agentera 3.0.0-dev.41 → 3.0.0-dev.46

package/bundle/skills/agentera/SKILL.md

@@ -34,14 +34,23 @@ documentation after deterministic abstention; it learns that contract from the C
 
 ## Bootstrap
 
-Run `npx -y agentera@next prime` for orientation. The JSON it returns is the complete
-contract — app status, state slices, attention items, next action, and the
-source contract that declares what's complete and what requires fallback.
+Run one pre-cutover `@next` call for orientation. It is read-only in clean, v2,
+partially migrated, and v3 projects. Clean, v2, and partial state returns
+`blocked` with the exact full entity-upgrade command in
+`state_cutover.recovery_command`; v3 returns `ok` unless health is degraded.
+The JSON also returns bounded app status, state slices, attention, and startup
+availability.
 
 ```bash
-npx -y agentera@next prime
+npx -y agentera@next prime --context status --format json
 ```
 
+An `ok` outcome needs no fallback or second dashboard call. Follow an exact
+recovery command for other outcomes; every returned v3 command stays on
+`npx -y agentera@next`. Do not use bare or stable-channel CLI forms before
+stable promotion. For deeper read-only evidence, run
+`npx -y agentera@next doctor --format json`.
+
 For capability-specific startup context:
 
 ```bash
@@ -49,10 +58,12 @@ npx -y agentera@next prime --context <capability> --format json
 ```
 
 This returns the capability's instructions, declared read/write needs, artifact
-inventory, included/missing state, and fallback commands. Use it before
-reading the instructions module directly.
+inventory, and `capability_context.startup`. Check its `outcome` (`ok`,
+`degraded`, or `blocked`). The `availability` rows identify bounded included
+families and deferred families; use a deferred row's `detail_command` for
+detail. Use this response before reading the instructions module directly.
 
-For static routing guidance (agentera vs native tools):
+For static routing guidance (CLI vs native tools):
 
 ```bash
 npx -y agentera@next prime --guidance
@@ -93,7 +104,7 @@ hardcoded rules. `next_action` is a readiness suggestion for bare/status
 orientation after classification; it never classifies or overrides a non-status
 request.
 
-The LLM host classifies natural language. Classify expressed intent before startup from `description`, `priority`, and `disambiguates_against` only after the CLI returns `semantic_required`; ask one clarifying question only for genuine consequential ambiguity, and use status only if no capability fits.
+The LLM host classifies natural language. Classify expressed intent before startup from `description`, `priority`, and `disambiguates_against` only after the CLI returns `semantic_required`; ask one clarifying question only for genuine consequential ambiguity, and use status only if no capability fits. Read that response's `receipt_contract` for the exact nullable `agentera.route_receipt.v1` schema, outcomes, nullability, compound and span rules, and runnable stdin example; `npx -y agentera@next route receipt --help` presents the same guide.
 
 The receipt input is `{ request: <original string>, receipt: <complete nullable
 API output> }`; every API field is present and outcome-inapplicable fields are
@@ -146,9 +157,11 @@ The prime dashboard rendering contract — template, field-by-field rules, outpu
 budget, attention-item ordering, exit marker — is owned by the status capability
 instructions. `npx -y agentera@next prime --context status --format json` returns the full
 `capability_context.instructions` body and the bounded
-`capability_context.context.status_context` state in one response. Render from
-that capsule without a separate bare-prime call or raw artifact read; use the
-named recovery command when the capsule marks detail as omitted.
+`capability_context.context.status_context` state and one
+`capability_context.startup` availability projection in one response. Render
+from that capsule without a separate bare-prime call or raw artifact read. An
+`ok` outcome needs no second call; for deferred detail, use only that family's
+exact `detail_command`.
 Ask for confirmation before invoking a state-changing downstream capability.
 
 The first response in a fresh interaction delivers the brief and a free-form
@@ -225,7 +238,10 @@ Common mutations:
 - `npx -y agentera@next state health append --input audit.yaml --format json`
 - `npx -y agentera@next state todo create --input todo.yaml --format json`
 - `npx -y agentera@next state todo update --id ID --input todo-patch.yaml --format json`
-- `npx -y agentera@next state todo set-severity|supersede|resolve|reopen --id ID ... --format json`
+- `npx -y agentera@next state todo set-severity --id ID ... --format json`
+- `npx -y agentera@next state todo supersede --id ID ... --format json`
+- `npx -y agentera@next state todo resolve --id ID ... --format json`
+- `npx -y agentera@next state todo reopen --id ID ... --format json`
 
 TODO create input is a full YAML/JSON typed record. TODO update input is a
 patch: omitted fields remain unchanged and only `target_version`,
@@ -242,8 +258,8 @@ task append/update payloads use only mutable task content and bare task IDs.
 
 Add `--dry-run` to preview any mutation without publishing it. Artifacts not
 listed above are outside the typed writer contract and remain governed by their
-owning capability's instructions and safety rails. `npx -y agentera@next schema --format
-json` exposes the machine-readable writer operation matrix under
+owning capability's instructions and safety rails.
+`npx -y agentera@next schema --format json` exposes the machine-readable writer operation matrix under
 `state_writer` and on each writable `artifact_schemas[*].write_interface`.
 
 ---
@@ -260,5 +276,5 @@ default singleton layout:
 
 Do not silently bypass the CLI and read raw entity files first. If
 CLI state declares complete coverage, do not perform defensive raw artifact
-reads. Use raw artifact reads only as a last-resort fallback after CLI
-fallback commands fail or declare incomplete state.
+reads. Use raw artifact reads only as a last-resort after the applicable
+availability row's exact detail command fails or state declares corruption.

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

@@ -8,7 +8,7 @@ ARTIFACTS:
       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 `agentera state 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:
@@ -25,7 +25,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Audit consumes decision caveats through CLI `evidence_context`, then
-      bounded `agentera state decisions list --limit 20 --format json` discovery
+      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.
@@ -45,7 +45,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Audit consumes latest progress verification and progress caveats through
-      CLI `evidence_context`, then bounded `agentera state progress list --limit
+      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.

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

@@ -66,7 +66,7 @@ VALIDATION:
     id: V7
     rule: evidence_context_first
     description: >-
-      Audit evaluation startup MUST begin with `agentera prime --context
+      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.

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

@@ -30,7 +30,7 @@ ARTIFACTS:
     description: >-
       Operational cycle log and the sole durable channel for bounded autonomous
       glossary caveat lifecycle evidence. Build consumes latest progress evidence from
-      execution_context first, then bounded `agentera state progress list --limit
+      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, and appends one entry per cycle with mandatory Verified field.
       Compacted by applying schema COMPACTION rules.
@@ -40,7 +40,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Build consumes health state from execution_context and included status
-      state before bounded `agentera state health list --limit 20 --format json`
+      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.
@@ -67,7 +67,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Build consumes status profile summary first and reads profile grounding
-      only from `agentera report profile-grounding --format json` when shared
+      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:
@@ -91,12 +91,12 @@ ARTIFACTS:
     local_role: produces_and_consumes
     description: >-
       Build alone publishes one explicitly user-confirmed terminology proposal
-      through `agentera state glossary publish --input REQUEST`. The typed writer
+      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 `agentera report glossary-advice --input REQUEST
+      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/build/schemas/validation.yaml

@@ -54,7 +54,7 @@ VALIDATION:
     rule: artifact_path_resolution
     description: >-
       Entity state MUST use exact/list CLI reads and typed writers discovered by
-      `agentera state <artifact> explain`. Check .agentera/docs.yaml only for
+      `npx -y agentera@next state <artifact> explain`. Check .agentera/docs.yaml only for
       intentional singleton path overrides.
     severity: warning
     checks:
@@ -64,7 +64,7 @@ VALIDATION:
     id: V7
     rule: execution_context_first
     description: >-
-      Build startup SHOULD begin from `agentera prime --context build
+      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.
@@ -112,7 +112,7 @@ VALIDATION:
     id: V11
     rule: sanitized_profile_grounding
     description: >-
-      Build MUST ground only from the `content` returned by `agentera report
+      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
@@ -126,7 +126,7 @@ VALIDATION:
     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 `agentera report glossary-advice --input REQUEST --format
+      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
@@ -153,7 +153,7 @@ VALIDATION:
     rule: glossary_publication_isolation
     description: >-
       Advice, tension, clarification, and progress caveat lifecycle MUST NOT call
-      `agentera state glossary publish`, create or reuse approval, substitute for
+      `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

package/bundle/skills/agentera/capabilities/design/schemas/exit.yaml

@@ -4,7 +4,7 @@ EXIT_CONDITIONS:
     condition: complete
     description: >-
       DESIGN.md was written (Create/Replace mode), updated (Refine mode),
-      or audited with findings reported (Audit mode). agentera check lint
+      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:
@@ -21,7 +21,7 @@ EXIT_CONDITIONS:
     condition: stuck
     description: >-
       Cannot write DESIGN.md because the user declined to approve the
-      draft, agentera check lint 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:

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

@@ -5,8 +5,8 @@ ARTIFACTS:
     local_role: produces_and_consumes
     description: >-
       Reasoning trail with confidence labels. Discuss reads existing decisions
-      through bounded `agentera state decisions list --limit 20 --format json`
-       discovery plus exact `agentera state decisions get --id ID --format json`
+      through bounded `npx -y agentera@next state decisions list --limit 20 --format json`
+       discovery plus exact `npx -y agentera@next state decisions get --id ID --format json`
       retrieval and its source_contract to avoid re-deliberation, and writes new decision entries with confidence
       (DL1 firm, DL2 provisional, DL3 exploratory). Compact older entries by
       applying schema COMPACTION rules; incomplete compacted entries are
@@ -39,7 +39,7 @@ ARTIFACTS:
     artifact: profile
     local_role: consumes
     description: >-
-      Discuss reads only sanitized non-glossary content from `agentera report
+      Discuss reads only sanitized non-glossary content from `npx -y agentera@next report
       profile-grounding --format json` at session start. It never direct-reads
       the profile path. It uses content only when the shared validity object is
       valid; absent or repair-needed results fail closed with exact recovery.

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

@@ -80,7 +80,7 @@ VALIDATION:
     id: V8
     rule: sanitized_profile_grounding
     description: >-
-      Discuss MUST ground only from the `content` returned by `agentera report
+      Discuss 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
@@ -92,7 +92,7 @@ VALIDATION:
     id: V9
     rule: governed_glossary_advice_events
     description: >-
-      Discuss MUST invoke `agentera report glossary-advice --input <file|->
+      Discuss MUST invoke `npx -y agentera@next report glossary-advice --input <file|->
       --format json` for initial meaning-sensitive user input and later
       user-authored premise changes or affected clarification answers that can
       change meaning. It MUST NOT invoke advice for unchanged replay, rendering,

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

@@ -25,7 +25,7 @@ ARTIFACTS:
       Document reads this during explore-and-generate mode to understand
       recent project context. During closeout, latest progress evidence and
       verification pointers are consumed through CLI `closeout_context`, then
-      bounded `agentera state progress list --limit 20 --format json` discovery
+      bounded `npx -y agentera@next state progress list --limit 20 --format json` discovery
        or exact `state progress get --id ID` retrieval. Raw reads are
       diagnostic-only for corruption or CLI-defect investigation.
   4:
@@ -34,7 +34,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Document reads this during explore-and-generate mode for project
-      context and decision awareness through bounded `agentera state decisions
+      context and decision awareness through bounded `npx -y agentera@next state decisions
       list --limit 20 --format json` discovery or exact `state decisions get
        --id ID` retrieval. Raw reads are diagnostic-only for corruption or
       CLI-defect investigation.
@@ -44,7 +44,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Document reads this to discover documentation gaps surfaced during health
-      audits through bounded `agentera state health list --limit 20 --format
+      audits through bounded `npx -y agentera@next state health list --limit 20 --format
        json` discovery or exact `state health get --id ID` retrieval. Raw reads
       are diagnostic-only for corruption or CLI-defect investigation.
   6:

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

@@ -85,7 +85,7 @@ VALIDATION:
     id: V9
     rule: closeout_context_first
     description: >-
-       During final synchronization, Document MUST use `agentera prime
+       During final synchronization, Document MUST use `npx -y agentera@next prime
        --context document --format json` and its `closeout_context`
        before using bounded state list/get contracts for TODO, docs, changelog,
        or progress. Raw artifact access is diagnostic-only or a write target.

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

@@ -64,6 +64,6 @@ ARTIFACTS:
     artifact: benchmark_context
     local_role: consumes
     description: >-
-      CLI-provided startup benchmark summary from `agentera prime --context
+      CLI-provided startup benchmark summary from `npx -y agentera@next prime --context
       optimize --format json`. Optimize consumes this before any direct
       latest-report.json, latest-report.md, or runs.jsonl diagnostic read.

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

@@ -65,7 +65,7 @@ VALIDATION:
     id: V7
     rule: benchmark_context_first
     description: >-
-      For benchmark-oriented startup, Optimize MUST start from `agentera prime
+      For benchmark-oriented startup, Optimize MUST start from `npx -y agentera@next prime
       --context optimize --format json` and consume complete
       benchmark_context before direct retained benchmark file reads. Direct
       latest-report.json, latest-report.md, or runs.jsonl reads are last-resort

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

@@ -5,7 +5,7 @@ ARTIFACTS:
     local_role: produces_and_consumes
     description: >-
       Orchestrate consumes plan task queue state through
-      `agentera prime --context orchestrate --format json` before raw
+      `npx -y agentera@next prime --context orchestrate --format json` before raw
        artifact access, then updates status (pending -> complete/blocked) only
        when resolving a task. Superseded tasks are terminal dependency
        satisfiers and stay out of ready and blocked queues. Failed evaluator results are recorded through the
@@ -16,7 +16,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Orchestrate consumes progress verification state from the returned
-      orchestration context first, then bounded `agentera state progress list
+      orchestration context first, then bounded `npx -y agentera@next state progress list
       --limit 20 --format json` fallback output. Exact detail uses `state
       progress get --id ID`; raw reads are diagnostic-only for corruption or
       CLI-defect investigation.
@@ -28,9 +28,9 @@ ARTIFACTS:
       For an active plan whose tasks are all terminal, Orchestrate consumes
       returned health state and delegates a limited staleness closure check.
       On PASS it publishes one typed `artifact_freshness` health record through
-      `agentera state health append --input PATH --format json` before setting
+      `npx -y agentera@next state health append --input PATH --format json` before setting
       the still-open plan complete. WARN or FAIL leaves the plan open and
-      surfaces the finding. Bounded `agentera state health list --limit 20
+      surfaces the finding. Bounded `npx -y agentera@next state health list --limit 20
       --format json` and exact `state health get --id ID` are fallback
       contracts. Raw reads are diagnostic-only for corruption or CLI-defect
       investigation.
@@ -47,7 +47,7 @@ ARTIFACTS:
     local_role: consumes
     description: >-
       Orchestrate consumes included decision context or bounded
-      `agentera state decisions list --limit 20 --format json` discovery and
+      `npx -y agentera@next state decisions list --limit 20 --format json` discovery and
       exact `state decisions get --id ID` retrieval, preserving firm
       constraints, exploratory uncertainties, and compacted-entry caveats.
       Raw reads are diagnostic-only for corruption or CLI-defect investigation.

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

@@ -62,12 +62,12 @@ VALIDATION:
     rule: orchestration_context_first
     description: >-
       Orchestrate startup and evaluation MUST use
-      `agentera prime --context orchestrate --format json` and the
+      `npx -y agentera@next prime --context orchestrate --format json` and the
       returned orchestration context before raw plan, progress, health, TODO,
       or decisions artifact reads.
     severity: critical
     checks:
-      - "orchestrate instructions contains agentera prime --context orchestrate --format json"
+      - "orchestrate instructions contains npx -y agentera@next prime --context orchestrate --format json"
       - "orchestrate instructions contains complete_for_orchestration_context"
       - "orchestrate instructions contains no raw plan, progress, health, TODO, or decisions reads"
   7:

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

@@ -53,7 +53,7 @@ ARTIFACTS:
     artifact: profile
     local_role: consumes
     description: >-
-      Plan reads only sanitized non-glossary content from `agentera report
+      Plan reads only sanitized non-glossary content from `npx -y agentera@next report
       profile-grounding --format json` to calibrate planning depth and pattern
       preferences. It never direct-reads the profile path and uses content only
       for shared validity `valid`; absent and repair-needed results fail closed.

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

@@ -91,7 +91,7 @@ VALIDATION:
     id: V9
     rule: sanitized_profile_grounding
     description: >-
-      Plan MUST ground only from the `content` returned by `agentera report
+      Plan 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

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

@@ -88,7 +88,7 @@ VALIDATION:
     rule: personal_glossary_output
     description: >-
       Profile Full MUST render and persist exactly one owned Glossary section
-      through `agentera report profile-glossary`. Entries use only the shared
+      through `npx -y agentera@next report profile-glossary`. Entries use only the shared
       primitive and personal provenance variants. Replacement preserves every
       non-glossary byte, malformed or ambiguous boundaries fail before effects,
       and personal production never reads a project glossary.

package/bundle/skills/agentera/capability_schema_contract.yaml

@@ -80,7 +80,7 @@ DIRECTORY_REQUIREMENTS:
       TypeScript module that exports the capability's behavioral instructions
       as a default-exported string constant. The runtime loads it via the
       compiled .js path and surfaces the prose through
-      `agentera prime --context <name> --format json`.
+      `npx -y agentera@next prime --context <name> --format json`.
   schemas_directory:
     path: schemas
     type: directory
@@ -409,7 +409,7 @@ ARTIFACTS:
       Behavioral instructions the agent reads. TypeScript module that exports
       a default-exported string constant. The runtime loads it via the
       compiled .js path and serves the prose through
-      `agentera prime --context <name> --format json`.
+      `npx -y agentera@next prime --context <name> --format json`.
     produces: false
     consumes: true
   4:

package/bundle/skills/agentera/schemas/artifacts/decisions.yaml

@@ -49,9 +49,9 @@ ENTITY_AUTHORITY:
   artifact: decisions
   boundaries: [decision, decision_revision, decision_satisfaction]
   retrieval:
-    list: agentera state decisions list --format json
-    get: agentera state decisions get --id ID --format json
-  mutation: agentera state decisions explain --format json
+    list: npx -y agentera@next state decisions list --format json
+    get: npx -y agentera@next state decisions get --id ID --format json
+  mutation: npx -y agentera@next state decisions explain --format json
   direct_file_edits: forbidden
   legacy_schema_below: migration_input_only
 

package/bundle/skills/agentera/schemas/artifacts/experiments.yaml

@@ -275,7 +275,7 @@ PUBLICATION:
     id: EP1
     operation: publish
     command: >-
-      agentera state experiments publish --objective ID [--id ID]
+      npx -y agentera@next state experiments publish --objective ID [--id ID]
       --input EXPERIMENT.yaml --format json
     description: >-
       The typed state writer is the mutation authority. It validates the
@@ -334,10 +334,10 @@ RETRIEVAL:
   1:
     id: ER1
     list: >-
-      agentera state experiments list --objective ID [--limit N]
+      npx -y agentera@next state experiments list --objective ID [--limit N]
       [--cursor TOKEN] --format json
     get: >-
-      agentera state experiments get --id ID --format json
+      npx -y agentera@next state experiments get --id ID --format json
     description: >-
       List returns newest-first objective-scoped canonical entities. Get returns
       one exact entity by bare ID.

package/bundle/skills/agentera/schemas/artifacts/glossary.yaml

@@ -42,7 +42,7 @@ DOCUMENT:
 PUBLICATION:
   implementation: active
   owner: build
-  command: agentera state glossary publish --input REQUEST --format json
+  command: npx -y agentera@next state glossary publish --input REQUEST --format json
   request_schema_version: agentera.glossaryPublicationRequest.v1
   atomic_unit: complete_document
   lock: established_project_writer_lock

package/bundle/skills/agentera/schemas/artifacts/health.yaml

@@ -67,9 +67,9 @@ ENTITY_AUTHORITY:
   artifact: health
   boundary: health_audit
   retrieval:
-    list: agentera state health list --format json
-    get: agentera state health get --id ID --format json
-  mutation: agentera state health explain --verb append --format json
+    list: npx -y agentera@next state health list --format json
+    get: npx -y agentera@next state health get --id ID --format json
+  mutation: npx -y agentera@next state health explain --verb append --format json
   direct_file_edits: forbidden
   legacy_schema_below: migration_input_only
 

package/bundle/skills/agentera/schemas/artifacts/plan.yaml

@@ -65,11 +65,11 @@ ENTITY_AUTHORITY:
   boundaries: [plan, plan_task]
   relationship: plan_task.record.plan is a bare plan ID
   retrieval:
-    list: agentera state plan list --format json
-    get: agentera state plan get --id ID --format json
-    tasks_list: agentera state plan tasks list [PLAN_ID] --format json
-    task_get: agentera state plan tasks get --id ID --format json
-  mutation: agentera state plan explain --format json
+    list: npx -y agentera@next state plan list --format json
+    get: npx -y agentera@next state plan get --id ID --format json
+    tasks_list: npx -y agentera@next state plan tasks list [PLAN_ID] --format json
+    task_get: npx -y agentera@next state plan tasks get --id ID --format json
+  mutation: npx -y agentera@next state plan explain --format json
   direct_file_edits: forbidden
   aggregate_schema_below: atomic_create_input
   migration_compatibility: explicitly_labeled_fields_only
@@ -419,7 +419,7 @@ TASK:
     type: mapping
     required: false
     description: >-
-      CLI-owned evaluator state written only by `agentera state plan
+      CLI-owned evaluator state written only by `npx -y agentera@next state plan
       record-evaluation`. It records attempt and failure counts, the latest
       verdict, retained failure evidence, and stable attempt provenance. Normal
       workflow records evaluation before completion. As recovery for persisted
@@ -598,6 +598,8 @@ LIFECYCLE_CONTRACT:
           - .venv
           - .pytest_cache
           - .ruff_cache
+          - .playwright-cli
+          - .agentera-generated
           - .cache
           - .snapshots
           - __pycache__
@@ -635,13 +637,13 @@ LIFECYCLE_CONTRACT:
           reason: Installed third-party dependencies are vendor content.
         - patterns: [.pnpm-store, .pnpm-store/**, .venv, .venv/**]
           reason: Package and Python environments are external dependency caches.
-        - patterns: [.pytest_cache, .pytest_cache/**, .ruff_cache, .ruff_cache/**]
-          reason: Tool caches are generated and carry no product contract.
+        - patterns: [.pytest_cache, .pytest_cache/**, .ruff_cache, .ruff_cache/**, .playwright-cli, .playwright-cli/**]
+          reason: Tool caches and local browser sessions are generated and carry no product contract.
         - patterns: ["**/.cache", "**/.cache/**", .snapshots, .snapshots/**]
           reason: Caches and filesystem snapshots are generated or external state.
         - patterns: ["**/dist", "**/dist/**", "**/build", "**/build/**", "**/coverage", "**/coverage/**"]
           reason: Compiled, bundled, and coverage outputs are generated from classified sources.
-        - patterns: [packages/cli/bundle, packages/cli/bundle/**, "**/.astro", "**/.astro/**", "**/.svelte-kit", "**/.svelte-kit/**"]
+        - patterns: [packages/cli/.agentera-generated, packages/cli/.agentera-generated/**, packages/cli/bundle, packages/cli/bundle/**, "**/.astro", "**/.astro/**", "**/.svelte-kit", "**/.svelte-kit/**"]
           reason: Runtime bundles and framework outputs are generated publication artifacts.
         - patterns: [.wrangler, .wrangler/**, "**/.wrangler", "**/.wrangler/**", "*.tgz", "**/*.tgz"]
           reason: Deployment outputs and package tarballs are generated publication artifacts.
@@ -665,7 +667,7 @@ LIFECYCLE_CONTRACT:
       - packages/cli/src/cli/appContext.ts
       - packages/cli/src/cli/commands/state/plan*.ts
       - packages/cli/src/cli/commands/prime.ts
-      - packages/cli/src/state/plan*.ts
+      - packages/cli/src/state/{plan*,entityListRuntimeRegistry}.ts
       - packages/cli/src/state/durability.ts
       - packages/cli/src/cli/commands/prime/*.ts
       - packages/cli/src/cli/capabilityContext/*.ts

package/bundle/skills/agentera/schemas/artifacts/progress.yaml

@@ -56,9 +56,9 @@ ENTITY_AUTHORITY:
   artifact: progress
   boundary: progress_cycle
   retrieval:
-    list: agentera state progress list --format json
-    get: agentera state progress get --id ID --format json
-  mutation: agentera state progress explain --verb append --format json
+    list: npx -y agentera@next state progress list --format json
+    get: npx -y agentera@next state progress get --id ID --format json
+  mutation: npx -y agentera@next state progress explain --verb append --format json
   direct_file_edits: forbidden
   legacy_schema_below: migration_input_only
   semantic_recency:

package/bundle/skills/agentera/schemas/artifacts/todo.yaml

@@ -132,10 +132,12 @@ PUBLIC_OWNERSHIP:
 
 LIFECYCLE:
   description: >-
-    set-severity, supersede, resolve, and reopen are flag-only typed transitions.
-    Each requires a reason and date; supersede additionally requires a distinct
-    existing replacement ID. Lifecycle operations are never accepted as
-    structured record content and never encoded as Markdown strikethrough.
+    activate is a flag-only reconciliation transition that requires the
+    preview effect SHA-256 and explicit confirmation. Item lifecycle transitions
+    set-severity, supersede, resolve, and reopen require a reason and date;
+    supersede additionally requires a distinct existing replacement ID. These
+    operations never accept structured record content or use Markdown
+    strikethrough.
   clearable_patch_fields: [target_version, requirements, acceptance, readiness]
   cli_owned_fields: [id, artifact, status, public_order, lifecycle]
   transition_fields: [reason, date, replacement]

package/dist/analytics/extractCorpus/cli.js

@@ -188,4 +188,3 @@ export function extractCorpusMain(argv, io = {}) {
         `${publication.signal_bytes} bytes${publication.signal_selection.capped ? "; selection applied" : ""}) [${total} records; ${familyBits}]`);
     return 0;
 }
-//# sourceMappingURL=cli.js.map

package/dist/analytics/extractCorpus/copilotSessions.js

@@ -273,4 +273,3 @@ export function extractCopilotSessions(storePath, errors, ctx) {
     }
     return records;
 }
-//# sourceMappingURL=copilotSessions.js.map

package/dist/analytics/extractCorpus/core.js

@@ -390,4 +390,3 @@ export function toolCallRecord(args) {
     return toolCallRecordFromItem({ ...args, item: payloadItem(args.event) });
 }
 export { isPlainObject, rglob, isDir, isFilePath };
-//# sourceMappingURL=core.js.map

package/dist/analytics/extractCorpus/corpus.js

@@ -165,4 +165,3 @@ export function buildCorpus(opts) {
     const deduped = dedupeRecords(records);
     return { metadata: buildMetadata(deduped, errors, runtimeStatuses, opts.coverage), records: deduped };
 }
-//# sourceMappingURL=corpus.js.map

package/dist/analytics/extractCorpus/coverageAudit.js

@@ -258,4 +258,3 @@ export function formatCoverageSummaryText(audit) {
     }
     return lines.join("\n");
 }
-//# sourceMappingURL=coverageAudit.js.map