {
       "type": "http",
-      "url": "https://${AAP_SERVER}/job_management/mcp",
+      "url": "https://${AAP_MCP_SERVER}/job_management/mcp",
       "headers": {
         "Authorization": "Bearer ${AAP_API_TOKEN}"
       },
-      "env": {
-        "AAP_SERVER": "${AAP_SERVER}",
-        "AAP_API_TOKEN": "${AAP_API_TOKEN}"
-      },
       "description": "Ansible Automation Platform (AAP) job management MCP server for managing job templates, job executions, and workflows"
     },
     "aap-mcp-inventory-management": {
       "type": "http",
-      "url": "https://${AAP_SERVER}/inventory_management/mcp",
+      "url": "https://${AAP_MCP_SERVER}/inventory_management/mcp",
       "headers": {
         "Authorization": "Bearer ${AAP_API_TOKEN}"
       },
-      "env": {
-        "AAP_SERVER": "${AAP_SERVER}",
-        "AAP_API_TOKEN": "${AAP_API_TOKEN}"
-      },
       "description": "Ansible Automation Platform (AAP) inventory management MCP server for managing inventories, hosts, and groups"
     }
   }

rh-sre/DEMO.md

@@ -37,7 +37,7 @@ Tools: <tool1>, <tool2>,...
 Docs: <doc1>, <doc2>, ...
 **** EXECUTION SUMMARY END ****
 """
-Agent, skills and tools names must include the plugin name, as in remediation-agent:remediator. 
+Agent, skills and tools names must include the plugin name, as in sre-agents:remediation. 
 Doc names must include only the folder and the document name, omit everything before the docs/ folder. Example: docs/ansible/cve-remediation-templates.md
 ```