auto
Automatically converge from goal to A-grade Seed and execute it
Check session status and measure goal drift
$ npx -y skills add Q00/ouroboros --skill status --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/statusContext preview
The summary Claude sees to decide when to auto-load this skill.
Check session status and measure goal drift
name: ouroboros-status description: "Check session status and measure goal drift" aliases: [drift] mcp_tool: ouroboros_session_status mcp_args: session_id: "$1"
Check session status and measure goal drift.
/ouroboros:ouroboros-status [session_id]
**Trigger keywords:** "am I drifting?", "session status", "drift check"
1. **Session Status**: Queries the current state of an execution session 2. **Drift Measurement**: Measures how far the execution has deviated from the original seed goal
When the user invokes this skill:
The Ouroboros MCP tools are often registered as **deferred tools** that must be explicitly loaded before use. **You MUST perform this step before proceeding.**
1. Use the active runtime's tool-discovery capability to find and load the status MCP tools:
tool discovery query: "+ouroboros session status"
2. The tools will typically be named with prefix `mcp__plugin_ouroboros_ouroboros__` (e.g., `ouroboros_session_status`, `ouroboros_measure_drift`). After runtime tool discovery returns, the tools become callable. 3. If the tools are callable — already exposed, or loaded by discovery — proceed with the steps below. An empty discovery result for already-exposed tools is expected, not a failure. Skip to the **Fallback** section only if they are genuinely absent (no Ouroboros MCP server).
**IMPORTANT**: Do NOT skip this step. Do NOT assume MCP tools are unavailable just because they don't appear in your immediate tool list. They are almost always available as deferred tools that need to be loaded first.
1. Determine the session to check:
2. Call `ouroboros_session_status` MCP tool:
Tool: ouroboros_session_status
Arguments:
session_id: <session ID>3. If the user asks about drift (or says "am I drifting?"), also call `ouroboros_measure_drift`:
Tool: ouroboros_measure_drift
Arguments:
session_id: <session ID>
current_output: <current execution output or file contents>
seed_content: <original seed YAML>
constraint_violations: [] (any known violations)
current_concepts: [] (concepts in current output)4. Present results:
| Combined Drift | Status | Action | |----------------|--------|--------| | 0.0 - 0.15 | Excellent | On track | | 0.15 - 0.30 | Acceptable | Monitor closely | | 0.30+ | Exceeded | Consider consensus review or course correction |
If the MCP server is not available:
Session tracking requires the Ouroboros MCP server. Run /ouroboros:setup to configure. Without MCP, you can manually check drift by comparing your current implementation against the seed specification.
User: am I drifting? Session: sess-abc-123 Status: running Seed ID: seed-456 Messages Processed: 8 Drift Measurement Report ======================== Combined Drift: 0.12 Status: ACCEPTABLE Component Breakdown: Goal Drift: 0.08 (50% weight) Constraint Drift: 0.10 (30% weight) Ontology Drift: 0.20 (20% weight) You're on track. Goal alignment is strong. ◆ On track — continue with `ooo run` or `ooo evaluate` when ready
Your final response MUST end with exactly one breadcrumb footer line:
◆ <current state> → next: <recommended action>
Derive `<current state>` from live session state via `ouroboros_session_status` when that MCP projection is available; otherwise derive it from this skill's actual outcome. Never use a linear `Step N of M` footer because Ouroboros is an evolutionary loop. When the next action is genuinely a choice, list 2-3 honest options in the `next:` clause. The breadcrumb line must be the last line of the response.
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Repo: Q00/ouroboros
Automatically converge from goal to A-grade Seed and execute it
Scan and manage brownfield repository/worktree defaults for interviews
Open or drive the Ouroboros settings GUI (browser, TUI, or conversational fallback)
Evaluate execution with three-stage verification pipeline