Browser & automation
canvas-health
Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.
haabe · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add haabe/mycelium --skill canvas-healthAbout this skill
name: canvas-health description: "Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions." metadata: instruction_budget: "87" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
Canvas Health Check
Audit the canvas knowledge base for quality, consistency, and completeness. The canvas is Mycelium's source of truth -- its quality directly determines agent output quality (Raschka: "context quality = model quality").
When to Use
- Before any diamond phase transition (called automatically by
/mycelium:diamond-assess) - After a period of inactivity (>7 days since last canvas update)
- When agent output quality seems to degrade
- After onboarding a new team member (ensures canvas is self-explanatory)
- Proactively: run periodically to catch silent drift
Workflow
-
Load project configuration:
- Read
.claude/diamonds/active.ymlforproduct_typeandproject_type - Read
${CLAUDE_PLUGIN_ROOT}/engine/canvas-guidance.ymlfor required/recommended/optional files per project type
- Read
-
Check file presence:
- For each required canvas file: does it exist? Is it non-empty (>50 bytes)?
- For each recommended canvas file: does it exist? Flag as gap if missing.
- Report:
N/M required files present, K recommended files missing
-
Check
_metablocks:- For each existing canvas file, check for
_meta:block - Flag missing
_metablocks - Flag
last_validatedpast the horizon for that file's category, per the "Which threshold applies to which canvas file" table in${CLAUDE_PLUGIN_ROOT}/engine/evidence-decay.md(strategic 180d, technical feasibility 120d, user-needs/competitive/market 90d, delivery metrics 30d, regulatory 365d; unlisted files fall back to 90d). - SKIP any file whose
_meta.applicabilitymarks it inapplicable (a value startingn/a, or naming a product type this project is not, or saying "NOT actively used"). Added v0.90.0. Two dogfood canvases held ZERO evidence — every metric field null, the only non-null leavesFalseschema defaults — and already said so in their own_meta. They decayed on a 30-day horizon anyway, and the only way to silence that warning would have been to date a validation of a file nobody uses: the manufactured-validation move v0.89.0 removedlast_updatedto prevent. Precedents for the marker:dora-metrics.yml#sre(n/a-until-production) anddependency-pins.yml(scope: local). This replaced a flat 30-day rule in v0.89.0. That rule was the only staleness number in this skill grounded in nothing — step 7 below has always used the decay table — and on the dogfood repo it flagged 20 of 25 canvases, including a strategic file validated 46 days earlier against a 180-day horizon. A check that fires on 80% of a corpus trains its reader to skip it. - Flag
versionfield missing or at 0
- For each existing canvas file, check for
-
Check confidence consistency:
- Gather all
confidence:values across canvas files - Flag confidence > 0.5 with
evidence_type: speculationorevidence_type: assumption - Flag confidence > 0.7 with fewer than 2 evidence sources
- Flag confidence values that haven't changed across git history (anchored confidence anti-pattern)
- Cross-check against
.claude/diamonds/active.ymlconfidence - Cross-check the confidence RATIONALE prose too, not only the
confidence:field. Projects record why a value moved in narrative fields (confidence_effect,confidence_effect_v2, or any prose block that names a number). Nothing reads those, so a canvas can be numerically consistent everywhere while the sentence explaining the number contradicts it. Flag when a rationale block names a confidence value that no longer matches.claude/diamonds/active.yml. Prose that encodes state is state, and it is otherwise unvalidated. (Roadmap dogfood 2026-08-02: the field said 0.10, the narrative beside it still said 0.25, and the numeric check passed.)
- Gather all
-
Check evidence type consistency:
- Every canvas file with
evidence_type:should have it set to one of the shipped schema enum values (schemas/canvas/_common.schema.json#$defs/evidence_type— Gilad's evidence ladder):speculation,anecdotal,data-supported,test-validated,launch-validated - Flag unknown evidence types (note:
_metablocks in the field carry structural markers likeschema/assessment/not-yet-populated— flag these only when they appear OUTSIDE_meta; inside_metathey describe the file, not an evidence claim) - Flag evidence graded
anecdotalor better whose only sources are mocked personas /internal_simulated(honesty check — simulated evidence sits atspeculationon the ladder regardless of how vivid it reads) - Every
source_class:value must be one of the values in the SHIPPED SCHEMA enum — read${CLAUDE_PLUGIN_ROOT}/schemas/canvas/_common.schema.json#$defs/source_classand compare against that, exactly as theevidence_typerule above already does. Do NOT hardcode the list here. Until v0.90.0 this step named five values while the schema had six;pointeris valid,check_source_independence.pyhandles it correctly, and a dogfood canvas used it 61 times. Following the prose produced 61 phantom violations — the documented-rule-diverges-from-enforcement class, in a step whose own sibling rule says to read the schema. - Flag
internal_stakeholderevidence with confidence > 0.5 that hasvalidated: falseor novalidatedfield — stakeholder beliefs should not carry high confide
- Every canvas file with