agentera 3.0.0-dev.5 → 3.0.0-dev.7

package/bundle/references/cli/vocabulary.md

@@ -10,22 +10,22 @@ included when they shape cross-suite usage.
 
 ## Authority order
 
-| Authority | Owns |
-| --- | --- |
-| `references/cli/vocabulary-index.yaml` | Authority order, normalization rules, plain-language layer rules, and Decision 44 replacement boundaries. |
-| `skills/agentera/protocol.yaml` | Confidence, severity, decision labels, exit signals, visual tokens, glyphs, and phases. |
-| `skills/agentera/capability_schema_contract.yaml` | Capability schema structure, required groups, priorities, and primitive-reference fields. |
-| `skills/agentera/schemas/artifacts/*.yaml` | Artifact field grammar, status values, path contracts, and validation rules. |
-| `references/artifacts/artifact-registry-interface-model.yaml` | Artifact identity facts: `artifact_id`, display name, default path, producers, consumers, type, scope. |
-| `references/cli/app-lifecycle-vocabulary.yaml` | App lifecycle canonical statuses, deprecated aliases, operation verbs, status concepts, and consumer ownership boundaries. |
-| `references/cli/update-channels.yaml` | Stable and development update channels, dist-tag/git resolution, default channel, and override keys. |
-| `references/cli/bundle-skill-vocabulary.yaml` | Canonical concepts, compatibility boundaries, and classification rules for `bundle` and `SKILL.md` usage. |
-| `references/cli/capability-instruction-contract.yaml` | Decision 57 capability instruction-file contract, current `packages/cli/src/capabilities/<name>/instructions.ts` authority, and implemented `first_invocation_read` CLI/schema discoverability (D65 collapsed the legacy `full`/`compact_startup` distinction into a single `prime_context` value with runtime enforcement). |
-| `references/cli/routing-execution-vocabulary.yaml` | Canonical concepts, compatibility boundaries, and classification rules for routing, suggestions, delegation, worker spawning, runtime subagent mechanisms, and pre-spawn Git commits. |
-| `skills/agentera/SKILL.md` | Agentera routing entry point, routing model, CLI-first state access, installed-app status checks, and safety rails. |
-| `packages/cli/src/capabilities/*/instructions.ts` | Capability behavior, workflow grammar, step markers, and cross-capability boundaries. Loaded as a default-exported string constant and served via `agentera prime --context <name> --format json`. |
-| `the agentera CLI` and `packages/cli/src/upgrade (doctor/upgrade)` | CLI-visible command labels, upgrade output, and doctor diagnostics. |
-| `README.md`, `UPGRADE.md`, `DESIGN.md`, `.agentera/*.yaml` | User-facing phrasing, design vocabulary, and current project-state examples. |
+| Authority                                                          | Owns                                                                                                                                                                                                                                                                                                                         |
+| ------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `references/cli/vocabulary-index.yaml`                             | Authority order, normalization rules, plain-language layer rules, and Decision 44 replacement boundaries.                                                                                                                                                                                                                    |
+| `skills/agentera/protocol.yaml`                                    | Confidence, severity, decision labels, exit signals, visual tokens, glyphs, and phases.                                                                                                                                                                                                                                      |
+| `skills/agentera/capability_schema_contract.yaml`                  | Capability schema structure, required groups, priorities, and primitive-reference fields.                                                                                                                                                                                                                                    |
+| `skills/agentera/schemas/artifacts/*.yaml`                         | Artifact field grammar, status values, path contracts, and validation rules.                                                                                                                                                                                                                                                 |
+| `references/artifacts/artifact-registry-interface-model.yaml`      | Artifact identity facts: `artifact_id`, display name, default path, producers, consumers, type, scope.                                                                                                                                                                                                                       |
+| `references/cli/app-lifecycle-vocabulary.yaml`                     | App lifecycle canonical statuses, deprecated aliases, operation verbs, status concepts, and consumer ownership boundaries.                                                                                                                                                                                                   |
+| `references/cli/update-channels.yaml`                              | Stable and development update channels, dist-tag/git resolution, default channel, and override keys.                                                                                                                                                                                                                         |
+| `references/cli/bundle-skill-vocabulary.yaml`                      | Canonical concepts, compatibility boundaries, and classification rules for `bundle` and `SKILL.md` usage.                                                                                                                                                                                                                    |
+| `references/cli/capability-instruction-contract.yaml`              | Decision 57 capability instruction-file contract, current `packages/cli/src/capabilities/<name>/instructions.ts` authority, and implemented `first_invocation_read` CLI/schema discoverability (D65 collapsed the legacy `full`/`compact_startup` distinction into a single `prime_context` value with runtime enforcement). |
+| `references/cli/routing-execution-vocabulary.yaml`                 | Canonical concepts, compatibility boundaries, and classification rules for routing, suggestions, delegation, worker spawning, runtime subagent mechanisms, and pre-spawn Git commits.                                                                                                                                        |
+| `skills/agentera/SKILL.md`                                         | Agentera routing entry point, routing model, CLI-first state access, installed-app status checks, and safety rails.                                                                                                                                                                                                          |
+| `packages/cli/src/capabilities/*/instructions.ts`                  | Capability behavior, workflow grammar, step markers, and cross-capability boundaries. Loaded as a default-exported string constant and served via `agentera prime --context <name> --format json`.                                                                                                                           |
+| `the agentera CLI` and `packages/cli/src/upgrade (doctor/upgrade)` | CLI-visible command labels, upgrade output, and doctor diagnostics.                                                                                                                                                                                                                                                          |
+| `README.md`, `UPGRADE.md`, `DESIGN.md`, `.agentera/*.yaml`         | User-facing phrasing, design vocabulary, and current project-state examples.                                                                                                                                                                                                                                                 |
 
 ## Normalization rules
 
@@ -49,39 +49,43 @@ examples. Diagnostics should state object, state, cause, and fix.
 
 ## Product grammar
 
-| Term | Definition | Common sources |
-| --- | --- | --- |
-| Agentera | The open protocol for turning AI agents into engineering teams through shared project state, roles, decisions, and verification. | `README.md`, `.agentera/vision.yaml`, `skills/agentera/SKILL.md` |
-| Agentera v2 | The current architecture: one Agentera skill, one `/agentera` entry point, twelve capabilities, YAML project state, and CLI-first access. | `README.md`, `UPGRADE.md`, `.agentera/decisions.yaml` |
-| Agentera skill | The runtime-loaded Agentera skill at `skills/agentera/`. It contains the routing entry and twelve capabilities. | `skills/agentera/SKILL.md` |
-| Capability | A routed behavioral unit inside the Agentera skill, with the prose module `packages/cli/src/capabilities/<name>/instructions.ts` plus `triggers.yaml`, `artifacts.yaml`, `validation.yaml`, and `exit.yaml`. | `AGENTS.md`, `skills/agentera/capabilities/*`, `packages/cli/src/capabilities/*` |
-| Shared protocol | The primitive vocabulary in `protocol.yaml`: confidence, severity, decision labels, exits, visual tokens, glyphs, and phases. | `skills/agentera/protocol.yaml` |
-| Capability schema contract | The executable contract for capability schema groups, stable IDs, priorities, deprecations, and primitive references. | `skills/agentera/capability_schema_contract.yaml` |
-| Project state | Structured files that preserve intent, decisions, plans, progress, health, docs, design, and session continuity. | `README.md`, `.agentera/docs.yaml` |
-| Project history | Durable history kept in files so future agents do not reconstruct history from chat residue. | `README.md`, `.agentera/progress.yaml` |
-| Saved project context | Project artifacts plus global profile data that let future sessions reuse context and preferences. | `README.md`, `profilera` prose |
-| Sharp colleague | Agentera's voice: direct, opinionated, evidence-backed, warm enough to collaborate, and willing to push back. | `.agentera/vision.yaml`, `DESIGN.md`, capability prose |
-| Docs-first workflow | Document intended behavior before tests and code; docs define intent, tests enforce it, code implements it. | `dokumentera`, `planera`, `realisera` prose |
+| Term                       | Definition                                                                                                                                                                                                                                                                          | Common sources                                                                   |
+| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- |
+| Agentera                   | The agent. One persistent identity that thinks through every step and keeps working when you walk away — the colleague, not the team. The CLI is the brain and spine: it owns routing, memory, capability prose, and the worker-spec contract. Host coding agents (Claude, Cursor, Codex, Copilot, OpenCode) are harnesses that provide the model and tool runtime; Agentera provides the identity, memory, discipline, and routing. Identity is per-project: same personality, same capabilities, different memory, no bleed. Headline: one agent, one CLI, many capabilities. | `README.md`, `.agentera/vision.yaml`, `.agentera/decisions.yaml` (D74), `skills/agentera/SKILL.md` |
+| Host runtime (harness)      | A host coding agent — Claude, Cursor, Codex, Copilot, or OpenCode — that provides the model, the tool runtime, and the spawn capacity. Agentera is the agent; the host is the harness. The host learns one contract: the JSON the CLI returns from `agentera prime`. Editor runtime installs are transport (the `skills/` directory, `plugin.json`), not an extension surface. | `.agentera/vision.yaml`, `.agentera/decisions.yaml` (D74), `skills/agentera/SKILL.md` |
+| Product surface            | Where the same fixed Agentera workflow ships: `@agentera/cli` (the agent runtime and narrow waist — owns routing, memory, capability prose, and the worker-spec contract), `@agentera/mobile` (primary app, a client of the CLI), `@agentera/web` (site and docs), and host runtimes (Claude, Cursor, Codex, Copilot, OpenCode). Host runtimes are harnesses — clients of the CLI, not extension hosts or peers. | `README.md`, `AGENTS.md`, `packages/*/README.md`, `.agentera/decisions.yaml` (D74) |
+| @agentera/mobile           | The flagship mobile/web app package at `packages/mobile`. SvelteKit, Cursor SDK, Cloudflare Worker.                                                                                                                                                                                 | `packages/mobile/README.md`, `packages/mobile/DESIGN.md`                         |
+| Agentera skill             | Internal transport, not a product word. The bundle at `skills/agentera/` packages Agentera's routing entry and capability prose for host editor runtimes — the `skills/` directory and `plugin.json` manifests host editors require. It is the same fixed workflow, not user extensibility. Per Decision 74, "skill" is retired from product vocabulary and survives only as internal transport; the product word is capabilities. | `skills/agentera/SKILL.md`, `README.md` Internals, `.agentera/decisions.yaml` (D74) |
+| Capability                 | A routed behavioral unit of the single Agentera agent, driven through the CLI. Eleven top-level capabilities (status, vision, discuss, research, plan, build, optimize, audit, document, design, orchestrate) plus profile, which surfaces through existing capabilities but appears as a peer row in user-facing docs. Each capability has a prose module at `packages/cli/src/capabilities/<name>/instructions.ts` plus `triggers.yaml`, `artifacts.yaml`, `validation.yaml`, and `exit.yaml`. English names are canonical per Decision 70; the Swedish `-era` names are legacy v2 stable only (see Legacy Swedish capability names). | `AGENTS.md`, `skills/agentera/capabilities/*`, `packages/cli/src/capabilities/*`, `.agentera/decisions.yaml` (D70, D74) |
+| Capability canonical name (v3) | The English name binding for v3+ capability invocation, per Decision 70, under the single-agent identity crystallized in Decision 74. Promoted from the Decision 43 alias set. Mobile UX, web docs, host runtimes, and the CLI all use the same English name; the v2 stable distribution uses the legacy Swedish `-era` IDs (see `Legacy Swedish capability names`). | `.agentera/decisions.yaml` (D43, D70, D74), `references/cli/vocabulary-index.yaml` (protected_surfaces) |
+| Legacy Swedish capability names (v2 stable) | The historical Swedish `-era` IDs (e.g. `hej`, `resonera`) used by the v2 stable distribution (`npx -y agentera@latest`) and preserved as historical references in archived plans, decisions, and changelogs. Out of scope for v3 surface per Decisions 70 and 74; the single-agent identity uses English capability names exclusively. Coexistence probe surfaces per-distribution naming divergence. | `.agentera/decisions.yaml` (D70, D74), `references/cli/vocabulary-index.yaml` (protected_surfaces) |
+| Shared protocol            | Internal primitive vocabulary in `protocol.yaml`: confidence, severity, decision labels, exits, visual tokens, glyphs, and phases.                                                                                                                                                  | `skills/agentera/protocol.yaml`                                                  |
+| Capability schema contract | The executable contract for capability schema groups, stable IDs, priorities, deprecations, and primitive references.                                                                                                                                                               | `skills/agentera/capability_schema_contract.yaml`                                |
+| Project state              | Structured files that preserve intent, decisions, plans, progress, health, docs, design, and session continuity.                                                                                                                                                                    | `README.md`, `.agentera/docs.yaml`                                               |
+| Project history            | Durable history kept in files so future agents do not reconstruct history from chat residue.                                                                                                                                                                                        | `README.md`, `.agentera/progress.yaml`                                           |
+| Saved project context      | Project artifacts plus global profile data that let future sessions reuse context and preferences.                                                                                                                                                                                  | `README.md`, `profile` prose                                                   |
+| Sharp colleague            | Agentera's voice: direct, opinionated, evidence-backed, warm enough to collaborate, and willing to push back.                                                                                                                                                                       | `.agentera/vision.yaml`, `DESIGN.md`, capability prose                           |
+| Docs-first workflow        | Document intended behavior before tests and code; docs define intent, tests enforce it, code implements it.                                                                                                                                                                         | `document`, `plan`, `build` prose                                      |
 
 ## Capability grammar
 
-| Glyph | Capability | Role |
-| --- | --- | --- |
-| `⌂` | hej | Orientation, routing, dashboard briefing, and next best action. |
-| `⛥` | visionera | Project direction, north star, principles, identity, and strategic tensions. |
-| `❈` | resonera | Structured deliberation, tradeoff pressure, and decision thinking. |
-| `⬚` | inspirera | External pattern analysis and useful cross-pollination. |
-| `≡` | planera | Planning with behavioral acceptance criteria; owns WHAT and WHY. |
-| `⧉` | realisera | Verified autonomous development cycle; owns HOW. |
-| `⎘` | optimera | Metric-driven optimization through one experiment per invocation. |
-| `⛶` | inspektera | Codebase health audit, architecture review, and artifact current-state review. |
-| `▤` | dokumentera | Documentation layer; owns docs-first workflow guidance. |
-| `♾` | profilera | Reusable decision profile and preference extraction. |
-| `◰` | visualisera | Visual identity, design tokens, and design-system language. |
-| `⎈` | orkestrera | Multi-cycle orchestration; dispatches work and evaluates completion. |
-
-Capability names use Swedish-style `-era` verb forms. The name is the action:
-`planera` plans, `realisera` realizes, `optimera` optimizes.
+| Glyph | Capability  | Role                                                                           |
+| ----- | ----------- | ------------------------------------------------------------------------------ |
+| `⌂`   | status      | Orientation, routing, dashboard briefing, and next best action.                |
+| `⛥`   | vision      | Project direction, north star, principles, identity, and strategic tensions.   |
+| `❈`   | discuss     | Structured deliberation, tradeoff pressure, and decision thinking.             |
+| `⬚`   | research    | External pattern analysis and useful cross-pollination.                        |
+| `≡`   | plan        | Planning with behavioral acceptance criteria; owns WHAT and WHY.               |
+| `⧉`   | build       | Verified autonomous development cycle; owns HOW.                               |
+| `⎘`   | optimize    | Metric-driven optimization through one experiment per invocation.              |
+| `⛶`   | audit       | Codebase health audit, architecture review, and artifact current-state review. |
+| `▤`   | document    | Documentation layer; owns docs-first workflow guidance.                        |
+| `♾`   | profile     | Reusable decision profile and preference extraction.                           |
+| `◰`   | design      | Visual identity, design tokens, and design-system language.                    |
+| `⎈`   | orchestrate | Multi-cycle orchestration; dispatches work and evaluates completion.           |
+
+Capability names use plain English verb forms (Decision 70). The name is the action:
+`plan` plans, `build` realizes, `optimize` optimizes.
 
 ### Capability instruction contract
 
@@ -110,62 +114,65 @@ the prose module directly.
 
 ## Invocation and routing grammar
 
-| Term | Definition |
-| --- | --- |
-| CLI-first state access | Read project state through `agentera` top-level commands before raw artifact reads. |
-| Top-level state commands | The canonical namespace command is `state` followed by a subcommand (`plan`, `progress`, `health`, `todo`, `decisions`, `docs`, `objective`, `experiments`, `query`). Legacy top-level aliases remain during migration; see [audience-namespace-cli-migration.yaml](references/cli/audience-namespace-cli-migration.yaml). |
-| Artifact-backed briefing | Any briefing or routing decision backed by Agentera project artifacts. It must use CLI-first state access. |
-| Bare `/agentera` | Invocation without a specific request. It delegates to `hej` and renders the Hej dashboard from one composite source command. |
-| Hej dashboard | User-facing project briefing with logo, status metrics, a narrative read inside `status`, attention, next action, and `⌂ hej · <status>`. Issues summary uses `critical · degraded · annoying` only. |
-| `agentera hej` | Compact CLI source data for the caller-rendered dashboard. It is not the dashboard itself. |
-| Direct route | A canonical capability name with optional following topic text, `/agentera <capability-name>` with optional topic text, or `/agentera <primary-alias>` routes directly to that capability and bypasses natural-language matching. |
-| Canonical capability route | A Swedish capability name such as `resonera`, `planera`, or `orkestrera`, optionally followed by topic text, plus the slash form `/agentera <capability-name>` with optional topic text. Canonical names remain protocol identity. |
-| Primary route alias | The one plain `/agentera <alias>` direct route for a capability, owned by `ROUTE_ALIASES.primary_aliases`. Each canonical capability has exactly one primary alias. |
-| Secondary request wording | Natural-language phrases in capability trigger schemas, such as `deliberate`, `brainstorm`, `rubber duck`, `brief`, and `what's next`. They route through trigger matching and are not primary aliases. |
-| Natural-language trigger | A phrase in `schemas/triggers.yaml` that maps a request to a capability. |
-| Trigger priority | `high`, `medium`, or `low`; owned by the schema contract. |
-| High-confidence match | A natural-language request with enough trigger evidence to route without asking. |
-| Borderline match | A request with competing plausible routes. Agentera asks for disambiguation. |
-| Fallback to hej | No sufficient match routes to hej for orientation. |
-| Concrete next action | A route suggestion tied to an object such as `PLAN Task N`, `TODO`, `OBJECTIVE`, or `VISION refresh`. |
-| Suggest, don't force | Hej recommends the next capability but waits for user confirmation. |
-| Capability handoff label | A recommendation from one capability to another. Use glyph plus canonical name, such as `⧉ realisera` or `≡ planera`, not standalone slash-capability names. SG priority codes are internal protocol references and are not user-facing handoff labels. |
-| Explicit route documentation | User-facing examples that teach the actual entry route. Use `/agentera <alias>` such as `/agentera build`; do not present aliases as CLI commands. |
-| Runtime question tool | Host-native bounded-choice prompt. Current examples: Claude Code `AskUserQuestion`, Copilot `ask_user`, Codex `request_user_input`, and OpenCode `question`. These are guidance examples, not schema authority. |
-| Question-tool gating | Use a native question tool only for at least two meaningful non-terminal next actions or consequential Proceed/Cancel; `Done` and custom/free-form answers do not count as alternatives. Initial Agentera/hej briefs stay free-form unless bounded choices were requested or the suggested next step is a state-changing Proceed/Cancel handoff. A single non-mutating suggested handoff may use a free-form prompt, but a single state-changing handoff uses native Proceed/Cancel confirmation. State-changing means the proposed next step may write artifacts, edit code, run optimization or orchestration cycles, apply migrations, refresh app/runtime state, or otherwise mutate project/runtime state. Apply the behavior rule first, with examples such as ⧉ realisera, ≡ planera when creating or updating plans, ▤ dokumentera when writing docs, ⎘ optimera when running or applying optimization cycles, and ⎈ orkestrera when dispatching cycles. This dispatcher rule governs hej and capability handoff prompts; invoked capability prose can impose stricter question-tool requirements. |
-| Handoff confirmation | Clear free-form acceptance of the named single suggestion confirms invocation. Selecting a downstream capability option in a bounded prompt also confirms invocation; selecting `Done` stops without routing. Ambiguous replies get one clarifying question. |
-| Route | Direct user invocation by canonical capability name, primary alias, or slash route. A route is already consent to invoke the capability and does not need an extra handoff confirmation. |
-| Suggest | Recommend a downstream capability and wait for confirmation. |
-| Delegate | Orkestrera assigns approved plan work to a worker capability during an explicitly orchestrated flow. |
-| Spawn | Realisera or Optimera launches an isolated runtime worker through the host subagent mechanism. |
-| Subagent mechanism | Runtime support for worker execution through Claude Code, OpenCode, Codex CLI, Copilot CLI, Cursor IDE, or another host-native worker surface. |
-| Legacy bridge | Temporary v1 entry points, especially `/hej`, that guide users to `/agentera` and the v2 upgrade path. |
-
-CLI-visible `agentera hej` labels are source labels. Preserve them in CLI tests
+| Term                         | Definition                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| CLI-first state access       | Read project state through `agentera` top-level commands before raw artifact reads.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Top-level state commands     | The canonical namespace command is `state` followed by a subcommand (`plan`, `progress`, `health`, `todo`, `decisions`, `docs`, `objective`, `experiments`, `query`). Legacy top-level aliases remain during migration; see [audience-namespace-cli-migration.yaml](references/cli/audience-namespace-cli-migration.yaml).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| Artifact-backed briefing     | Any briefing or routing decision backed by Agentera project artifacts. It must use CLI-first state access.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| Bare `/agentera`             | Invocation without a specific request. It delegates to `status` and renders the status dashboard from one composite source command.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+| Status dashboard                | User-facing project briefing with logo, status metrics, a narrative read inside `status`, attention, next action, and `⌂ status · <status>`. Issues summary uses `critical · degraded · annoying` only.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| `agentera prime`               | Compact CLI source data for the caller-rendered dashboard. It is not the dashboard itself.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| Direct route                 | A canonical capability name with optional following topic text, `/agentera <capability-name>` with optional topic text, or `/agentera <primary-alias>` routes directly to that capability and bypasses natural-language matching.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Canonical capability route   | An English capability name such as `discuss`, `plan`, or `orchestrate`, optionally followed by topic text, plus the slash form `/agentera <capability-name>` with optional topic text. Canonical names remain protocol identity.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Primary route alias          | The one plain `/agentera <alias>` direct route for a capability, owned by `ROUTE_ALIASES.primary_aliases`. Each canonical capability has exactly one primary alias.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Secondary request wording    | Natural-language phrases in capability trigger schemas, such as `deliberate`, `brainstorm`, `rubber duck`, `brief`, and `what's next`. They route through trigger matching and are not primary aliases.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Natural-language trigger     | A phrase in `schemas/triggers.yaml` that maps a request to a capability.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| Trigger priority             | `high`, `medium`, or `low`; owned by the schema contract.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| High-confidence match        | A natural-language request with enough trigger evidence to route without asking.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Borderline match             | A request with competing plausible routes. Agentera asks for disambiguation.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Fallback to status             | No sufficient match routes to status for orientation.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Concrete next action         | A route suggestion tied to an object such as `PLAN Task N`, `TODO`, `OBJECTIVE`, or `VISION refresh`.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| Suggest, don't force         | Status recommends the next capability but waits for user confirmation.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Capability handoff label     | A recommendation from one capability to another. Use glyph plus canonical name, such as `⧉ build` or `≡ plan`, not standalone slash-capability names. SG priority codes are internal protocol references and are not user-facing handoff labels.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Explicit route documentation | User-facing examples that teach the actual entry route. Use `/agentera <alias>` such as `/agentera build`; do not present aliases as CLI commands.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Runtime question tool        | Host-native bounded-choice prompt. Current examples: Claude Code `AskUserQuestion`, Copilot `ask_user`, Codex `request_user_input`, and OpenCode `question`. These are guidance examples, not schema authority.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| Question-tool gating         | Use a native question tool only for at least two meaningful non-terminal next actions or consequential Proceed/Cancel; `Done` and custom/free-form answers do not count as alternatives. Initial Agentera/status briefs stay free-form unless bounded choices were requested or the suggested next step is a state-changing Proceed/Cancel handoff. A single non-mutating suggested handoff may use a free-form prompt, but a single state-changing handoff uses native Proceed/Cancel confirmation. State-changing means the proposed next step may write artifacts, edit code, run optimization or orchestration cycles, apply migrations, refresh app/runtime state, or otherwise mutate project/runtime state. Apply the behavior rule first, with examples such as ⧉ build, ≡ plan when creating or updating plans, ▤ document when writing docs, ⎘ optimize when running or applying optimization cycles, and ⎈ orchestrate when dispatching cycles. This dispatcher rule governs status and capability handoff prompts; invoked capability prose can impose stricter question-tool requirements. |
+| Handoff confirmation         | Clear free-form acceptance of the named single suggestion confirms invocation. Selecting a downstream capability option in a bounded prompt also confirms invocation; selecting `Done` stops without routing. Ambiguous replies get one clarifying question.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Route                        | Direct user invocation by canonical capability name, primary alias, or slash route. A route is already consent to invoke the capability and does not need an extra handoff confirmation.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| Suggest                      | Recommend a downstream capability and wait for confirmation.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Delegate                     | Orchestrate assigns approved plan work to a worker capability during an explicitly orchestrated flow.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| Spawn                        | Build or Optimize launches an isolated runtime worker through the host subagent mechanism.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| Subagent mechanism           | Runtime support for worker execution through Claude Code, OpenCode, Codex CLI, Copilot CLI, Cursor IDE, or another host-native worker surface.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| Legacy bridge                | Temporary v1 entry points, especially `/hej`, that guide users to `/agentera` and the v2 upgrade path.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+
+CLI-visible `agentera prime` labels are source labels. Preserve them in CLI tests
 and parsing code, but transform them before presenting a user dashboard:
-`mode:`, `profile:`, `health:`, `issues:`, `plan:`, `objective:`,
+`mode:`, `profile:`, `health:`, `todo:`, `plan:`, `objective:`,
 `attention:`, `next_action:`, and `source_contract:`.
 
 Primary route aliases are slash-route vocabulary, not CLI command vocabulary:
 
-| Canonical capability | Primary route alias |
-| --- | --- |
-| `hej` | `/agentera status` |
-| `visionera` | `/agentera vision` |
-| `resonera` | `/agentera discuss` |
-| `inspirera` | `/agentera research` |
-| `planera` | `/agentera plan` |
-| `realisera` | `/agentera build` |
-| `optimera` | `/agentera optimize` |
-| `inspektera` | `/agentera audit` |
-| `dokumentera` | `/agentera document` |
-| `profilera` | `/agentera profile` |
-| `visualisera` | `/agentera design` |
-| `orkestrera` | `/agentera orchestrate` |
-
-Do not teach primary aliases as CLI state commands. The CLI state surface
-remains `hej`, `plan`, `progress`, `health`, `todo`, `decisions`, `docs`,
-`objective`, `experiments`, and advanced `query`.
+| Canonical capability (v3) | Legacy Swedish ID (v2 stable) | Slash route              |
+| ------------------------- | ----------------------------- | ------------------------ |
+| `status`                  | `hej`                         | `/agentera status`       |
+| `vision`                  | `visionera`                   | `/agentera vision`       |
+| `discuss`                 | `resonera`                    | `/agentera discuss`      |
+| `research`                | `inspirera`                   | `/agentera research`     |
+| `plan`                    | `planera`                     | `/agentera plan`         |
+| `build`                   | `realisera`                   | `/agentera build`        |
+| `optimize`                | `optimera`                    | `/agentera optimize`     |
+| `audit`                   | `inspektera`                  | `/agentera audit`        |
+| `document`                | `dokumentera`                 | `/agentera document`     |
+| `profile`                 | `profilera`                   | `/agentera profile`      |
+| `design`                  | `visualisera`                 | `/agentera design`       |
+| `orchestrate`             | `orkestrera`                  | `/agentera orchestrate`  |
+
+Do not teach primary aliases as CLI state commands. v3 orientation is
+`agentera prime` (capability ID `status` via `prime --context status`); routine
+state reads use `agentera state plan`, `state progress`, `state health`,
+`state todo`, `state decisions`, `state docs`, `state objective`,
+`state experiments`, and advanced `state query`. The v2 stable distribution
+retains `hej` and the rest of the Swedish capability surface per Decision 70.
 
 When capability prose recommends another capability, use the handoff label
 grammar (`<glyph> <capability>`). Keep slash forms only when documenting the
@@ -194,23 +201,23 @@ ambiguous-term sweep remain separate follow-up work.
 
 ## Artifact grammar
 
-| Term | Definition |
-| --- | --- |
-| Artifact | A project or agent state file owned by one or more capabilities. |
-| Human-facing artifact | A root-level Markdown artifact intended for people, such as `TODO.md`, `CHANGELOG.md`, or `DESIGN.md`. |
-| Severity band policy | TODO.md severity bands are header-only allowed for Degraded (⇉), Normal (→), and Annoying (⇢); Critical (⇶) is enforced and must contain at least one `- [type]` item. Authority: `skills/agentera/schemas/artifacts/todo.yaml` CONVENTION TC6; executable rule in `packages/cli/src/hooks/validateArtifact.ts` `validateMdItems`. |
-| Agent-facing artifact | A structured YAML artifact under `.agentera/`, such as `.agentera/progress.yaml`. |
-| Global artifact | A user-level artifact outside a project, such as `PROFILE.md` or `USAGE.md`. |
-| Canonical artifact name | Display identifier such as `VISION.md`, `PROGRESS.md`, or `DOCS.md`; not always a literal path. |
-| Resolved artifact path | The actual path after consulting `.agentera/docs.yaml` mapping or the default layout. |
-| Artifact mapping | `.agentera/docs.yaml` rows that map canonical names to project-local paths and producers. |
-| ArtifactRegistry | The registry interface model for artifact IDs, display names, default paths, producers, consumers, type, scope, and special cases. |
-| `artifact_id` | Machine identifier such as `progress`, `health`, `docs`, or `objective`. |
-| `display_name` | Human-readable canonical name, usually the v1-style Markdown name. |
-| `default_path` | Registry-owned path used when no docs mapping overrides it. |
-| `local_role` | Capability relationship to an artifact: `produces`, `consumes`, or `produces_and_consumes`. |
-| Docs override boundary | `docs.yaml` may override paths for known display names; it must not redefine canonical identity facts. |
-| Objective state | Optimera state under `.agentera/optimera/<objective-name>/`, including `objective.yaml`, `experiments.yaml`, and harness files. |
+| Term                    | Definition                                                                                                                                                                                                                                                                                                                           |
+| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Artifact                | A project or agent state file owned by one or more capabilities.                                                                                                                                                                                                                                                                     |
+| Human-facing artifact   | A root-level Markdown artifact intended for people, such as `TODO.md`, `CHANGELOG.md`, or `DESIGN.md`.                                                                                                                                                                                                                               |
+| Severity band policy    | TODO.md severity bands (⇶ Critical, ⇉ Degraded, → Normal, ⇢ Annoying) may be header-only when they have no open work; open items use `- [ ] [type:train]` only. Authority: `skills/agentera/schemas/artifacts/todo.yaml` CONVENTION TC5; executable rule in `packages/cli/src/hooks/validateArtifact/markdown.ts` `validateMdItems`. |
+| Agent-facing artifact   | A structured YAML artifact under `.agentera/`, such as `.agentera/progress.yaml`.                                                                                                                                                                                                                                                    |
+| Global artifact         | A user-level artifact outside a project, such as `PROFILE.md` or `USAGE.md`.                                                                                                                                                                                                                                                         |
+| Canonical artifact name | Protocol `artifact_id` such as `plan`, `progress`, or `docs`; human-facing Markdown filenames such as `TODO.md` are `display_name` values, not protocol identity.                                                                                                                                                                    |
+| Resolved artifact path  | The actual path after consulting `.agentera/docs.yaml` mapping or the default layout.                                                                                                                                                                                                                                                |
+| Artifact mapping        | `.agentera/docs.yaml` rows that map `artifact_id` values to project-local paths and producers.                                                                                                                                                                                                                                       |
+| ArtifactRegistry        | The registry interface model for artifact IDs, display names, default paths, producers, consumers, type, scope, and special cases.                                                                                                                                                                                                   |
+| `artifact_id`           | Machine identifier such as `progress`, `health`, `docs`, or `objective`.                                                                                                                                                                                                                                                             |
+| `display_name`          | Human-readable filename label such as `VISION.md` or `TODO.md`; registry-owned, not protocol identity.                                                                                                                                                                                                                               |
+| `default_path`          | Registry-owned path used when no docs mapping overrides it.                                                                                                                                                                                                                                                                          |
+| `local_role`            | Capability relationship to an artifact: `produces`, `consumes`, or `produces_and_consumes`.                                                                                                                                                                                                                                          |
+| Docs override boundary  | `docs.yaml` may override paths for known display names; it must not redefine canonical identity facts.                                                                                                                                                                                                                               |
+| Objective state         | Optimize state under `.agentera/optimize/<objective-name>/`, including `objective.yaml`, `experiments.yaml`, and harness files.                                                                                                                                                                                                      |
 
 Canonical artifact IDs include `vision`, `decisions`, `plan`, `progress`,
 `todo`, `health`, `docs`, `design`, `profile`, `objective`, `experiments`,
@@ -221,54 +228,54 @@ Canonical artifact IDs include `vision`, `decisions`, `plan`, `progress`,
 
 ### Exit signals
 
-| Signal | Meaning | Use |
-| --- | --- | --- |
-| `complete` | The workflow finished successfully. | Normal completion. |
-| `flagged` | Work completed with caveats the user should know. | List each concern. |
-| `stuck` | The capability cannot proceed. | State blocker and attempted work. |
-| `waiting` | Required information is missing. | State exactly what is needed. |
+| Signal     | Meaning                                           | Use                               |
+| ---------- | ------------------------------------------------- | --------------------------------- |
+| `complete` | The workflow finished successfully.               | Normal completion.                |
+| `flagged`  | Work completed with caveats the user should know. | List each concern.                |
+| `stuck`    | The capability cannot proceed.                    | State blocker and attempted work. |
+| `waiting`  | Required information is missing.                  | State exactly what is needed.     |
 
 Exit marker grammar is `<glyph> <capability> · <status>`, for example
-`▤ dokumentera · complete`. For `flagged`, `stuck`, and `waiting`, add `▸`
+`▤ document · complete`. For `flagged`, `stuck`, and `waiting`, add `▸`
 details.
 
 ### Finding severity
 
-| Value | Meaning |
-| --- | --- |
+| Value      | Meaning                                                  |
+| ---------- | -------------------------------------------------------- |
 | `critical` | Broken functionality, security issue, or data-loss risk. |
-| `warning` | Works but poorly, confusingly, or in a fragile way. |
-| `info` | Minor, cosmetic, or low-impact improvement. |
+| `warning`  | Works but poorly, confusingly, or in a fragile way.      |
+| `info`     | Minor, cosmetic, or low-impact improvement.              |
 
 ### Issue severity
 
-| Value | Glyph | Meaning |
-| --- | --- | --- |
-| `critical` | `⇶` | Blocks progress or breaks functionality. |
-| `degraded` | `⇉` | Works, but poorly, slowly, or fragily. |
-| `normal` | `→` | Standard work. |
-| `annoying` | `⇢` | Cosmetic or minor friction. |
+| Value      | Glyph | Meaning                                  |
+| ---------- | ----- | ---------------------------------------- |
+| `critical` | `⇶`   | Blocks progress or breaks functionality. |
+| `degraded` | `⇉`   | Works, but poorly, slowly, or fragily.   |
+| `normal`   | `→`   | Standard work.                           |
+| `annoying` | `⇢`   | Cosmetic or minor friction.              |
 
 ### Confidence language
 
-| Value | Meaning |
-| --- | --- |
-| `firm` | User is committed. Treat as a hard constraint. |
+| Value         | Meaning                                         |
+| ------------- | ----------------------------------------------- |
+| `firm`        | User is committed. Treat as a hard constraint.  |
 | `provisional` | Best current answer. Treat as a strong default. |
-| `exploratory` | Direction to try. Treat as a suggestion. |
+| `exploratory` | Direction to try. Treat as a suggestion.        |
 
 Numeric confidence is `0-100`: `90-100` verified, `70-89` strong,
 `50-69` moderate, `30-49` weak, and `0-29` speculative.
 
 ### Phase language
 
-| Phase | Primary capabilities | Meaning |
-| --- | --- | --- |
-| `envision` | visionera | Define north star and direction. |
-| `deliberate` | resonera | Think through tradeoffs and decisions. |
-| `plan` | planera | Break intent into scoped work. |
-| `build` | realisera, optimera, dokumentera, visualisera | Produce code, docs, designs, or measured improvements. |
-| `audit` | inspektera | Evaluate health, risks, and state alignment. |
+| Phase        | Primary capabilities                          | Meaning                                                |
+| ------------ | --------------------------------------------- | ------------------------------------------------------ |
+| `envision`   | vision                                         | Define north star and direction.                       |
+| `deliberate` | discuss                                      | Think through tradeoffs and decisions.                 |
+| `plan`       | plan                                          | Break intent into scoped work.                         |
+| `build`      | build, optimize, document, design             | Produce code, docs, designs, or measured improvements. |
+| `audit`      | audit                                         | Evaluate health, risks, and state alignment.           |
 
 Use `phase` for protocol-level lifecycle state. Use `step` for capability-local
 progress markers such as `── step 2/6: verify`.
@@ -284,86 +291,86 @@ tests, labels, or active state.
 
 ## Workflow grammar
 
-| Form | Meaning | Example |
-| --- | --- | --- |
-| `Each invocation = one ...` | Capability scope limit. | `Each invocation = one experiment.` |
-| `─── <glyph> <capability> · <context> ───` | Capability introduction marker. | `─── ⎘ optimera · measure ───` |
-| `── step N/M: verb` | Capability-local progress marker. | `── step 4/8: implement` |
-| `## Safety rails` plus `<critical>` | Non-negotiable constraints. | `NEVER push to remote repos without explicit instruction.` |
-| `Detect mode/context/level` | Step 0 classification before the main workflow. | Dokumentera detects create, update, audit, or first-run survey. |
-| Decision gate | Explicit condition-based branch before proceeding. | Optimera keep/discard decision. |
-| Exit-early stop condition | Stop condition when work is already complete or unnecessary. | Docs current, no stale work found. |
-| Behavioral verification gate | Realisera check that behavior was verified against real project state. | Tests, builds, or manual verification. |
-| Pre-write self-audit | Prose check for verbosity mismatch, abstraction creep, and filler accumulation. | `agentera lint --artifact <ARTIFACT>` exposes the checks through the CLI. |
-| Plan-completion sweep | Realisera cleanup when plan tasks finish. | Progress rollup, changelog, TODO, health cross-reference, archive. |
-| Worker spawn | Isolated implementation or measurement by a worker through the host subagent mechanism. | Realisera and optimera can use it. |
-| Stale-base awareness | Prevent workers from branching from old `origin/main` or stale HEAD. | Use pre-spawn Git commits before spawning workers. |
-| Orchestration loop | Orkestrera loop: select, delegate, evaluate, resolve, log. | Orkestrera delegates; it does not implement. |
-| Evidence audit | Check that recorded verification actually proves acceptance criteria. | Orkestrera and inspektera use this language. |
-| Loop stop condition | Stop repeated failed cycles, tasks, or experiments. | Prevents endless retries. |
+| Form                                       | Meaning                                                                                 | Example                                                                   |
+| ------------------------------------------ | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
+| `Each invocation = one ...`                | Capability scope limit.                                                                 | `Each invocation = one experiment.`                                       |
+| `─── <glyph> <capability> · <context> ───` | Capability introduction marker.                                                         | `─── ⎘ optimize · measure ───`                                            |
+| `── step N/M: verb`                        | Capability-local progress marker.                                                       | `── step 4/8: implement`                                                  |
+| `## Safety rails` plus `<critical>`        | Non-negotiable constraints.                                                             | `NEVER push to remote repos without explicit instruction.`                |
+| `Detect mode/context/level`                | Step 0 classification before the main workflow.                                         | Document detects create, update, audit, or first-run survey.            |
+| Decision gate                              | Explicit condition-based branch before proceeding.                                      | Optimize keep/discard decision.                                           |
+| Exit-early stop condition                  | Stop condition when work is already complete or unnecessary.                            | Docs current, no stale work found.                                        |
+| Behavioral verification gate               | Build check that behavior was verified against real project state.                  | Tests, builds, or manual verification.                                    |
+| Pre-write self-audit                       | Prose check for verbosity mismatch, abstraction creep, and filler accumulation.         | `agentera lint --artifact <ARTIFACT>` exposes the checks through the CLI. |
+| Plan-completion sweep                      | Build cleanup when plan tasks finish.                                               | Progress rollup, changelog, TODO, health cross-reference, archive.        |
+| Worker spawn                               | Isolated implementation or measurement by a worker through the host subagent mechanism. | Build and optimize can use it.                                        |
+| Stale-base awareness                       | Prevent workers from branching from old `origin/main` or stale HEAD.                    | Use pre-spawn Git commits before spawning workers.                        |
+| Orchestration loop                         | Orchestrate loop: select, delegate, evaluate, resolve, log.                              | Orchestrate delegates; it does not implement.                              |
+| Evidence audit                             | Check that recorded verification actually proves acceptance criteria.                   | Orchestrate and audit use this language.                              |
+| Loop stop condition                        | Stop repeated failed cycles, tasks, or experiments.                                     | Prevents endless retries.                                                 |
 
 For user-facing operations, prefer plain aliases when the branded phrase does
 not add precision:
 
-| Internal or branded phrase | User-facing phrase |
-| --- | --- |
-| Reality Verification Gate | behavioral verification gate |
-| Conductor protocol | orchestration loop |
-| Evidence audit | verification review |
-| Memory layer | saved project context |
+| Internal or branded phrase | User-facing phrase           |
+| -------------------------- | ---------------------------- |
+| Reality Verification Gate  | behavioral verification gate |
+| Conductor protocol         | orchestration loop           |
+| Evidence audit             | verification review          |
+| Memory layer               | saved project context        |
 
 ### Artifact-writing checks
 
-| Term | Definition |
-| --- | --- |
-| Verbosity mismatch | Artifact prose exceeds the intended budget or grows without adding signal. |
-| Abstraction creep | Prose lacks a concrete anchor such as a path, line number, metric, identifier, commit, or quote. |
-| Filler accumulation | Prose accumulates hedges, redundant transitions, self-reference, summary preambles, or generic justification. |
-| Concrete anchor | A file path, line number, commit hash, metric value, identifier, or direct quote. |
-| Lead-with-conclusion | Start with the actionable conclusion, then provide evidence. |
-| Compaction | Keep recent full entries, preserve older one-line archives, and drop beyond retention limits. |
+| Term                 | Definition                                                                                                    |
+| -------------------- | ------------------------------------------------------------------------------------------------------------- |
+| Verbosity mismatch   | Artifact prose exceeds the intended budget or grows without adding signal.                                    |
+| Abstraction creep    | Prose lacks a concrete anchor such as a path, line number, metric, identifier, commit, or quote.              |
+| Filler accumulation  | Prose accumulates hedges, redundant transitions, self-reference, summary preambles, or generic justification. |
+| Concrete anchor      | A file path, line number, commit hash, metric value, identifier, or direct quote.                             |
+| Lead-with-conclusion | Start with the actionable conclusion, then provide evidence.                                                  |
+| Compaction           | Keep recent full entries, preserve older one-line archives, and drop beyond retention limits.                 |
 
 ## Capability-specific recurring vocabulary
 
-| Capability | Common terms |
-| --- | --- |
-| hej | Orientation, dashboard, returning project, fresh project, attention, next action, concrete object, route suggestion. |
-| visionera | North star, persona, principles, direction, identity, tensions, create/refine/replace/audit modes. |
-| resonera | Socratic questioning, one question at a time, honest friction, steelman, tradeoffs, decision pressure. |
-| inspirera | Source analysis, pattern extraction, cross-pollination, worth stealing, external practice, adaptation. |
-| planera | WHAT and WHY, behavioral acceptance criteria, scope, included/excluded/deferred, task dependencies, plan-level current-state check. |
-| realisera | Cycle, orient/select/research/plan/spawn/verify/commit/audit/log, HOW, progress log, worker spawn. |
-| optimera | Objective, experiment, baseline, harness, locked measurement, hypothesis, metric, regression, keep/discard gate. |
-| inspektera | Audit, health grade, dimensions, findings, evidence, impact, suggested action, artifact current-state review, deliberate decisions. |
-| dokumentera | Intent-first docs, explore-and-generate, update-and-verify, first-run survey, evergreen docs, docs become the spec. |
-| profilera | Decision profile, signal extraction, confidence, preference, validation, reusable user model. |
-| visualisera | Visual identity, design tokens, semantic weight, terminal-native, glyphs, logo scarcity. |
-| orkestrera | Plan execution, delegate, task-notification result, presence check, evaluate, resolve, loop stop condition. |
+| Capability  | Common terms                                                                                                                        |
+| ----------- | ----------------------------------------------------------------------------------------------------------------------------------- |
+| status      | Orientation, dashboard, returning project, fresh project, attention, next action, concrete object, route suggestion.                |
+| vision      | North star, persona, principles, direction, identity, tensions, create/refine/replace/audit modes.                                  |
+| discuss     | Socratic questioning, one question at a time, honest friction, steelman, tradeoffs, decision pressure.                              |
+| research    | Source analysis, pattern extraction, cross-pollination, worth stealing, external practice, adaptation.                              |
+| plan        | WHAT and WHY, behavioral acceptance criteria, scope, included/excluded/deferred, task dependencies, plan-level current-state check. |
+| build       | Cycle, orient/select/research/plan/spawn/verify/commit/audit/log, HOW, progress log, worker spawn.                                  |
+| optimize    | Objective, experiment, baseline, harness, locked measurement, hypothesis, metric, regression, keep/discard gate.                    |
+| audit       | Audit, health grade, dimensions, findings, evidence, impact, suggested action, artifact current-state review, deliberate decisions. |
+| document    | Intent-first docs, explore-and-generate, update-and-verify, first-run survey, evergreen docs, docs become the spec.                 |
+| profile     | Decision profile, signal extraction, confidence, preference, validation, reusable user model.                                       |
+| design      | Visual identity, design tokens, semantic weight, terminal-native, glyphs, logo scarcity.                                            |
+| orchestrate | Plan execution, delegate, task-notification result, presence check, evaluate, resolve, loop stop condition.                         |
 
 ## Runtime, install, and release grammar
 
-| Term | Definition |
-| --- | --- |
-| Agentera directory | Plain-language name for the local directory named by `AGENTERA_HOME`; user data stays at this directory root. |
-| App files directory | Plain-language name for `$AGENTERA_HOME/app`, where Agentera's scripts and skill files live. Internal JSON may call this `managedAppRoot`; do not use that phrase in prompts. |
-| User data directory | The `AGENTERA_HOME` root that keeps `PROFILE.md`, `USAGE.md`, `history/`, `benchmarks/`, `intermediate/`, `sessions/`, and other preserved user-state paths. |
-| `AGENTERA_HOME` | Environment variable pointing at the Agentera directory. Explain this only when the user needs the exact setting. |
-| Normal Agentera directory | Platform data directory for Agentera when `AGENTERA_HOME` is unset. |
-| `--install-root` | Compatibility flag name for existing CLI options; surrounding text should say Agentera directory. |
-| Directory with unknown files | A directory Agentera must not overwrite silently. Say this instead of unmanaged root. |
-| Missing normal directory | Previewable. Agentera can show a no-write repair preview. |
-| Missing chosen directory | Needs a user decision when provided through `AGENTERA_HOME` or explicit `--install-root`. |
-| Package refresh | Package-manager or marketplace update. It does not prove Agentera's app files are current. |
-| App repair | Normal repair flow that previews or applies Agentera app files plus managed runtime config, plugins, hooks, commands, and safe cleanup together. It must not edit shell startup files, and package-manager commands remain opt-in through `--update-packages`. |
-| `--only bundle` | Compatibility selector for narrow app-file work. Do not present it as the normal repair recommendation when managed runtime surfaces may also need repair. |
-| Preview | No-write mode. Required before upgrade or app repair writes; the underlying command flag is `--dry-run`. |
-| `--yes` | Explicit apply flag after preview and approval. |
-| Final check | Setup validation after upgrade apply. Uses the same app-home probe as `agentera doctor` (`build_doctor_status`), not `setup_doctor.build_report`. |
-| Package-update opt-in | External package manager changes require `--update-packages`. |
-| Runtime adapter | Runtime-specific Agentera adapter support for skill loading, hooks, artifact validation, lifecycle metadata, and diagnostics. |
-| Host support | What a runtime can theoretically do. Distinguish it from shipped Agentera behavior. |
-| Hook lifecycle | Runtime callbacks such as `SessionStart`, `Stop`, `PreToolUse`, and `PostToolUse`. |
-| Setup doctor | Diagnostic command surface for install/runtime health. |
+| Term                         | Definition                                                                                                                                                                                                                                                     |
+| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Agentera directory           | Plain-language name for the local directory named by `AGENTERA_HOME`; user data stays at this directory root.                                                                                                                                                  |
+| App files directory          | Plain-language name for `$AGENTERA_HOME/app`, where Agentera's scripts and skill files live. Internal JSON may call this `managedAppRoot`; do not use that phrase in prompts.                                                                                  |
+| User data directory          | The `AGENTERA_HOME` root that keeps `PROFILE.md`, `USAGE.md`, `history/`, `benchmarks/`, `intermediate/`, `sessions/`, and other preserved user-state paths.                                                                                                   |
+| `AGENTERA_HOME`              | Environment variable pointing at the Agentera directory. Explain this only when the user needs the exact setting.                                                                                                                                              |
+| Normal Agentera directory    | Platform data directory for Agentera when `AGENTERA_HOME` is unset.                                                                                                                                                                                            |
+| `--install-root`             | Compatibility flag name for existing CLI options; surrounding text should say Agentera directory.                                                                                                                                                              |
+| Directory with unknown files | A directory Agentera must not overwrite silently. Say this instead of unmanaged root.                                                                                                                                                                          |
+| Missing normal directory     | Previewable. Agentera can show a no-write repair preview.                                                                                                                                                                                                      |
+| Missing chosen directory     | Needs a user decision when provided through `AGENTERA_HOME` or explicit `--install-root`.                                                                                                                                                                      |
+| Package refresh              | Package-manager or marketplace update. It does not prove Agentera's app files are current.                                                                                                                                                                     |
+| App repair                   | Normal repair flow that previews or applies Agentera app files plus managed runtime config, plugins, hooks, commands, and safe cleanup together. It must not edit shell startup files, and package-manager commands remain opt-in through `--update-packages`. |
+| `--only bundle`              | Compatibility selector for narrow app-file work. Do not present it as the normal repair recommendation when managed runtime surfaces may also need repair.                                                                                                     |
+| Preview                      | No-write mode. Required before upgrade or app repair writes; the underlying command flag is `--dry-run`.                                                                                                                                                       |
+| `--yes`                      | Explicit apply flag after preview and approval.                                                                                                                                                                                                                |
+| Final check                  | Setup validation after upgrade apply. Uses the same app-home probe as `agentera doctor` (`build_doctor_status`), not `setup_doctor.build_report`.                                                                                                              |
+| Package-update opt-in        | External package manager changes require `--update-packages`.                                                                                                                                                                                                  |
+| Runtime adapter              | Runtime-specific Agentera adapter support for skill loading, hooks, artifact validation, lifecycle metadata, and diagnostics.                                                                                                                                  |
+| Host support                 | What a runtime can theoretically do. Distinguish it from shipped Agentera behavior.                                                                                                                                                                            |
+| Hook lifecycle               | Runtime callbacks such as `SessionStart`, `Stop`, `PreToolUse`, and `PostToolUse`.                                                                                                                                                                             |
+| Setup doctor                 | Diagnostic command surface for install/runtime health.                                                                                                                                                                                                         |
 
 Canonical runtime names are Claude Code, OpenCode, Copilot CLI, Codex CLI, Cursor IDE, and Cursor Agent CLI.
 
@@ -373,7 +380,7 @@ Decision 54 makes app lifecycle state a protocol surface, not ad hoc output
 copy. The machine-readable authority is
 `references/cli/app-lifecycle-vocabulary.yaml`; it owns the canonical status
 order, status definitions, deprecated aliases, cross-major status concepts,
-scoped operation verbs, and consumer ownership boundaries for doctor, hej,
+scoped operation verbs, and consumer ownership boundaries for doctor, status,
 upgrade, docs, and tests.
 
 Use this prose as guidance only: human-readable text can be friendlier, but it
@@ -440,7 +447,7 @@ references, generic plain language, and ambiguous current prose.
 Use this prose as guidance only: current conceptual docs should say the object
 they mean, such as Agentera app files, suite package, plugin-shipped hooks,
 removed `bundle-status` command, Agentera routing entry point, skill entry file,
-v1 skill entry file, or legacy hej bridge. Preserve shipped identifiers and
+historical v1 skill entry paths (post-3.0 removed from the repo tree). Preserve shipped identifiers and
 literal paths such as `.agentera-bundle.json`, `bundle.status`,
 `activeBundleRoot`, `--only bundle`, and `skills/agentera/SKILL.md` unless an
 explicit compatibility migration is in scope.
@@ -451,61 +458,61 @@ human-facing boundary.
 
 ## Evaluation and evidence grammar
 
-| Term | Definition |
-| --- | --- |
-| Validation passed | Evidence that required checks completed successfully. Name the checks. |
-| Focused tests | Targeted tests for the changed surface. |
-| Full pytest | Repository-wide pytest run. Use exact counts when recorded. |
-| Capability validator | `uv run agentera check validate capability skills/agentera/capabilities/<name>`. |
-| Cross-capability validation | Checks that capability schemas agree with registry, protocol, routing, and exit contracts. |
-| Smoke eval | Runtime/setup check for crashes, non-zero exits, or obvious host failures. |
-| Live-host smoke | Explicit opt-in model-host check against real runtime access. |
-| Semantic eval | Offline fixture evaluation that checks whether captured output means the right thing. |
-| Semantic fixture | Markdown fixture with prompt, seeded project state, captured output, tool trace, and expected facts. |
-| Startup-overhead analysis | Local-only Decision 51 measurement surface for raw Agentera artifact access after CLI state calls during capability startup/state gathering. It replaced an uncommitted route/intro startup-window draft that found zero qualifying windows, and must report the retained `CLI state -> raw artifact access` metric before recommending a startup envelope or guidance fix. |
-| Startup report | Human-readable and structured report pair that includes boundary source, runtime coverage, startup metrics, threshold rationale, recommendation, and privacy caveats without raw transcript text or raw local paths. |
-| Seeded project state | Fixture-provided artifacts used as the source of truth for expected behavior. |
-| Oracle | Artifact-derived expectation, such as the exact plan task hej should route to. |
-| Regression | Required safety check for behavior that must not degrade. |
-| Harness | Optimera measurement substrate. Once approved, it is immutable ground truth. |
-| Objective | Measurable optimization charter under `.agentera/optimera/<name>/`. |
-| Experiment | One falsifiable optimization attempt with hypothesis, method, metric, regression, status, and conclusion. |
-| Keep/discard gate | Keep only if the metric improves and regression gates pass; discard otherwise. |
+| Term                        | Definition                                                                                                                                                                                                                                                                                                                                                                  |
+| --------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Validation passed           | Evidence that required checks completed successfully. Name the checks.                                                                                                                                                                                                                                                                                                      |
+| Focused tests               | Targeted tests for the changed surface.                                                                                                                                                                                                                                                                                                                                     |
+| Full pytest                 | Repository-wide pytest run. Use exact counts when recorded.                                                                                                                                                                                                                                                                                                                 |
+| Capability validator        | `uv run agentera check validate capability skills/agentera/capabilities/<name>`.                                                                                                                                                                                                                                                                                            |
+| Cross-capability validation | Checks that capability schemas agree with registry, protocol, routing, and exit contracts.                                                                                                                                                                                                                                                                                  |
+| Smoke eval                  | Runtime/setup check for crashes, non-zero exits, or obvious host failures.                                                                                                                                                                                                                                                                                                  |
+| Live-host smoke             | Explicit opt-in model-host check against real runtime access.                                                                                                                                                                                                                                                                                                               |
+| Semantic eval               | Offline fixture evaluation that checks whether captured output means the right thing.                                                                                                                                                                                                                                                                                       |
+| Semantic fixture            | Markdown fixture with prompt, seeded project state, captured output, tool trace, and expected facts.                                                                                                                                                                                                                                                                        |
+| Startup-overhead analysis   | Local-only Decision 51 measurement surface for raw Agentera artifact access after CLI state calls during capability startup/state gathering. It replaced an uncommitted route/intro startup-window draft that found zero qualifying windows, and must report the retained `CLI state -> raw artifact access` metric before recommending a startup envelope or guidance fix. |
+| Startup report              | Human-readable and structured report pair that includes boundary source, runtime coverage, startup metrics, threshold rationale, recommendation, and privacy caveats without raw transcript text or raw local paths.                                                                                                                                                        |
+| Seeded project state        | Fixture-provided artifacts used as the source of truth for expected behavior.                                                                                                                                                                                                                                                                                               |
+| Oracle                      | Artifact-derived expectation, such as the exact plan task status should route to.                                                                                                                                                                                                                                                                                              |
+| Regression                  | Required safety check for behavior that must not degrade.                                                                                                                                                                                                                                                                                                                   |
+| Harness                     | Optimera measurement substrate. Once approved, it is immutable ground truth.                                                                                                                                                                                                                                                                                                |
+| Objective                   | Measurable optimization charter under `.agentera/optimera/<name>/`.                                                                                                                                                                                                                                                                                                         |
+| Experiment                  | One falsifiable optimization attempt with hypothesis, method, metric, regression, status, and conclusion.                                                                                                                                                                                                                                                                   |
+| Keep/discard gate           | Keep only if the metric improves and regression gates pass; discard otherwise.                                                                                                                                                                                                                                                                                              |
 
 ## Visual grammar
 
-| Token family | Values |
-| --- | --- |
-| Status tokens | `■` complete, `▣` in progress, `□` open, `▨` blocked. |
-| Severity tokens | `⇶` critical, `⇉` degraded, `→` normal, `⇢` annoying. |
-| Confidence tokens | `━` firm, `─` provisional, `┄` exploratory. |
-| Trend tokens | `⮉` improving, `⮋` degrading. |
-| Structural tokens | `───` section divider, `▸` list item, `·` separator, `→` flow, `█▓░` progress bar. |
-| Logo | Box-drawing Agentera logo. Use for the Hej dashboard, major completions, and significant artifacts. |
+| Token family      | Values                                                                                              |
+| ----------------- | --------------------------------------------------------------------------------------------------- |
+| Status tokens     | `■` complete, `▣` in progress, `□` open, `▨` blocked.                                               |
+| Severity tokens   | `⇶` critical, `⇉` degraded, `→` normal, `⇢` annoying.                                               |
+| Confidence tokens | `━` firm, `─` provisional, `┄` exploratory.                                                         |
+| Trend tokens      | `⮉` improving, `⮋` degrading.                                                                       |
+| Structural tokens | `───` section divider, `▸` list item, `·` separator, `→` flow, `█▓░` progress bar.                  |
+| Logo              | Box-drawing Agentera logo. Use for the Hej dashboard, major completions, and significant artifacts. |
 
 Visualisera owns visual identity in `DESIGN.md`. Protocol owns token meanings in
 `skills/agentera/protocol.yaml`.
 
 ## Canonical phrases
 
-| Phrase | Use |
-| --- | --- |
-| “The open protocol for turning AI agents into engineering teams.” | Product identity. |
-| “One install, one entry point, one query interface to all project state.” | v2 app-home promise. |
-| “Continuity lives in files, not memory.” | Realisera/project-state principle. |
-| “The conversation preserves reasoning; the artifact preserves the plan.” | Planera boundary. |
-| “Planera owns WHAT and WHY; realisera owns HOW.” | Planning/building boundary. |
-| “The colleague says what they think, then shows the evidence.” | Inspektera voice. |
-| “Findings contradicting deliberate decisions are not findings.” | Audit boundary. |
-| “Select the concrete next action before selecting the skill.” | Hej routing discipline. |
-| “A skill name without a concrete object is not a valid suggestion.” | Hej next-action rule. |
-| “Suggest, don’t force.” | Hej confirmation rule. |
-| “Document intended behavior before building.” | Dokumentera intent-first mode. |
-| “Write as intended steady state.” | Evergreen documentation rule. |
-| “Keep it DRY: reference, don’t repeat.” | Documentation maintenance rule. |
-| “The harness is the immutable ground truth.” | Optimera measurement rule. |
-| “Improve + pass regression = keep; everything else is discarded.” | Optimera experiment rule. |
-| “The orchestrator delegates; it does not implement.” | Orkestrera role boundary. |
+| Phrase                                                                    | Use                                                    |
+| ------------------------------------------------------------------------- | ------------------------------------------------------ |
+| "One agent, one CLI, many capabilities."                                   | Product identity headline (Decision 74).              |
+| “One install, one entry point, one query interface to all project state.” | CLI state-access promise (internals/contributor docs). |
+| “Continuity lives in files, not memory.”                                  | Realisera/project-state principle.                     |
+| “The conversation preserves reasoning; the artifact preserves the plan.”  | Plan boundary.                                      |
+| “Plan owns WHAT and WHY; build owns HOW.”                          | Planning/building boundary.                            |
+| “The colleague says what they think, then shows the evidence.”            | Audit voice.                                      |
+| “Findings contradicting deliberate decisions are not findings.”           | Audit boundary.                                        |
+| “Select the concrete next action before selecting the capability.”             | Hej routing discipline.                                |
+| “A capability name without a concrete object is not a valid suggestion.”       | Hej next-action rule.                                  |
+| “Suggest, don’t force.”                                                   | Hej confirmation rule.                                 |
+| “Document intended behavior before building.”                             | Dokumentera intent-first mode.                         |
+| “Write as intended steady state.”                                         | Evergreen documentation rule.                          |
+| “Keep it DRY: reference, don’t repeat.”                                   | Documentation maintenance rule.                        |
+| “The harness is the immutable ground truth.”                              | Optimera measurement rule.                             |
+| “Improve + pass regression = keep; everything else is discarded.”         | Optimera experiment rule.                              |
+| “The orchestrator delegates; it does not implement.”                      | Orkestrera role boundary.                              |
 
 ## Ambiguous terms to qualify
 
@@ -513,63 +520,63 @@ Do not use these terms bare. A busy developer should be able to search the
 phrase, identify the affected object, and know whether the term describes a
 schema concept, runtime capability, install state, or user action.
 
-| Ambiguous term | Why bare usage is risky | Required wording |
-| --- | --- | --- |
-| Skill | Confuses v1 standalone skills, the v2 Agentera skill, and internal workflows. | Use `Agentera skill` for the installed runtime surface, `v1 skill` for history, and `capability` for v2 workflows. |
-| Contract | Could mean schema structure, artifact shape, protocol primitive, adapter behavior, or product promise. | Use `schema contract`, `artifact schema`, `protocol primitives`, `runtime adapter contract`, or `product promise`. |
-| Status | Different surfaces use different state machines and output labels. | Use `exit status`, `task status`, `installed-app status`, `install status`, `docs status`, or `health status`. |
-| Freshness | Sounds like a branded synonym for several normal states: current, stale, synced, or out of date. | Use object-specific state wording such as `artifact is current`, `Agentera app files need repair`, `docs are current`, or `plan-level current-state check`. |
-| Checkpoint | In software, can mean commit, savepoint, restore point, model checkpoint, or milestone. | Use `final state sync`, `plan-level current-state check`, `checkpoint commit`, or `pre-dispatch checkpoint commit`. |
-| Stale | The cause and fix differ by object. | Use `stale artifact`, `Agentera app files need repair`, `stale marker`, or `stale worktree base`. Avoid `stale` in recovery prompts when `out of date` or `needs repair` is clearer. |
-| Phase | Conflicts with numbered workflow steps. | Use `phase` only for protocol lifecycle: `envision`, `deliberate`, `plan`, `build`, `audit`. Use `step` for capability-local actions. |
-| Objective state | Clear only inside optimera. | First mention `optimization objective state`; then `objective state` is fine in optimera context. Do not modify outside optimera or explicit user instruction. |
-| Support | Could mean theoretical host capability, shipped Agentera wiring, or verified behavior. | Use `host capability`, `Agentera adapter support`, or `tested support`. |
-| Runtime support | Too broad to be actionable in compatibility docs. | Replace with `host capability`, `Agentera adapter support`, or `tested support`, whichever is true. |
-| AskUserQuestion | Internal primitive leaking into human prose. | In user docs, say `ask the user`. In adapter docs, say `runtime question tool`. |
-| MCP | Optional substrate, not a core Agentera requirement. | Say `optional MCP integration` only where the feature literally depends on MCP. |
+| Ambiguous term  | Why bare usage is risky                                                                                | Required wording                                                                                                                                                                     |
+| --------------- | ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Skill           | Confuses v1 standalone skills, the host editor skill bundle, and internal workflows.                  | Per Decision 74, `skill` is internal transport, not product vocabulary. Use `capability` for Agentera workflows; reserve `skill` for the `skills/` directory and host editor manifests; `v1 skill` for history.       |
+| Contract        | Could mean schema structure, artifact shape, protocol primitive, adapter behavior, or product promise. | Use `schema contract`, `artifact schema`, `protocol primitives`, `runtime adapter contract`, or `product promise`.                                                                   |
+| Status          | Different surfaces use different state machines and output labels.                                     | Use `exit status`, `task status`, `installed-app status`, `install status`, `docs status`, or `health status`.                                                                       |
+| Freshness       | Sounds like a branded synonym for several normal states: current, stale, synced, or out of date.       | Use object-specific state wording such as `artifact is current`, `Agentera app files need repair`, `docs are current`, or `plan-level current-state check`.                          |
+| Checkpoint      | In software, can mean commit, savepoint, restore point, model checkpoint, or milestone.                | Use `final state sync`, `plan-level current-state check`, `checkpoint commit`, or `pre-dispatch checkpoint commit`.                                                                  |
+| Stale           | The cause and fix differ by object.                                                                    | Use `stale artifact`, `Agentera app files need repair`, `stale marker`, or `stale worktree base`. Avoid `stale` in recovery prompts when `out of date` or `needs repair` is clearer. |
+| Phase           | Conflicts with numbered workflow steps.                                                                | Use `phase` only for protocol lifecycle: `envision`, `deliberate`, `plan`, `build`, `audit`. Use `step` for capability-local actions.                                                |
+| Objective state | Clear only inside optimera.                                                                            | First mention `optimization objective state`; then `objective state` is fine in optimera context. Do not modify outside optimera or explicit user instruction.                       |
+| Support         | Could mean theoretical host capability, shipped Agentera wiring, or verified behavior.                 | Use `host capability`, `Agentera adapter support`, or `tested support`.                                                                                                              |
+| Runtime support | Too broad to be actionable in compatibility docs.                                                      | Replace with `host capability`, `Agentera adapter support`, or `tested support`, whichever is true.                                                                                  |
+| AskUserQuestion | Internal primitive leaking into human prose.                                                           | In user docs, say `ask the user`. In adapter docs, say `runtime question tool`.                                                                                                      |
+| MCP             | Optional substrate, not a core Agentera requirement.                                                   | Say `optional MCP integration` only where the feature literally depends on MCP.                                                                                                      |
 
 High-risk diagnostic rewrites:
 
-| Avoid in diagnostics | Use instead |
-| --- | --- |
-| `bundle freshness gap detected` | `Agentera app files need repair` |
-| `bundle freshness guard failed` | `install status check failed` |
-| `bundle refresh required` | `repair Agentera app files` |
-| `app refresh required` | `Agentera app files need repair` or `Agentera app files are outdated` |
-| `upgrade guard triggered` | `v1 migration check found legacy files` |
-| `stale marker` | `missing or outdated version marker` |
-| `artifact freshness failed` | `artifact is stale` or `artifact needs sync` |
+| Avoid in diagnostics            | Use instead                                                           |
+| ------------------------------- | --------------------------------------------------------------------- |
+| `bundle freshness gap detected` | `Agentera app files need repair`                                      |
+| `bundle freshness guard failed` | `install status check failed`                                         |
+| `bundle refresh required`       | `repair Agentera app files`                                           |
+| `app refresh required`          | `Agentera app files need repair` or `Agentera app files are outdated` |
+| `upgrade guard triggered`       | `v1 migration check found legacy files`                               |
+| `stale marker`                  | `missing or outdated version marker`                                  |
+| `artifact freshness failed`     | `artifact is stale` or `artifact needs sync`                          |
 
 ## Source index
 
 High-signal source surfaces for this vocabulary:
 
-| Source | Vocabulary surface |
-| --- | --- |
-| `skills/agentera/SKILL.md` | Routing entry, routing layers, CLI-first access, installed-app status check, and v1 migration check. |
-| `skills/agentera/protocol.yaml` | Protocol primitives, glyphs, phases, visual tokens, exit signals. |
-| `skills/agentera/capability_schema_contract.yaml` | Schema groups, priorities, stable IDs, primitive-reference fields. |
-| `packages/cli/src/capabilities/*/instructions.ts` | Workflow grammar, capability roles, safety rails, exit marker forms. Loaded as a default-exported string constant; runtime serves it via `agentera prime --context <name> --format json`. |
-| `skills/agentera/capabilities/*/schemas/*.yaml` | Trigger patterns, artifact roles, validation rules, exit conditions. |
-| `skills/agentera/schemas/artifacts/*.yaml` | Artifact fields, status enums, validation vocabulary, and protected current-state fields. |
-| `references/artifacts/artifact-registry-interface-model.yaml` | Canonical artifact registry language. |
-| `references/cli/app-lifecycle-vocabulary.yaml` | App lifecycle canonical status and operation vocabulary authority. |
-| `references/cli/update-channels.yaml` | Update channel resolution and override-key authority. |
-| `references/cli/bundle-skill-vocabulary.yaml` | Bundle and `SKILL.md` concept classification authority. |
-| `references/cli/capability-instruction-contract.yaml` | Decision 57 capability instruction-file and first-invocation read contract authority. |
-| `references/cli/routing-execution-vocabulary.yaml` | Routing and execution vocabulary authority. |
-| `the agentera CLI` | Flat State CLI labels and `agentera hej` source contract. |
-| `packages/cli/src/upgrade (doctor/upgrade)` | Upgrade and doctor output grammar. |
-| `packages/cli/src/state/installRoot.ts` | Install-root classification semantics. |
-| `hooks/validate_artifact.py` | Runtime artifact-write validation and hook exit codes. |
-| `README.md` | Product, invocation, artifact, and user-facing capability language. |
-| `UPGRADE.md` | Upgrade flow, package refresh, app-home repair, and runtime migration terms. |
-| `DESIGN.md` | Visual identity, glyph, severity, confidence, and structural token language. |
-| `.agentera/docs.yaml` | Current documentation registry, mapping, coverage, and audit vocabulary. |
-| `.agentera/decisions.yaml` | Decision grammar, v2 architecture rationale, routing decisions. |
-| `.agentera/progress.yaml` | Cycle, evidence, context, and final state-sync examples. |
-| `.agentera/health.yaml` | Audit dimensions, grades, trajectories, findings, and artifact current-state review. |
-| `.agentera/archive/*.md` | Historical plan-level current-state checks and staleness rationale. |
-| `.agentera/optimera/*` | Objective, experiment, harness, metric, and keep/discard examples. |
-| `fixtures/semantic/*.md` | Semantic eval fixture, oracle, and Hej dashboard constraints. |
-| `tests/` | Regression evidence for CLI labels, installed-app status, routing, exits, and schema contracts. |
+| Source                                                        | Vocabulary surface                                                                                                                                                                        |
+| ------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `skills/agentera/SKILL.md`                                    | Routing entry, routing layers, CLI-first access, installed-app status check, and v1 migration check.                                                                                      |
+| `skills/agentera/protocol.yaml`                               | Protocol primitives, glyphs, phases, visual tokens, exit signals.                                                                                                                         |
+| `skills/agentera/capability_schema_contract.yaml`             | Schema groups, priorities, stable IDs, primitive-reference fields.                                                                                                                        |
+| `packages/cli/src/capabilities/*/instructions.ts`             | Workflow grammar, capability roles, safety rails, exit marker forms. Loaded as a default-exported string constant; runtime serves it via `agentera prime --context <name> --format json`. |
+| `skills/agentera/capabilities/*/schemas/*.yaml`               | Trigger patterns, artifact roles, validation rules, exit conditions.                                                                                                                      |
+| `skills/agentera/schemas/artifacts/*.yaml`                    | Artifact fields, status enums, validation vocabulary, and protected current-state fields.                                                                                                 |
+| `references/artifacts/artifact-registry-interface-model.yaml` | Canonical artifact registry language.                                                                                                                                                     |
+| `references/cli/app-lifecycle-vocabulary.yaml`                | App lifecycle canonical status and operation vocabulary authority.                                                                                                                        |
+| `references/cli/update-channels.yaml`                         | Update channel resolution and override-key authority.                                                                                                                                     |
+| `references/cli/bundle-skill-vocabulary.yaml`                 | Bundle and `SKILL.md` concept classification authority.                                                                                                                                   |
+| `references/cli/capability-instruction-contract.yaml`         | Decision 57 capability instruction-file and first-invocation read contract authority.                                                                                                     |
+| `references/cli/routing-execution-vocabulary.yaml`            | Routing and execution vocabulary authority.                                                                                                                                               |
+| `the agentera CLI`                                            | Flat State CLI labels and `agentera hej` source contract.                                                                                                                                 |
+| `packages/cli/src/upgrade (doctor/upgrade)`                   | Upgrade and doctor output grammar.                                                                                                                                                        |
+| `packages/cli/src/state/installRoot.ts`                       | Install-root classification semantics.                                                                                                                                                    |
+| `hooks/validate_artifact.py`                                  | Runtime artifact-write validation and hook exit codes.                                                                                                                                    |
+| `README.md`                                                   | Product, invocation, artifact, and user-facing capability language.                                                                                                                       |
+| `UPGRADE.md`                                                  | Upgrade flow, package refresh, app-home repair, and runtime migration terms.                                                                                                              |
+| `DESIGN.md`                                                   | Visual identity, glyph, severity, confidence, and structural token language.                                                                                                              |
+| `.agentera/docs.yaml`                                         | Current documentation registry, mapping, coverage, and audit vocabulary.                                                                                                                  |
+| `.agentera/decisions.yaml`                                    | Decision grammar, v2 architecture rationale, routing decisions.                                                                                                                           |
+| `.agentera/progress.yaml`                                     | Cycle, evidence, context, and final state-sync examples.                                                                                                                                  |
+| `.agentera/health.yaml`                                       | Audit dimensions, grades, trajectories, findings, and artifact current-state review.                                                                                                      |
+| `.agentera/archive/*.md`                                      | Historical plan-level current-state checks and staleness rationale.                                                                                                                       |
+| `.agentera/optimera/*`                                        | Objective, experiment, harness, metric, and keep/discard examples.                                                                                                                        |
+| `fixtures/semantic/*.md`                                      | Semantic eval fixture, oracle, and Hej dashboard constraints.                                                                                                                             |
+| `tests/`                                                      | Regression evidence for CLI labels, installed-app status, routing, exits, and schema contracts.                                                                                           |