From mycelium
Updates project canvas YAML files like purpose.yml, north-star.yml, and opportunities.yml with new evidence, ensures cross-file consistency, logs changes, and runs counter-argument checks.
npx claudepluginhub haabe/mycelium --plugin myceliumThis skill uses the workspace's default tool permissions.
1. **Never update without evidence** -- every canvas change must have a source
Lints canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically, before transitions, or after inactivity.
Manages persistent progress state, module health, dependency graphs, and ADRs across sessions. Use for workflows needing durable tracking of decisions and status beyond single interactions.
Generate GitHub-renderable Mermaid flowcharts from PRDs, docs, codebases, or combinations with evidence maps tracing nodes to sources, confidence scoring, and unknowns lists. Use for user flow diagrams.
Share bugs, ideas, or general feedback.
| Information Type | Canvas File | Source |
|---|---|---|
| Purpose, mission, why | purpose.yml | Sinek |
| North Star metric, inputs | north-star.yml | North Star Framework |
| BVSSH health scores | bvssh-health.yml | Smart |
| Value chain, competitive | landscape.yml | Wardley |
| Team structure | team-shape.yml | Skelton |
| User opportunities, OST | opportunities.yml | Torres |
| User needs map | user-needs.yml | Allen |
| Goals, ideas, steps | gist.yml | Gilad |
| Service quality scores | services.yml | Downe |
| Go-to-market, positioning | go-to-market.yml | Lauchengco |
| Delivery performance | dora-metrics.yml | Forsgren |
| Security threats | threat-model.yml | OWASP |
| Privacy assessment | privacy-assessment.yml | GDPR/PbD |
| Trust architecture | trust-signals.yml | Digital Trust |
| Jobs to be done | jobs-to-be-done.yml | Christensen |
| Bounded contexts | bounded-contexts.yml | Evans (DDD) |
| Value stream map | value-stream.yml | Rother & Shook (VSM) |
| Content delivery metrics | content-metrics.yml | v0.11.0 |
| AI tool delivery metrics | ai-tool-metrics.yml | v0.11.0 |
| Service delivery metrics | service-metrics.yml | v0.11.0 |
| Human task tracking | human-tasks.yml | v0.11.0 |
| Archived/discarded solutions | archived-solutions.yml | v0.12.0 |
| Leaf lifecycle calibration | cycle-history.yml | v0.12.0 |
| Adaptive thresholds | thresholds.yml | v0.12.0 |
| User scenarios (Hoskins) | scenarios.yml | Hoskins |
Before applying the canvas update, draft a one-line counter-argument: "What's the strongest case AGAINST this update — what evidence or perspective would invalidate it?" If you can't articulate one, run /mycelium:devils-advocate before proceeding.
This addresses the bias cluster documented in corrections.md (L5 sycophancy 2026-04-20, eval overfitting 2026-04-30, sharper-framing-isn't-righter 2026-05-03). Common shape: agent prefers what feels right over what evidence supports under competing pressure (be helpful vs. be honest, sharpen framing vs. preserve evidence base). The counter-argument step forces the missing perspective explicit, so the bias surfaces before it lands in canvas.
Especially important when interpolating user-supplied content (already untrusted per ${CLAUDE_PLUGIN_ROOT}/harness/security-trust.md#prompt-injection-defense) AND when increasing a confidence value — both contexts where the agent is most likely to default toward the optimistic read.