From mycelium
Evaluates Mycelium framework health by analyzing cycle-history.yml for velocity, discard rates, confidence calibration, gate effectiveness, and regressions. Re-runs key eval scenarios. Run quarterly or every 20 cycles.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mycelium:framework-healthThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Mycelium evaluates its own process. This is triple-loop learning — the framework assessing whether it is getting better at producing good outcomes.
Mycelium evaluates its own process. This is triple-loop learning — the framework assessing whether it is getting better at producing good outcomes.
Read .claude/canvas/cycle-history.yml. If fewer than 5 cycles recorded, report:
"Insufficient cycle data for framework health assessment. [N] cycles recorded; minimum 5 needed. Continue recording outcomes."
For each dimension, compute the metric and compare against trend (if prior assessments exist):
Cycle Velocity:
Discard Rate:
Confidence Calibration:
Gate Effectiveness:
Regression Rate:
Re-run any eval scenario tagged regression AND router-discipline from .claude/evals/scenarios/integration/. These are deferred design-time decisions that need periodic re-verification (the AGENTS.md router design is the canonical case — see agents-md-router-discipline.yml).
For each scenario:
/mycelium:eval-runner against the scenario filebaseline_reference fieldIf a scenario fails its success_criteria for the first time, log to corrections.md as a new generalizable correction with the scenario name as evidence. Do not auto-remediate — surface the regression for human review.
If cycle count ≥ minimum_n for any threshold in .claude/canvas/thresholds.yml:
${CLAUDE_PLUGIN_ROOT}/engine/adaptive-thresholds.mdFor each dimension, verify the counter-metric is not degrading:
Read .claude/memory/cluster-instances.md. For each cluster:
spec-status clusters with linked spec docs (e.g., ${CLAUDE_PLUGIN_ROOT}/engine/consistency-check-spec.md): check whether the spec's promotion-bar conditions have been met. Concretely: count detection rules drafted vs. required, FP-rate measurements available vs. needed.This step closes the recursion the cluster log was created to address: graduation criteria become mechanically auditable rather than promises stored in commit messages.
The README's "How Mycelium got smarter" section shows 5 case headers; the full list lives in docs/receipts/cases/. Stale README highlights are a Goodhart signal: if the receipts surface freezes, the framework's "we get smarter with each cycle" claim degrades to "we got smarter once".
For each case currently on the README:
docs/receipts/cases/ newer than the rotation candidate that better demonstrate the framework's recent behavior?docs/receipts/cases/ in >60 days, flag as a possible-low-friction signal — either the framework genuinely caused no recent friction (rare), or the dogfood loop has weakened (usually).Per docs/contributing/style.md#highlights-rotation. Cases stay in docs/receipts/cases/ even when rotated off README; only the README mention rotates.
Run a lightweight version of /mycelium:canvas-health step 9b on docs/:
Last updated >60 days)Surface in the dashboard. Full details delegate to /mycelium:canvas-health.
## Framework Health Dashboard
Assessment date: [date]
Cycles analyzed: [N]
Period: [date range]
### Dimensions
| Dimension | Current | Trend | Status | Counter-Metric |
|-----------|---------|-------|--------|----------------|
| Cycle velocity | [X days avg] | [improving/stable/degrading] | [healthy/warning/critical] | Outcome quality: [OK/degrading] |
| Discard rate | [avg phase X] | [earlier/stable/later] | [healthy/warning/critical] | False positive rate: [OK/rising] |
| Confidence calibration | [factor X.XX] | [improving/stable/diverging] | [healthy/warning/critical] | Decision speed: [OK/slowing] |
| Gate effectiveness | [see detail] | — | [healthy/warning/critical] | Flow speed: [OK/slowing] |
| Regression rate | [X%] | [decreasing/stable/increasing] | [healthy/warning/critical] | Innovation rate: [OK/declining] |
### Threshold Calibration
| Threshold | Default | Calibrated | Based On | Change |
|-----------|---------|-----------|----------|--------|
| ICE advance | 100 | [value or "insufficient data"] | N cycles | [+/-] |
| Confidence factor | 1.0 | [value or "insufficient data"] | N cycles | [+/-] |
| Bakeoff delta | 20% | [value or "insufficient data"] | N bakeoffs | [+/-] |
### Pattern Signals Active
[List any active pattern detector signals from ${CLAUDE_PLUGIN_ROOT}/engine/pattern-detector.md]
### Recommendations
[Specific actions based on findings — not generic advice]
npx claudepluginhub haabe/mycelium --plugin myceliumAggregates feedback signals across Mycelium loops to report health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations. Run weekly, post-launch, or when metrics stall.
Measures knowledge flywheel health by counting artifact files in learnings/patterns/research/retros, checking 7-day activity, detecting staleness, auditing cache metrics, and tracking Brownian Ratchet gates.
Monitors harness health across four observability layers: operational cadence, trend visibility, telemetry export, and meta-observability. Use for health checks, cadence setup, snapshot analysis, and telemetry config.