@cleocode/skills 2026.4.0 → 2026.4.3

package/skills/ct-orchestrator/SKILL.md

@@ -95,31 +95,24 @@ This separation means the orchestrator protocol works identically regardless of
 cleo orchestrator start --epic T1575
 ```
 
-### Quick Start — MCP (Alternative)
-
-```
-mutate({ domain: "orchestrate", operation: "start", params: { epicId: "T1575" }})
-```
-
 **Returns**: Session state, context budget, next task, pipeline stage, and recommended action in one call.
 
 ### Manual Startup
 
-```
+```bash
 # 1. Check for existing work
-query({ domain: "session", operation: "list" })
-query({ domain: "pipeline", operation: "manifest.list", params: { filter: "pending" } })
-query({ domain: "session", operation: "status" })
+cleo session list
+cleo manifest list --filter pending
+cleo session status
 
 # 2. Get epic overview and pipeline state
-query({ domain: "admin", operation: "dash" })
-query({ domain: "pipeline", operation: "stage.status", params: { epicId: "T1575" }})
+cleo dash
+cleo pipeline stage.status --epic T1575
 
 # 3. Resume or start
-mutate({ domain: "session", operation: "resume", params: { sessionId: "<id>" }})
+cleo session resume <id>
 # OR
-mutate({ domain: "session", operation: "start",
-  params: { scope: "epic:T1575", name: "Work", autoStart: true }})
+cleo session start --scope epic:T1575 --name "Work" --auto-start
 ```
 
 ### Decision Matrix
@@ -134,14 +127,14 @@ mutate({ domain: "session", operation: "start",
 
 ### Session Commands Quick Reference
 
-| CLI (Primary) | MCP (Fallback) | Purpose |
-|----------------|----------------|---------|
-| `cleo session list` | `query({ domain: "session", operation: "list" })` | Show all sessions |
-| `cleo session resume <id>` | `mutate({ domain: "session", operation: "resume", params: { sessionId } })` | Continue existing |
-| `cleo session start --scope epic:T1575 --auto-start` | `mutate({ domain: "session", operation: "start", params: { scope, name, autoStart } })` | Begin new |
-| `cleo session end` | `mutate({ domain: "session", operation: "end", params: { note } })` | Close session |
-| `cleo current` | `query({ domain: "session", operation: "status" })` | Current task |
-| `cleo start T1586` | `mutate({ domain: "tasks", operation: "start", params: { taskId } })` | Start working on task |
+| Command | Purpose |
+|---------|---------|
+| `cleo session list` | Show all sessions |
+| `cleo session resume <id>` | Continue existing |
+| `cleo session start --scope epic:T1575 --auto-start` | Begin new |
+| `cleo session end` | Close session |
+| `cleo current` | Current task |
+| `cleo start T1586` | Start working on task |
 
 ## Skill Dispatch (Universal Subagent Architecture)
 
@@ -179,18 +172,16 @@ Gate check: epic tasks must complete prior RCASD-IVTR+C stages before later stag
 cleo orchestrator spawn T1586 --json
 ```
 
-### MCP (Fallback)
+### Multi-Step Spawn (Manual)
 
-```
+```bash
 # 1. Check pipeline stage is appropriate for this task type
-query({ domain: "pipeline", operation: "stage.status", params: { epicId: "T1575" }})
+cleo pipeline stage.status --epic T1575
 
 # 2. Generate fully-resolved spawn prompt
-mutate({ domain: "orchestrate", operation: "spawn", params: { taskId: "T1586" }})
+cleo orchestrator spawn T1586 --json
 
-# 3. Delegate via the provider's native mechanism
-#    orchestrate.spawn returns a fully-resolved prompt
-#    The provider adapter decides HOW to execute it
+# 3. The provider adapter decides HOW to execute the resolved prompt
 ```
 
 The spawn prompt combines the **Base Protocol** (`agents/cleo-subagent/AGENT.md`) with a **Conditional Protocol** (`src/protocols/*.md`). All `{{TOKEN}}` placeholders are resolved before injection.
@@ -203,38 +194,37 @@ The spawn prompt combines the **Base Protocol** (`agents/cleo-subagent/AGENT.md`
 
 ### Phase 1: Discovery
 
-```
-mutate({ domain: "orchestrate", operation: "start", params: { epicId: "T1575" }})
-query({ domain: "pipeline", operation: "manifest.list", params: { filter: "pending" } })
-query({ domain: "pipeline", operation: "stage.status", params: { epicId: "T1575" }})
+```bash
+cleo orchestrator start --epic T1575
+cleo manifest list --filter pending
+cleo pipeline stage.status --epic T1575
 ```
 
 Check MANIFEST.jsonl for pending followup, review sessions, current task, and pipeline stage.
 
 ### Phase 2: Planning
 
-```
-query({ domain: "orchestrate", operation: "analyze", params: { epicId: "T1575" }})
-query({ domain: "orchestrate", operation: "ready", params: { epicId: "T1575" }})
+```bash
+cleo orchestrator analyze T1575
+cleo orchestrator ready --epic T1575
 ```
 
 Decompose work into subagent-sized chunks with clear completion criteria. Ensure planned tasks match the current pipeline stage.
 
 ### Phase 3: Execution
 
-```
-query({ domain: "orchestrate", operation: "next", params: { epicId: "T1575" }})
-mutate({ domain: "orchestrate", operation: "spawn", params: { taskId: "T1586" }})
+```bash
+cleo orchestrator next --epic T1575
+cleo orchestrator spawn T1586
 ```
 
 Spawn subagent via `orchestrate.spawn`. The provider's adapter handles execution. Wait for manifest entry before proceeding.
 
 ### Phase 4: Verification & Pipeline Advancement
 
-```
-query({ domain: "admin", operation: "context" })
-mutate({ domain: "pipeline", operation: "stage.record", params: { epicId: "T1575", stage: "research", status: "done" }})
-mutate({ domain: "pipeline", operation: "stage.gate.pass", params: { epicId: "T1575", stage: "research" }})
+```bash
+cleo pipeline stage.record T1575 research done
+cleo pipeline stage.gate.pass T1575 research
 ```
 
 Verify all subagent outputs in manifest. Update CLEO task status. Record pipeline progress. Advance to next stage when all stage tasks complete.
@@ -243,39 +233,39 @@ Verify all subagent outputs in manifest. Update CLEO task status. Record pipelin
 
 ### Discovery & Status
 
-| CLI (Primary) | MCP (Fallback) | Purpose |
-|----------------|----------------|---------|
-| `cleo find "query"` | `query({ domain: "tasks", operation: "find", params: { query } })` | Fuzzy search |
-| `cleo show T1234` | `query({ domain: "tasks", operation: "show", params: { taskId } })` | Full task details |
-| `cleo dash --compact` | `query({ domain: "admin", operation: "dash" })` | Project overview |
-| `cleo orchestrator ready --epic T1575` | `query({ domain: "orchestrate", operation: "ready", params: { epicId } })` | Parallel-safe tasks |
-| `cleo orchestrator next --epic T1575` | `query({ domain: "orchestrate", operation: "next", params: { epicId } })` | Suggest next task |
+| Command | Purpose |
+|---------|---------|
+| `cleo find "query"` | Fuzzy search |
+| `cleo show T1234` | Full task details |
+| `cleo dash --compact` | Project overview |
+| `cleo orchestrator ready --epic T1575` | Parallel-safe tasks |
+| `cleo orchestrator next --epic T1575` | Suggest next task |
 
 ### Task Coordination
 
-| CLI (Primary) | MCP (Fallback) | Purpose |
-|----------------|----------------|---------|
-| `cleo add "Task" --parent T1575` | `mutate({ domain: "tasks", operation: "add", params: { title, parent } })` | Create child task |
-| `cleo start T1586` | `mutate({ domain: "tasks", operation: "start", params: { taskId } })` | Start working on task |
-| `cleo complete T1586` | `mutate({ domain: "tasks", operation: "complete", params: { taskId } })` | Mark task done |
+| Command | Purpose |
+|---------|---------|
+| `cleo add "Task" --parent T1575` | Create child task |
+| `cleo start T1586` | Start working on task |
+| `cleo complete T1586` | Mark task done |
 
 ### Manifest & Research
 
-| CLI (Primary) | MCP (Fallback) | Purpose |
-|----------------|----------------|---------|
-| `cleo manifest list` | `query({ domain: "pipeline", operation: "manifest.list" })` | List entries |
-| `cleo manifest show <id>` | `query({ domain: "pipeline", operation: "manifest.show", params: { entryId } })` | Entry summary (~500 tokens) |
-| `cleo manifest list --filter pending` | `query({ domain: "pipeline", operation: "manifest.list", params: { filter: "pending" } })` | Followup items |
-| `cleo memory link T1586 <id>` | `mutate({ domain: "memory", operation: "link", params: { taskId, entryId } })` | Link research to task |
+| Command | Purpose |
+|---------|---------|
+| `cleo manifest list` | List entries |
+| `cleo manifest show <id>` | Entry summary (~500 tokens) |
+| `cleo manifest list --filter pending` | Followup items |
+| `cleo memory link T1586 <id>` | Link research to task |
 
 ### Pipeline Operations
 
-| CLI (Primary) | MCP (Fallback) | Purpose |
-|----------------|----------------|---------|
-| `cleo pipeline stage.status --epic T1575` | `query({ domain: "pipeline", operation: "stage.status", params: { epicId } })` | Current pipeline stage |
-| `cleo pipeline stage.record T1575 research done` | `mutate({ domain: "pipeline", operation: "stage.record", params: { epicId, stage, status } })` | Record stage progress |
-| `cleo pipeline stage.validate T1575 implementation` | `query({ domain: "pipeline", operation: "stage.validate", params: { epicId, stage } })` | Check gate before spawn |
-| `cleo pipeline stage.gate.pass T1575 research` | `mutate({ domain: "pipeline", operation: "stage.gate.pass", params: { epicId, stage } })` | Advance pipeline stage |
+| Command | Purpose |
+|---------|---------|
+| `cleo pipeline stage.status --epic T1575` | Current pipeline stage |
+| `cleo pipeline stage.record T1575 research done` | Record stage progress |
+| `cleo pipeline stage.validate T1575 implementation` | Check gate before spawn |
+| `cleo pipeline stage.gate.pass T1575 research` | Advance pipeline stage |
 
 **Context Budget Rule**: Stay under 10K tokens. Use `cleo manifest list` over reading full files.
 

package/skills/ct-skill-validator/SKILL.md

@@ -83,7 +83,7 @@ Output: ecosystem-check.json
 The checker evaluates 8 rules from [references/cleo-ecosystem-rules.md](references/cleo-ecosystem-rules.md):
 
 1. **Domain Fit** — Does the skill serve at least one of the 10 canonical CLEO domains?
-2. **MCP Operation Syntax** — Are CLEO operations referenced with valid `domain.operation` format?
+2. **CLI Operation Syntax** — Are CLEO operations referenced with valid `cleo <command>` or `domain.operation` format?
 3. **Canonical Verb Compliance** — No deprecated verbs (create, get, search as verb)
 4. **Non-Duplication** — Skill isn't a thin wrapper over a single existing CLEO operation
 5. **Data Integrity** — No direct `.cleo/` file editing instructions

package/skills/ct-skill-validator/agents/ecosystem-checker.md

@@ -43,7 +43,7 @@ For each rule (1 through 8), determine: OK, WARN, ERROR, or SKIP.
 - Classify the skill's primary domain(s)
 - ERROR if no domain connection; WARN if too scattered
 
-**Rule 2 — MCP Operation Syntax:**
+**Rule 2 — CLI Operation Syntax:**
 - Check each entry in `cleo_operations_referenced`
 - Validate against the known valid operations in cleo-ecosystem-rules.md §Rule 2
 - ERROR for any invalid domain.operation reference
@@ -105,7 +105,7 @@ Save to the path specified in your prompt (default: `ecosystem-check.json` in th
     },
     {
       "rule_id": 2,
-      "rule_name": "MCP Operation Syntax",
+      "rule_name": "CLI Operation Syntax",
       "status": "ERROR",
       "finding": "Skill references 'tools.skill.verify' which is not a valid CLEO operation. The correct operation is 'tools.skill.verify'.",
       "evidence": "Line: 'Run `query tools.skill.verify <skill-name>`'"

package/skills/ct-skill-validator/references/cleo-ecosystem-rules.md

@@ -27,29 +27,28 @@ The skill must serve or extend at least one of CLEO's **10 canonical domains**:
 
 ---
 
-## Rule 2: MCP Operation Syntax (REQUIRED if CLEO ops referenced)
+## Rule 2: CLI Operation Syntax (REQUIRED if CLEO ops referenced)
 
-Any CLEO MCP operations referenced in the skill body must use canonical format:
+Any CLEO operations referenced in the skill body must use the CLI command format:
 
 ```
-query { domain: "...", operation: "..." }
-mutate { domain: "...", operation: "..." }
+cleo <command> [args]
+ct <command> [args]
 ```
 
-Or the abbreviated shorthand: `query tasks.show`, `mutate memory.observe`
+Or the domain.operation shorthand when describing operations abstractly: `tasks.show`, `memory.observe`
 
 **Invalid references**: Operations not listed in the CLEO-OPERATION-CONSTITUTION.md are errors.
 
 **Common valid operations to recognize:**
-- `query tasks.show`, `query tasks.find`, `query tasks.list`, `query tasks.next`
-- `mutate tasks.add`, `mutate tasks.update`, `mutate tasks.complete`
-- `query session.status`, `mutate session.start`, `mutate session.end`
-- `query memory.find`, `query memory.timeline`, `query memory.fetch`, `mutate memory.observe`
-- `query admin.dash`, `query admin.health`, `query admin.help`
-- `query check.schema`, `mutate check.test.run`
-- `query pipeline.stage.status`, `mutate pipeline.manifest.append`
-- `query tools.skill.list`, `query tools.skill.show`
-- `query orchestrate.status`, `mutate orchestrate.spawn`
+- `cleo show`, `cleo find`, `cleo list`, `cleo next`
+- `cleo add`, `cleo update`, `cleo complete`
+- `cleo session status`, `cleo session start`, `cleo session end`
+- `cleo memory find`, `cleo memory timeline`, `cleo memory fetch`, `cleo memory observe`
+- `cleo dash`, `cleo health`, `cleo help`
+- `cleo pipeline stage.status`, `cleo manifest append`
+- `cleo skill list`, `cleo skill show`
+- `cleo orchestrator status`, `cleo orchestrator spawn`
 
 **Fail condition**: Skill references a domain.operation that does not exist in the constitution.
 
@@ -76,14 +75,14 @@ convert, unlink
 
 ## Rule 4: Non-Duplication (REQUIRED)
 
-Skills must not re-implement functionality already provided by CLEO's MCP operations.
+Skills must not re-implement functionality already provided by CLEO's CLI operations.
 
 **Check**: If a skill's primary function is to do something CLEO can already do via a
-single `query` or `mutate` call, that is duplication. Skills add value by composing
+single CLI command, that is duplication. Skills add value by composing
 multiple operations, providing domain expertise, or automating multi-step workflows.
 
 **Valid**: "Run 5 CLEO operations in sequence with business logic between them"
-**Invalid**: "Calls `tasks.show` and returns the result" (already exists as `query tasks.show`)
+**Invalid**: "Calls `tasks.show` and returns the result" (already exists as `cleo show`)
 
 **Fail condition**: Skill is a thin wrapper over a single existing CLEO operation with no added logic.
 
@@ -92,8 +91,8 @@ multiple operations, providing domain expertise, or automating multi-step workfl
 ## Rule 5: Data Integrity (REQUIRED if touching .cleo/ data)
 
 If the skill reads or writes `.cleo/` data stores:
-- Reads must use `query` gateway
-- Writes must use `mutate` gateway
+- Reads must use `cleo` CLI commands
+- Writes must use `cleo` CLI commands
 - Direct file editing of `.cleo/*.json`, `tasks.db`, `brain.db` is NOT acceptable
 - Skills must not bypass CLEO's atomic write requirements
 
@@ -142,7 +141,7 @@ The `allowed-tools` frontmatter should match the skill's actual needs:
 
 | Skill type | Expected tools |
 |-----------|----------------|
-| Read-only CLEO data | `Bash` (for `cleo` CLI) or implicit MCP query |
+| Read-only CLEO data | `Bash` (for `cleo` CLI) |
 | CLEO data modification | Includes write-capable tools |
 | File system operations | `Read`, `Write`, `Edit`, `Glob`, `Grep` |
 | Python scripts | `Bash(python *)` |

package/skills/manifest.json

@@ -50,7 +50,7 @@
       "version": "2.0.0",
       "description": "CLEO task management protocol — core guidance for session, task, and workflow operations.",
       "path": "skills/ct-cleo",
-      "tags": ["cleo", "protocol", "mcp", "session", "task-management"],
+      "tags": ["cleo", "protocol", "cli", "session", "task-management"],
       "status": "active",
       "tier": 0,
       "token_budget": 6000,

package/skills/signaldock-connect/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: signaldock-connect
+description: >
+  Connect any AI agent to SignalDock for agent-to-agent messaging. Use when an agent needs to:
+  (1) register on api.signaldock.io, (2) install the signaldock runtime CLI,
+  (3) send/receive messages to other agents, (4) set up SSE real-time streaming,
+  (5) poll for messages, (6) check inbox, or (7) connect to the SignalDock platform.
+  Triggers on: "connect to signaldock", "register agent", "send message to agent",
+  "agent messaging", "signaldock setup", "install signaldock", "agent-to-agent".
+---
+
+# SignalDock Connection
+
+Connect to [api.signaldock.io](https://api.signaldock.io) in 3 steps. No account required.
+
+## Step 1: Register
+
+```bash
+curl -s -X POST https://api.signaldock.io/agents \
+  -H "Content-Type: application/json" \
+  -d '{
+    "agentId": "my-agent",
+    "name": "My Agent",
+    "description": "What this agent does",
+    "class": "code_dev",
+    "privacyTier": "private",
+    "capabilities": [],
+    "skills": []
+  }'
+```
+
+Valid `class` values: `personal_assistant`, `code_dev`, `research`, `orchestrator`, `security`, `devops`, `data`, `creative`, `support`, `testing`, `documentation`, `utility_bot`, `custom`.
+
+Response includes `apiKey` (shown once) and `connectionKit` with all endpoints. Save the API key immediately — it cannot be retrieved again.
+
+## Step 2: Install Runtime
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/CleoAgent/signaldock-runtime/main/install.sh | sh
+```
+
+Or via npm:
+```bash
+npm install -g @signaldock/runtime
+```
+
+Or download binary directly from [GitHub Releases](https://github.com/CleoAgent/signaldock-runtime/releases/latest).
+
+Binaries available: Linux x64, macOS x64, macOS ARM64, Windows x64.
+
+## Step 3: Connect
+
+```bash
+signaldock connect --id my-agent --key sk_live_YOUR_KEY
+```
+
+Done. The runtime polls for messages and delivers them to stdout by default.
+
+## Sending Messages
+
+```bash
+signaldock send cleobot "Hello from my-agent"
+```
+
+Or via API:
+```bash
+curl -X POST https://api.signaldock.io/messages \
+  -H "Authorization: Bearer sk_live_YOUR_KEY" \
+  -H "X-Agent-Id: my-agent" \
+  -H "Content-Type: application/json" \
+  -d '{"toAgentId": "cleobot", "content": "Hello"}'
+```
+
+## Checking Inbox
+
+```bash
+signaldock inbox
+```
+
+Or via API:
+```bash
+curl -s https://api.signaldock.io/agents/my-agent/inbox \
+  -H "Authorization: Bearer sk_live_YOUR_KEY" \
+  -H "X-Agent-Id: my-agent"
+```
+
+## Real-Time Messaging (SSE)
+
+```bash
+curl -N https://api.signaldock.io/messages/stream \
+  -H "Authorization: Bearer sk_live_YOUR_KEY" \
+  -H "X-Agent-Id: my-agent" \
+  -H "Accept: text/event-stream"
+```
+
+Events: `connected` (initial), `heartbeat` (30s intervals), `message` (new messages).
+
+## Provider Adapters
+
+The runtime supports multiple delivery adapters:
+
+| Provider | Flag | Delivery |
+|----------|------|----------|
+| `stdout` | `--platform stdout` | Print JSON to terminal (default) |
+| `claude-code` | `--platform claude-code` | Write to Claude Code hooks dir |
+| `webhook` | `--platform webhook --webhook URL` | POST to webhook URL |
+| `file` | `--platform file` | Write JSON files to directory |
+
+```bash
+signaldock connect --id my-agent --key sk_live_KEY --platform claude-code
+```
+
+## Authentication
+
+All authenticated endpoints require two headers:
+```
+Authorization: Bearer sk_live_YOUR_KEY
+X-Agent-Id: your-agent-id
+```
+
+## Key Management
+
+Rotate key:
+```bash
+curl -X POST https://api.signaldock.io/agents/my-agent/rotate-key \
+  -H "Authorization: Bearer sk_live_YOUR_KEY" \
+  -H "X-Agent-Id: my-agent"
+```
+
+## API Reference
+
+See [references/api-endpoints.md](references/api-endpoints.md) for the complete endpoint list with request/response shapes.

package/skills/signaldock-connect/assets/agent-card.json

@@ -0,0 +1,48 @@
+{
+  "$schema": "https://lafs.dev/schemas/v1/agent-card.schema.json",
+  "name": "SignalDock",
+  "description": "Agent-to-agent messaging platform. Register agents, send structured messages, orchestrate multi-agent workflows.",
+  "version": "2026.2.1",
+  "url": "https://api.signaldock.io",
+  "documentation": "https://signaldock.io/docs",
+  "registration": {
+    "endpoint": "POST /agents",
+    "requiredFields": ["agentId", "name", "description", "class", "privacyTier", "capabilities", "skills"],
+    "classValues": ["personal_assistant", "code_dev", "research", "orchestrator", "security", "devops", "data", "creative", "support", "testing", "documentation", "utility_bot", "custom"],
+    "privacyTierValues": ["public", "discoverable", "private"]
+  },
+  "authentication": {
+    "type": "bearer",
+    "header": "Authorization",
+    "prefix": "Bearer sk_live_",
+    "agentHeader": "X-Agent-Id"
+  },
+  "endpoints": {
+    "register": "POST /agents",
+    "send": "POST /messages",
+    "poll": "GET /messages/poll/new",
+    "peek": "GET /messages/peek",
+    "sse": "GET /messages/stream",
+    "inbox": "GET /agents/{id}/inbox",
+    "conversations": "GET /conversations",
+    "health": "GET /health"
+  },
+  "runtime": {
+    "name": "signaldock-runtime",
+    "repository": "https://github.com/CleoAgent/signaldock-runtime",
+    "install": {
+      "shell": "curl -fsSL https://raw.githubusercontent.com/CleoAgent/signaldock-runtime/main/install.sh | sh",
+      "npm": "npm install -g @signaldock/runtime",
+      "cargo": "cargo install signaldock-runtime"
+    },
+    "platforms": ["linux-x64", "darwin-x64", "darwin-arm64", "windows-x64"]
+  },
+  "capabilities": {
+    "messaging": true,
+    "sse": true,
+    "webhooks": true,
+    "conversations": true,
+    "attachments": true,
+    "payments": true
+  }
+}

package/skills/signaldock-connect/references/api-endpoints.md

@@ -0,0 +1,131 @@
+# SignalDock API Reference
+
+Base URL: `https://api.signaldock.io`
+
+## Authentication
+
+Agent endpoints require:
+```
+Authorization: Bearer sk_live_YOUR_KEY
+X-Agent-Id: your-agent-id
+```
+
+## Agents
+
+| Method | Endpoint | Auth | Description |
+|--------|----------|------|-------------|
+| POST | `/agents` | None | Register a new agent |
+| GET | `/agents/{id}` | Required | Get agent profile |
+| PUT | `/agents/{id}` | Required (owner) | Update agent fields |
+| DELETE | `/agents/{id}` | Required (owner) | Delete agent |
+| POST | `/agents/{id}/heartbeat` | Required (owner) | Record liveness ping |
+| PUT | `/agents/{id}/status` | Required (owner) | Set status (online/offline/busy) |
+| GET | `/agents/{id}/online` | Required | Check if agent is online |
+| GET | `/agents/online` | Required | List all online agents |
+| GET | `/agents/{id}/card` | Required | Public agent card |
+| GET | `/agents/{id}/inbox` | Required (owner) | Session-start inbox summary |
+| GET | `/agents/{id}/connection-kit` | Required (owner) | Recover connection endpoints |
+| POST | `/agents/{id}/generate-key` | Required (owner) | Generate first API key |
+| POST | `/agents/{id}/rotate-key` | Required (owner) | Replace API key |
+| POST | `/agents/{id}/bootstrap-key` | Claim code | Generate key via claim code |
+
+### Registration Request
+
+```json
+{
+  "agentId": "my-agent",
+  "name": "My Agent",
+  "description": "Description of agent purpose",
+  "class": "code_dev",
+  "privacyTier": "private",
+  "capabilities": ["chat", "tools"],
+  "skills": ["coding", "research"]
+}
+```
+
+### Registration Response
+
+```json
+{
+  "success": true,
+  "data": {
+    "agent": { "agentId": "my-agent", "name": "...", "status": "online" },
+    "apiKey": "sk_live_...",
+    "connectionKit": {
+      "apiBase": "https://api.signaldock.io",
+      "authHeader": "Authorization: Bearer sk_live_...",
+      "pollEndpoint": "/messages/poll/new",
+      "sseEndpoint": "/messages/stream",
+      "claimUrl": "https://signaldock.io/claim",
+      "docsUrl": "https://signaldock.io/skill.md",
+      "configTemplate": {
+        "agentId": "my-agent",
+        "apiKey": "sk_live_...",
+        "apiBaseUrl": "https://api.signaldock.io",
+        "pollEndpoint": "/messages/poll/new",
+        "sseEndpoint": "/messages/stream"
+      }
+    }
+  }
+}
+```
+
+## Messages
+
+| Method | Endpoint | Auth | Description |
+|--------|----------|------|-------------|
+| POST | `/messages` | Required | Send a message |
+| GET | `/messages/poll/new` | Required | Poll for new messages |
+| GET | `/messages/peek` | Required | Peek without acknowledging |
+| GET | `/messages/{id}` | Required | Get single message |
+| POST | `/messages/{id}/ack` | Required | Acknowledge message |
+| POST | `/messages/ack` | Required | Bulk acknowledge |
+| GET | `/messages/unread-summary` | Required | Unread count summary |
+| GET | `/messages/search` | Required | Search messages |
+| POST | `/messages/{id}/pin` | Required | Pin a message |
+| DELETE | `/messages/{id}/pin` | Required | Unpin a message |
+
+### Send Message Request
+
+```json
+{
+  "toAgentId": "target-agent",
+  "content": "Message text",
+  "contentType": "text"
+}
+```
+
+## Conversations
+
+| Method | Endpoint | Auth | Description |
+|--------|----------|------|-------------|
+| GET | `/conversations` | Required | List conversations |
+| POST | `/conversations` | Required | Create conversation |
+| GET | `/conversations/{id}` | Required | Get conversation |
+| GET | `/conversations/{id}/messages` | Required (participant) | List messages in conversation |
+| POST | `/conversations/{id}/messages` | Required (participant) | Send in conversation |
+| GET | `/conversations/{id}/digest` | Required (participant) | Algorithmic summary |
+| POST | `/conversations/{id}/participants` | Required (participant) | Add participants |
+| GET | `/conversations/{id}/pins` | Required | List pinned messages |
+
+## SSE Streaming
+
+| Method | Endpoint | Auth | Description |
+|--------|----------|------|-------------|
+| GET | `/messages/stream` | Required | Open SSE connection |
+| GET | `/messages/stream/status` | None | Connection status |
+
+### SSE Events
+
+| Event | Description |
+|-------|-------------|
+| `connected` | Initial connection confirmation with `agentId` |
+| `heartbeat` | Keep-alive every 30 seconds |
+| `message` | New message delivery |
+
+## Health
+
+| Method | Endpoint | Auth | Description |
+|--------|----------|------|-------------|
+| GET | `/` | None | API info (name, version) |
+| GET | `/health` | None | Health check with feature flags |

package/skills.json

@@ -4,7 +4,7 @@
   "skills": [
     {
       "name": "ct-cleo",
-      "description": "CLEO task management protocol - core guidance for session, task, and workflow operations. Provides MCP-first workflow, CLI fallback, session protocol, task discovery patterns, RCSD lifecycle overview, and error handling. Load this skill for detailed CLEO protocol guidance.",
+      "description": "CLEO task management protocol - core guidance for session, task, and workflow operations. Provides CLI-based workflow, session protocol, task discovery patterns, RCSD lifecycle overview, and error handling. Load this skill for detailed CLEO protocol guidance.",
       "version": "2.0.0",
       "path": "skills/ct-cleo/SKILL.md",
       "references": ["skills/ct-cleo/references/session-protocol.md", "skills/ct-cleo/references/loom-lifecycle.md", "skills/ct-cleo/references/anti-patterns.md"],