agentera 3.0.0-dev.6 → 3.0.0-dev.69

package/bundle/skills/agentera/capabilities/audit/schemas/artifacts.yaml

@@ -0,0 +1,84 @@
+ARTIFACTS:
+  1:
+    id: A1
+    artifact: health
+    local_role: produces_and_consumes
+    description: >-
+      Codebase health assessment with findings, dimension grades, and trajectory.
+      Audit writes audit entries with per-dimension grades, findings with
+      severity and confidence scores, trend comparisons, and de facto
+      architecture patterns. During evaluation startup, Audit consumes health
+      state through CLI `evidence_context`, then bounded `npx -y agentera@next state health
+       list --limit 20 --format json` and exact `state health get --id ID`.
+      Raw health reads are diagnostic-only for corruption or CLI-defect investigation.
+  2:
+    id: A2
+    artifact: vision
+    local_role: consumes
+    description: >-
+      Audit treats vision state as protected during evidence-context startup;
+      missing or not-checked vision caveats from CLI `evidence_context` are preserved
+      instead of forcing a raw vision read.
+  3:
+    id: A3
+    artifact: decisions
+    local_role: consumes
+    description: >-
+      Audit consumes decision caveats through CLI `evidence_context`, then
+      bounded `npx -y agentera@next state decisions list --limit 20 --format json` discovery
+       and exact `state decisions get --id ID` retrieval. Raw decision reads
+      are diagnostic-only for corruption or CLI-defect investigation. Compacted
+      decision caveats must be preserved rather than reconstructed.
+  4:
+    id: A4
+    artifact: todo
+    local_role: produces_and_consumes
+    description: >-
+      Audit reads this to avoid re-reporting known issues and writes to it
+      with user confirmation when filing
+      critical and warning findings. During evaluation startup, known TODO state is
+      consumed through CLI `evidence_context`; raw TODO reads are diagnostic-only
+      for corruption or CLI-defect investigation.
+  5:
+    id: A5
+    artifact: progress
+    local_role: consumes
+    description: >-
+      Audit consumes latest progress verification and progress caveats through
+      CLI `evidence_context`, then bounded `npx -y agentera@next state progress list --limit
+       20 --format json` discovery and exact `state progress get --id ID`
+      retrieval. Raw progress reads are diagnostic-only for corruption or
+      CLI-defect investigation.
+  6:
+    id: A6
+    artifact: plan
+    local_role: consumes
+    description: >-
+      Audit consumes evaluation target and plan criteria through CLI
+      `evidence_context` before any diagnostic-only raw plan read. The plan's Created date
+      still provides the artifact-current-state baseline when that state is needed.
+  7:
+    id: A7
+    artifact: design
+    local_role: consumes
+    description: >-
+      Audit treats design state as optional during evidence-context startup;
+      missing design caveats from CLI `evidence_context` are preserved before any
+      diagnostic-only raw design read.
+  8:
+    id: A8
+    artifact: docs
+    local_role: consumes
+    description: >-
+      Audit reads this first to resolve project-local artifact mappings
+      and checks the versioning convention for the version health dimension. During
+      evaluation startup, docs state and version-boundary caveats are consumed through
+      CLI `evidence_context` before any diagnostic-only raw docs read.
+  9:
+    id: A9
+    artifact: profile
+    local_role: consumes
+    description: >-
+      Audit consumes profile status and stale-profile caveats through CLI
+      `evidence_context`; stale or missing profile state is preserved as a caveat and
+      is not approval to refresh profile state or read profile directly during startup.

package/bundle/skills/agentera/capabilities/{inspektera → audit}/schemas/exit.yaml

@@ -4,8 +4,8 @@ EXIT_CONDITIONS:
     condition: complete
     description: >-
       All selected audit dimensions were assessed, findings were synthesized,
-      grades were assigned, HEALTH.md was updated, and the user was presented
-      with actionable results.
+      grades were assigned, the health artifact was updated, and the user was
+      presented with actionable results.
     exit_signal: complete
   2:
     id: E2

package/bundle/skills/agentera/capabilities/audit/schemas/triggers.yaml

@@ -0,0 +1,25 @@
+TRIGGERS:
+  1:
+    id: T1
+    description: Audit local codebase health, architecture, quality, or technical debt.
+    priority: high
+  2:
+    id: T2
+    description: Review the local repository's code, architecture, dependencies, or structural health.
+    priority: high
+    disambiguates_against:
+      - capability: research
+        hint: "audit reviews this local codebase; research analyzes an external source or repository"
+      - capability: document
+        hint: "audit owns code and architecture health; document owns documentation maintenance and docs audits"
+      - capability: design
+        hint: "audit owns code and architecture health; design owns visual identity and design-system review"
+      - capability: optimize
+        hint: "audit assesses local health; optimize improves an existing system against a measurable target"
+  3:
+    id: T3
+    description: Review local health after implementation activity reveals a need for assessment.
+    priority: medium
+    disambiguates_against:
+      - capability: build
+        hint: "audit checks codebase health after build activity; build continues development"

package/bundle/skills/agentera/capabilities/{inspektera → audit}/schemas/validation.yaml

@@ -3,8 +3,8 @@ VALIDATION:
     id: V1
     rule: read_only_codebase
     description: >-
-      Inspektera MUST NOT modify any source code files. It is a read-only
-      assessment capability. Other capabilities fix what inspektera finds.
+      Audit MUST NOT modify any source code files. It is a read-only
+      assessment capability. Other capabilities fix what audit finds.
     severity: critical
     checks:
       - "No source code files are modified during audit"
@@ -24,9 +24,10 @@ VALIDATION:
     id: V3
     rule: decisions_respected
     description: >-
-      Findings that contradict deliberate decisions documented in DECISIONS.md
-      MUST be discarded or downgraded to info (SF3). A deliberate decision is
-      not a finding; it is an implementation of that decision.
+      Findings that contradict deliberate decisions returned by the bounded
+      decisions entity view MUST be discarded or downgraded to info
+      (SF3). A deliberate decision is not a finding; it is an
+      implementation of that decision.
     severity: critical
     checks:
       - "No finding contradicts a known deliberate decision"
@@ -53,8 +54,8 @@ VALIDATION:
     id: V6
     rule: exit_marker_required
     description: >-
-      Every inspektera invocation MUST emit an exit marker. The marker uses
-      the canonical glyph ⛶ (SG3) in the format ⛶ inspektera · <status>
+      Every audit invocation MUST emit an exit marker. The marker uses
+      the canonical glyph ⛶ (SG3) in the format ⛶ audit · <status>
       where status is one of EX1-EX4.
     severity: critical
     checks:
@@ -65,30 +66,30 @@ VALIDATION:
     id: V7
     rule: evidence_context_first
     description: >-
-      Inspektera evaluation startup MUST begin with `agentera prime --context
-      inspektera --format json` and use complete CLI `evidence_context` before
-      raw plan, progress, docs, health, TODO, or decisions artifacts.
+      Audit evaluation startup MUST begin with `npx -y agentera@next prime --context
+      audit --format json` and use complete CLI `evidence_context` before
+      bounded state list/get contracts for plan, progress, docs, health, TODO,
+      or decisions. Raw artifact access is diagnostic-only.
     severity: critical
     checks:
-      - "Evidence context is requested through prime --context before raw artifacts"
-      - "Complete evidence_context is used for evaluation target, criteria, evidence, caveats, and residual risks"
+      - "Evidence context is requested through prime --context before bounded state list/get"
   8:
     id: V8
     rule: evidence_context_fallback_before_raw
     description: >-
       When evidence_context is absent, incomplete, or caveated for needed state,
-      Inspektera MUST run listed existing CLI fallback commands before any last-resort
-      raw artifact read.
+       Audit MUST run listed bounded CLI fallback commands before any
+       diagnostic-only raw artifact read.
     severity: critical
     checks:
-      - "evidence_context.fallback_commands are attempted before raw artifact reads"
+      - "evidence_context.fallback_commands are attempted before diagnostic-only raw reads"
       - "capability_context.state.fallback_commands is used when evidence_context is unavailable"
-      - "Raw artifact reads are last-resort diagnostics, not normal evaluation startup"
+      - "Raw artifact reads are diagnostic-only, not normal evaluation startup"
   9:
     id: V9
     rule: evidence_context_caveats_preserved
     description: >-
-      Inspektera reports MUST preserve evidence_context caveats for stale app/profile
+      Audit reports MUST preserve evidence_context caveats for stale app/profile
       state, compacted decisions, protected-state boundaries, unavailable version or
       publication evidence, manual-check states, and residual risks instead of hiding,
       flattening, or reconstructing them.
@@ -101,7 +102,7 @@ VALIDATION:
     id: V10
     rule: satisfaction_authority_boundary
     description: >-
-      When Inspektera touches decision satisfaction, it may report provisional
+      When Audit touches decision satisfaction, it may report provisional
       satisfaction with evidence but MUST NOT user-confirm satisfaction. Missing,
       compacted, open, provisional, or review-needed satisfaction state remains a
       caveat and review pressure; automation must not reconstruct hidden outcomes
@@ -111,3 +112,21 @@ VALIDATION:
       - "Provisional satisfaction requires evidence"
       - "Only the user confirms final satisfaction"
       - "Missing or compacted satisfaction caveats are preserved"
+  11:
+    id: V11
+    rule: terminology_drift_read_only
+    description: >-
+      Terminology-drift findings MUST cite every variant with verified
+      project-relative file and line evidence. Canonical terms are proposals,
+      never decisions or writes. Optional personal-profile divergence is
+      comparison evidence only; missing profile evidence produces no claim.
+      Audit remains mutation-free and read-only. Build project-glossary
+      publication is active. Audit performs no consumer lookup; Discuss, Plan,
+      and Build use the separate active read-only advice path. Personal-profile
+      mutation and docs-mapping mutation remain outside both paths.
+    severity: critical
+    checks:
+      - "Every reported drift variant has project-file evidence"
+      - "Weak, deliberate, tracked, and no-drift candidates produce no finding"
+      - "Audit mutates no glossary, profile, docs mapping, code, or project file"
+      - "Build publication and read-only glossary consumers are active under separate mutation boundaries"

package/bundle/skills/agentera/capabilities/build/schemas/artifacts.yaml

@@ -0,0 +1,103 @@
+ARTIFACTS:
+  1:
+    id: A1
+    artifact: vision
+    local_role: produces_and_consumes
+    description: >-
+      Build consumes this through CLI execution_context caveats or explicit
+      fallback state when available, and never modifies it during cycles. Created
+      during vision bootstrap.
+  2:
+    id: A2
+    artifact: todo
+    local_role: produces_and_consumes
+    description: >-
+      Build consumes TODO state from execution_context and included status state
+      before direct reads, then writes newly discovered issues and resolved
+      entries. Severity classified per protocol SI1-SI4.
+  3:
+    id: A3
+    artifact: changelog
+    local_role: produces_and_consumes
+    description: >-
+      Build consumes changelog boundary from execution_context or the listed
+      CLI fallback before direct reads. It appends public change entries under
+      [Unreleased] based on commit type and promotes on version bumps.
+  4:
+    id: A4
+    artifact: progress
+    local_role: produces_and_consumes
+    description: >-
+      Durable project-outcome log and the sole durable channel for bounded
+      autonomous glossary caveat lifecycle evidence. Build consumes latest
+      progress evidence from execution_context first, then bounded `npx -y
+      agentera@next state progress list --limit 20 --format json` discovery or
+      exact `state progress get --id ID` retrieval. The typed writer's
+      progress_write_policy governs whether a cycle appends zero or one record;
+      every appended cycle has a mandatory non-empty verified field.
+  5:
+    id: A5
+    artifact: health
+    local_role: consumes
+    description: >-
+      Build consumes health state from execution_context and included status
+      state before bounded `npx -y agentera@next state health list --limit 20 --format json`
+       discovery or exact `state health get --id ID` retrieval, focusing on
+      critical and degraded findings for work selection. Raw reads are
+      diagnostic-only for corruption or CLI-defect investigation.
+  6:
+    id: A6
+    artifact: decisions
+    local_role: consumes
+    description: >-
+      Build consumes decision caveats and bounded list/get fallback commands from
+      execution_context first. Firm (DL1) entries are constraints and exploratory
+      (DL3) entries are uncertain foundations during work selection. Raw reads are
+      diagnostic-only for corruption or CLI-defect investigation.
+  7:
+    id: A7
+    artifact: plan
+    local_role: produces_and_consumes
+    description: >-
+      Build consumes selected task, acceptance criteria, dependencies,
+      constraints, and source contract metadata from CLI execution_context before
+      direct plan reads, then updates task status and surprises during execution.
+  8:
+    id: A8
+    artifact: profile
+    local_role: consumes
+    description: >-
+      Build consumes status profile summary first and reads profile grounding
+      only from `npx -y agentera@next report profile-grounding --format json` when shared
+      validity is `valid`. Absent or repair-needed state preserves exact
+      recovery and does not authorize refresh or direct profile reads.
+  9:
+    id: A9
+    artifact: docs
+    local_role: consumes
+    description: >-
+      Build consumes artifact mappings and docs caveats from execution_context
+      and included status docs state before direct docs reads.
+  10:
+    id: A10
+    artifact: design
+    local_role: consumes
+    description: >-
+      Build treats design state missing from execution_context as a caveat or
+      fallback-only need, and reads it only when building user-facing features
+      after listed CLI fallbacks are exhausted.
+  11:
+    id: A11
+    artifact: glossary
+    local_role: produces_and_consumes
+    description: >-
+      Build alone publishes one explicitly user-confirmed terminology proposal
+      through `npx -y agentera@next state glossary publish --input REQUEST`. The typed writer
+      revalidates audit source evidence and atomically records the immutable
+      approval beside the shared-only project entry. Build does not consume the
+      glossary only to validate replay and preserve unrelated publication state.
+      Separately, at governed meaning-sensitive Build events it requests bounded
+      read-only advice through `npx -y agentera@next report glossary-advice --input REQUEST
+      --format json`. Advice and progress caveats never publish terminology,
+      approve a proposal, reuse confirmation, mutate personal profiles or docs
+      mappings, or grant publication authority to another capability.

package/bundle/skills/agentera/capabilities/{realisera → build}/schemas/exit.yaml

@@ -3,9 +3,11 @@ EXIT_CONDITIONS:
     id: E1
     condition: complete
     description: >-
-      One full cycle completed. Work was selected, implemented, verified
-      against the project's test/build suite, committed with a conventional
-      message, and PROGRESS.md and TODO.md were updated.
+      One full cycle completed. Work was selected, implemented, and verified
+      against the project's test/build suite. Required artifact updates
+      preceded the cycle's single conventional commit. They include TODO,
+      changelog, and plan updates. Progress is present for policy-required
+      cases and optional for allowed durable outcomes.
     exit_signal: complete
   2:
     id: E2
@@ -13,15 +15,15 @@ EXIT_CONDITIONS:
     description: >-
       The cycle completed but with notable issues. Possible causes:
       verification passed but with warnings, the committed work is narrower
-      than intended due to scope reduction, or discoveries logged in
-      PROGRESS.md suggest the next cycle may face blockers.
+      than intended due to scope reduction, or durable discoveries recorded in
+      progress state suggest the next cycle may face blockers.
     exit_signal: flagged
   3:
     id: E3
     condition: stuck
     description: >-
       Cannot complete a cycle because VISION.md does not exist and the
-      brainstorm cannot proceed without the user, every available work item
+      vision bootstrap cannot proceed without the user, every available work item
       is blocked, or the verification suite is broken and cannot be fixed
       within the cycle's scope.
     exit_signal: stuck

package/bundle/skills/agentera/capabilities/build/schemas/triggers.yaml

@@ -0,0 +1,27 @@
+TRIGGERS:
+  1:
+    id: T1
+    description: A scoped implementation task or one verified development cycle.
+    priority: high
+  2:
+    id: T2
+    description: Implement one requested feature, fix, or bounded development task.
+    priority: high
+    disambiguates_against:
+      - capability: vision
+        hint: "build implements code; vision defines or refines project direction"
+      - capability: profile
+        hint: "build implements a software task; profile builds a reusable decision profile"
+      - capability: orchestrate
+        hint: "build completes one task or cycle; orchestrate runs an entire plan or multiple tasks"
+  3:
+    id: T3
+    description: Start or continue a single concrete implementation task.
+    priority: medium
+  4:
+    id: T4
+    description: Implement a scoped task after its plan or requirements are established.
+    priority: medium
+    disambiguates_against:
+      - capability: plan
+        hint: "build implements an established task; plan structures work before implementation"

package/bundle/skills/agentera/capabilities/build/schemas/validation.yaml

@@ -0,0 +1,184 @@
+VALIDATION:
+  1:
+    id: V1
+    rule: verified_field_mandatory
+    description: >-
+      Every progress entity record appended by Build MUST have a non-empty
+      verified field. The field carries either observed output from the primary
+      entrypoint, an allowlisted N/A tag, or a free-form rationale of at least 8
+      words.
+    severity: critical
+    checks:
+      - "Every cycle entry has a verified field"
+      - "verified field is not empty"
+  2:
+    id: V2
+    rule: one_cycle_per_invocation
+    description: >-
+      Build executes exactly one cycle per invocation. After logging required
+      artifacts (Step 7) and committing once (Step 8), the capability MUST stop.
+      The typed progress_write_policy determines whether the cycle appends zero
+      or one progress record. Multiple cycles require separate invocations or an
+      explicit user request.
+    severity: critical
+    checks:
+      - "At most one progress entity is appended per invocation"
+      - "Durable outcomes needed by future work may append one verified record"
+      - "Required glossary caveats and plan-completion sweeps append one verified record"
+      - "Attempt-only cycles with no durable project truth append no record"
+  3:
+    id: V3
+    rule: no_remote_push
+    description: >-
+      Build MUST NOT push to any remote repository. All commits are local
+      only. Remote operations require explicit user instruction outside this
+      capability.
+    severity: critical
+    checks:
+      - "No git push commands issued"
+  4:
+    id: V4
+    rule: vision_readonly_during_cycle
+    description: >-
+      The canonical vision artifact MUST NOT be modified during a cycle. It may only be written
+      during a vision bootstrap.
+    severity: critical
+    checks:
+      - "Vision artifact not modified outside brainstorm"
+  5:
+    id: V5
+    rule: attempt_history_authority
+    description: >-
+      Build MUST NOT reconstruct task or release attempt history from progress.
+      Plan evaluations own task attempts, while qualification and publication
+      receipts own release attempts and retry state. Missing retry state does
+      not authorize an attempt-only progress record.
+    severity: critical
+    checks:
+      - "Progress is not used as task or release attempt history"
+      - "Retry state comes only from its owning plan or receipt authority"
+  6:
+    id: V6
+    rule: artifact_path_resolution
+    description: >-
+      Entity state MUST use exact/list CLI reads and typed writers discovered by
+      `npx -y agentera@next state <artifact> explain`. Check .agentera/docs.yaml only for
+      intentional singleton path overrides.
+    severity: warning
+    checks:
+      - "Entity files are not read or edited directly"
+      - "docs.yaml checked before singleton artifact access"
+  7:
+    id: V7
+    rule: execution_context_first
+    description: >-
+      Build startup SHOULD begin from `npx -y agentera@next prime --context build
+      --format json` and consume complete execution_context
+      state before direct reads of plan, progress, TODO, docs, health,
+      decisions, changelog, vision, profile, or design artifacts.
+    severity: warning
+    checks:
+      - "execution_context requested through supported prime --context seam"
+      - "complete execution_context used before direct startup artifact reads"
+  8:
+    id: V8
+    rule: fallback_before_raw
+    description: >-
+      When execution_context is incomplete or caveated, Build MUST run listed
+      CLI fallback commands before any last-resort raw artifact diagnostic and
+      MUST preserve caveats in cycle reporting.
+    severity: critical
+    checks:
+      - "CLI fallback commands run before raw artifact diagnostics"
+      - "execution_context caveats preserved in progress or cycle report"
+  9:
+    id: V9
+    rule: context_generation_readonly
+    description: >-
+      Generating execution_context is read-only. It MUST NOT refresh profile or
+      installed app state, edit vision or objective state, spawn workers, commit,
+      push, tag, publish, or introduce unsupported capability-name CLI commands.
+    severity: critical
+    checks:
+      - "No protected state mutation during context generation"
+      - "No unsupported `agentera build` command introduced"
+  10:
+    id: V10
+    rule: satisfaction_authority_boundary
+    description: >-
+      When Build touches decision satisfaction, it may mark provisional
+      satisfaction with evidence but MUST NOT user-confirm satisfaction. Missing,
+      compacted, open, provisional, or review-needed satisfaction state remains a
+      caveat and review pressure; automation must not reconstruct hidden outcomes
+      or claim it proved user intent.
+    severity: critical
+    checks:
+      - "Provisional satisfaction requires evidence"
+      - "Only the user confirms final satisfaction"
+      - "Missing or compacted satisfaction caveats are preserved"
+  11:
+    id: V11
+    rule: sanitized_profile_grounding
+    description: >-
+      Build MUST ground only from the `content` returned by `npx -y agentera@next report
+      profile-grounding --format json` when shared validity is valid; it MUST
+      preserve absent/repair-needed recovery and MUST NOT direct-read PROFILE.md.
+    severity: critical
+    checks:
+      - "Sanitized grounding command used after prime startup"
+      - "Prime and report validity objects agree before content use"
+      - "Raw profile path not read"
+  12:
+    id: V12
+    rule: governed_glossary_advice
+    description: >-
+      At initial meaning-sensitive cycle intent and later user-authored changes
+      or clarification answers that can alter intent, Build MUST request bounded
+      advice through `npx -y agentera@next report glossary-advice --input REQUEST --format
+      json`. Unchanged replay, unrelated turns, rendering, and tool output MUST
+      NOT refresh advice.
+    severity: critical
+    checks:
+      - "Exact project authority or proven-gap personal fallback grounds intent"
+      - "Governed changes refresh only the affected meaning"
+      - "Incidental turns and unchanged replay do not refresh"
+  13:
+    id: V13
+    rule: glossary_review_and_autonomy
+    description: >-
+      Interactive Build MUST ask one focused clarification before disputed
+      meaning-sensitive reliance whenever review is required. If autonomous Build
+      cannot pause, it MUST avoid the disputed meaning, proceed conservatively
+      only where safe, and append one idempotent privacy-safe glossary_caveat
+      lifecycle envelope through the typed progress writer.
+    severity: critical
+    checks:
+      - "Clarification precedes meaning-sensitive execution and re-evaluates only the affected meaning"
+      - "Autonomous work does not assume disputed meaning"
+      - "Current, resolved, and superseded caveat events obey opaque identity lifecycle"
+  14:
+    id: V14
+    rule: glossary_publication_isolation
+    description: >-
+      Advice, tension, clarification, and progress caveat lifecycle MUST NOT call
+      `npx -y agentera@next state glossary publish`, create or reuse approval, substitute for
+      digest-bound user confirmation, satisfy decisions or plan state, or grant
+      Discuss or Audit publication authority.
+    severity: critical
+    checks:
+      - "Advice and caveat paths perform zero glossary publication writes"
+      - "Only separately supplied digest-confirmed publication retains Build authority"
+  15:
+    id: V15
+    rule: transient_no_plan_execution_input
+    description: >-
+      When no current executable plan owns startup, Build MAY accept one bounded
+      `agentera.buildExecutionRequest.v1` through `prime --context build --input
+      <file|-> --format json`. The request supplies explicit scope and acceptance
+      transiently; it MUST NOT persist, create, or mutate plan state. Current
+      plan-owned execution conflicts instead of silently ignoring the request.
+    severity: critical
+    checks:
+      - "Transient input is used only when no current executable plan owns startup"
+      - "No request content is placed in argv or persisted"
+      - "No-plan execution requires explicit scope and acceptance"

package/bundle/skills/agentera/capabilities/{visualisera → design}/schemas/artifacts.yaml

@@ -1,44 +1,44 @@
 ARTIFACTS:
   1:
     id: A1
-    artifact_id: design
+    artifact: design
     local_role: produces_and_consumes
     description: >-
       Visual identity system with design tokens, typography, colors,
-      spacing, constraints, and component contracts. Visualisera writes and
+      spacing, constraints, and component contracts. Design writes and
       reads agent-readable YAML token blocks with HTML comment markers.
   2:
     id: A2
-    artifact_id: vision
+    artifact: vision
     local_role: consumes
     description: >-
-      Visualisera reads the Identity section to propose visual tokens
+      Design reads the Identity section to propose visual tokens
       coherent with the declared verbal personality.
   3:
     id: A3
-    artifact_id: progress
+    artifact: progress
     local_role: consumes
     description: >-
-      Visualisera reads this during refine mode to identify UI work and
+      Design reads this during refine mode to identify UI work and
       inline design decisions since the design system was written.
   4:
     id: A4
-    artifact_id: todo
+    artifact: todo
     local_role: produces_and_consumes
     description: >-
-      Visualisera reads this to check for design-related issues and files
+      Design reads this to check for design-related issues and files
       code drift findings here during audit mode.
   5:
     id: A5
-    artifact_id: docs
+    artifact: docs
     local_role: consumes
     description: >-
-      Visualisera reads this first to resolve project-local artifact mappings
+      Design reads this first to resolve project-local artifact mappings
       before accessing other artifacts.
   6:
     id: A6
-    artifact_id: profile
+    artifact: profile
     local_role: consumes
     description: >-
-      Visualisera reads aesthetic preferences from the profile as defaults
+      Design reads aesthetic preferences from the profile as defaults
       during the create conversation.

package/bundle/skills/agentera/capabilities/{visualisera → design}/schemas/exit.yaml

@@ -4,16 +4,16 @@ EXIT_CONDITIONS:
     condition: complete
     description: >-
       DESIGN.md was written (Create/Replace mode), updated (Refine mode),
-      or audited with findings reported (Audit mode). Validation script
-      ran without errors, and all changes had explicit user approval.
+      or audited with findings reported (Audit mode). npx -y agentera@next check lint
+      --artifact design passed, and all changes had explicit user approval.
     exit_signal: complete
   2:
     id: E2
     condition: flagged
     description: >-
       The design system was produced or audited but with issues worth
-      surfacing. Possible causes: validation passed with advisory warnings,
-      the design drifts from VISION.md Identity, or audit findings were
+      surfacing. Possible causes: lint passed with advisory warnings,
+      the design drifts from vision Identity, or audit findings were
       neither fixed nor filed.
     exit_signal: flagged
   3:
@@ -21,7 +21,7 @@ EXIT_CONDITIONS:
     condition: stuck
     description: >-
       Cannot write DESIGN.md because the user declined to approve the
-      draft, the validation script reports unresolvable errors, or the
+      draft, npx -y agentera@next check lint reports unresolvable errors, or the
       project's UI stack is inaccessible.
     exit_signal: stuck
   4: