Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check session status and measure goal drift
.claude/skills/q00-ouroboros-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 162% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 385% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 39% | 0% |
Check session status and measure goal drift.
/ouroboros:ouroboros-status [session_id]Trigger keywords: "am I drifting?", "session status", "drift check"
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.
tool discovery query: "+ouroboros session status"
mcp__plugin_ouroboros_ouroboros__ (e.g., ouroboros_session_status, ouroboros_measure_drift). After runtime tool discovery returns, the tools become callable.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.
session_id provided: Use it directlyouroboros_session_status MCP tool: Tool: ouroboros_session_status Arguments: session_id: <session ID>
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)
📍 next-step based on context:📍 Session active — say "am I drifting?" to measure drift, or continue with ooo run📍 On track — continue with ooo run or ooo evaluate when ready📍 Warning: significant drift detected. Consider ooo interview to re-clarify, or ooo evolve to course-correct| 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| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→pass | 10,774 | 4,515 | -58% | 1 | 1 | 0% | 1,947 | 1,887 | -3% | 0 | 0 | — |
case-01 | fail→fail | 3,557 | 24,182 | +580% | 1 | 1 | 0% | 464 | 1,196 | +158% | 0 | 0 | — |
case-02 | fail→fail | 8,427 | 9,567 | +14% | 1 | 1 | 0% | 1,218 | 2,683 | +120% | 0 | 0 | — |
case-03 | fail→pass | 8,199 | 10,738 | +31% | 1 | 1 | 0% | 1,187 | 3,107 | +162% | 0 | 0 | — |
case-04 | fail→fail | 7,595 | 3,909 | -49% | 1 | 1 | 0% | 1,278 | 1,521 | +19% | 0 | 0 | — |
case-05 | fail→fail | 10,287 | 4,854 | -53% | 1 | 1 | 0% | 1,454 | 1,813 | +25% | 0 | 0 | — |
case-06 | fail→pass | 3,234 | 7,528 | +133% | 1 | 1 | 0% | 435 | 2,108 | +385% | 0 | 0 | — |
case-07 | fail→fail | 15,034 | 20,050 | +33% | 1 | 1 | 0% | 997 | 3,649 | +266% | 0 | 0 | — |
case-09 | fail→pass | 16,914 | 5,889 | -65% | 1 | 1 | 0% | 2,382 | 2,035 | -15% | 0 | 0 | — |
case-10 | fail→pass | 10,329 | 4,391 | -57% | 1 | 1 | 0% | 1,564 | 1,579 | +1% | 0 | 0 | — |
case-11 | fail→pass | 11,580 | 6,983 | -40% | 1 | 1 | 0% | 1,579 | 2,194 | +39% | 0 | 0 | — |
case-12 | fail→pass | 19,234 | 4,769 | -75% | 1 | 1 | 0% | 2,874 | 1,968 | -32% | 0 | 0 | — |
case-13 | pass→pass | 32,672 | 15,580 | -52% | 1 | 1 | 0% | 2,878 | 3,328 | +16% | 0 | 0 | — |
case-14 | pass→fail | 17,179 | 6,133 | -64% | 1 | 1 | 0% | 2,507 | 1,394 | -44% | 0 | 0 | — |
case-15 | pass→fail | 17,750 | 14,810 | -17% | 1 | 1 | 0% | 3,299 | 3,269 | -1% | 0 | 0 | — |
case-16 | fail→fail | 4,886 | 7,928 | +62% | 1 | 1 | 0% | 603 | 2,041 | +238% | 0 | 0 | — |
case-17 | fail→pass | 16,345 | 10,068 | -38% | 1 | 1 | 0% | 2,126 | 2,532 | +19% | 0 | 0 | — |
case-18 | fail→pass | 7,988 | 2,785 | -65% | 1 | 1 | 0% | 1,077 | 1,363 | +27% | 0 | 0 | — |
case-19 | fail→pass | 15,010 | 2,499 | -83% | 1 | 1 | 0% | 1,910 | 1,440 | -25% | 0 | 0 | — |
case-20 | pass→fail | 6,603 | 3,742 | -43% | 1 | 1 | 0% | 1,021 | 1,507 | +48% | 0 | 0 | — |
case-21 | pass→pass | 14,021 | 4,284 | -69% | 1 | 1 | 0% | 2,522 | 1,797 | -29% | 0 | 0 | — |
case-22 | pass→pass | 13,589 | 10,408 | -23% | 1 | 1 | 0% | 2,255 | 2,520 | +12% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 20 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.