@vpxa/aikit 0.1.381 → 0.1.383

package/scaffold/dist/definitions/bodies.mjs

@@ -7,8 +7,9 @@ ${t.map((e,t)=>`   ${t+1}. ${e}`).join(`
 Execute these MCP calls at session start, before ANY other work:
 
 1. \`mcp__aikit__flow({ action: 'status' })\` — Check active flow state.
-2. \`mcp__aikit__status({ includePrelude: true })\` — Load L0 workspace context (compact summary).
-3. If workspaceCore is null → \`mcp__aikit__onboard({ path: "." })\` first, then status again.
+2. \`mcp__aikit__status({ includePrelude: true })\` — Load workspace skill + onboard context.
+3. If \`onboarded\` is false or \`onboard_context\` is null → \`mcp__aikit__onboard({ path: ".", mode: "generate" })\` first, then status again.
+4. If \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, or \`nextAction.kind === "update_onboard"\` → \`mcp__aikit__onboard({ path: ".", update: true })\` first, then status again.
 
 **Failure to execute these before any other action is a protocol violation.**
 
@@ -34,9 +35,13 @@ Auto-clarity exception: use fuller prose for security warnings, irreversible con
 
 When dispatching subagents, include this line: "Communication style: terse like smart caveman; technical substance intact; no filler; auto-clarity exception for security/irreversible/misread-prone sequences."
 
+## User-Facing Presentation
+
+Use \`present({ schemaVersion: 1, title, blocks })\` for almost every substantive user response. If the response is more than 3 sentences, contains a list/table/checklist/plan/status/verdict/summary/progress/evidence map, or asks for approval/choice, use \`present\`. Prefer \`present\` even without actions for read-only summaries; add \`actions\` for approvals, confirmations, and selections. Plain text only for tiny status updates or one simple question that fits in 3 short sentences.
+
 ## Bootstrap
-1. status({ includePrelude: true }) -> onboard({ path: "." }) if needed.
-1a. For flow dispatch: status({ includePrelude: true }) → if onboard missing or workspace stale, onboard({ path: ".", update: true }) before any subagent dispatch.
+1. status({ includePrelude: true }) -> onboard({ path: ".", mode: "generate" }) if missing.
+1a. For flow dispatch: status({ includePrelude: true }) → if \`onboard_context\` missing, generate onboard; if \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, run onboard({ path: ".", update: true }) before any subagent dispatch.
 2. Apply layered knowledge protocol (see below).<!-- layered-header -->
 3. search({ query: "SESSION CHECKPOINT", origin: "curated" }) before planning.
 5. Load skills by trigger: aikit always; multi-agents-development before delegation; present before non-tiny output (preferBrowser=true by default; set preferBrowser:false for inline rendering — auto-falls back to browser if client doesn't support inline); brainstorming for design decisions.
@@ -70,7 +75,7 @@ Classify each step by agent role:
 For Mixed flows, each step inherits classification from its dispatched agent. Write-capable agents get \`readonly: false\`; all others \`readonly: true\`.
 
 ### Pre-Dispatch Staleness Check
-Before dispatching a write-capable agent, run \`status({ includePrelude: true })\` to verify onboard freshness. If workspace structure changed since last onboard (new/deleted/modified files), run \`onboard({ path: ".", update: true })\` first. Read-only dispatches skip this check (0 token cost). The \`readonly\` flag is a contractual convention, not runtime enforcement — subagents retain full MCP tool access.
+Before dispatching a write-capable agent, run \`status({ includePrelude: true })\` to verify onboard freshness. If \`onboard_context\` is missing, generate it; if \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, run \`onboard({ path: ".", update: true })\` first. Read-only dispatches skip this check (0 token cost). The \`readonly\` flag is a contractual convention, not runtime enforcement — subagents retain full MCP tool access.
 
 ## Protocol Coverage Map
 - conversation-compression: before each dispatch batch, withdraw/profile context; after each batch, deposit status/files/decisions/blockers; never echo raw subagent output.
@@ -107,16 +112,16 @@ Every \`runSubagent\` prompt includes all of:
 
 1. **Agent + Goal** — exact specialist name, testable acceptance criteria.
 2. **Files + Boundary** — target files, do-not-touch list.
- 3. **Arch Context** — Pre-compress with AI Kit tools before including in prompt. pick by token budget: efficient → \`file_summary\` (T1=structure, T2=content), full → \`digest\`. Default efficient. **Never pass raw file contents — always compress first.** This eliminates subagent need for \`read_file\`.
+3. **Arch Context** — Pre-compress with AI Kit tools before including in prompt. pick by token budget: efficient → \`file_summary\` (T1=structure, T2=content), full → \`digest\`. Default efficient. **Never pass raw file contents — always compress first.** This eliminates subagent need for \`read_file\`.
 4. **Prior Knowledge** — \`knowledge({ action: "lesson", subAction: "list-lessons", topic: "<2-3 keywords>", minConfidence: 70 })\` + \`search({ query: "<task area>", category: "conventions", limit: 3 })\`. Include high-confidence results. Skip for Floor.
 5. **Artifacts Path** — active flow's run dir / artifacts path from \`flow({ action: 'status' })\`.
 6. **FORGE** — tier (from forge_classify), task_id, evidence requirements. Pass tier directly; Documenter/SKILL.md maps tier to docs generation depth internally. Reviewers add CRITICAL/HIGH claims into your task_id; never create their own.
-7. **Flow Context** — "Call \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\` as your FIRST action. Reuse withdrawn refs and L0 card refs before broad retrieval. Do NOT independently reload workspace-core or architecture cards when dispatch already carries applicable refs."
- 8. ${i().replace(/\n/g,`
+7. **Flow Context** — "Call \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\` as your FIRST action. Reuse withdrawn refs plus supplied workspace skill/onboard context before broad retrieval. Do NOT independently rediscover repo basics when dispatch already carries applicable refs."
+8. ${i().replace(/\n/g,`
     `)}
- 9. **Self-Review** — checklist before declaring status: scope respected? tests pass? conventions followed?
- 10. **Return contract** — \`DONE\` | \`DONE_WITH_CONCERNS\` | \`NEEDS_CONTEXT\` | \`BLOCKED\`. ≤200 words: status, files, decisions. Full detail only if BLOCKED.
- 11. **Read-Only Mode** — \`readonly: true|false\`. Controls whether agent may modify files. Derived from flow type + step classification. Write-capable agents (Implementer, Refactor, Frontend, Debugger) receive \`false\`; all others \`true\`. Contractual convention — no runtime enforcement.
+9. **Self-Review** — checklist before declaring status: scope respected? tests pass? conventions followed?
+10. **Return contract** — \`DONE\` | \`DONE_WITH_CONCERNS\` | \`NEEDS_CONTEXT\` | \`BLOCKED\`. ≤200 words: status, files, decisions. Full detail only if BLOCKED.
+11. **Read-Only Mode** — \`readonly: true|false\`. Controls whether agent may modify files. Derived from flow type + step classification. Write-capable agents (Implementer, Refactor, Frontend, Debugger) receive \`false\`; all others \`true\`. Contractual convention — no runtime enforcement.
 
 Always pass \`agentName\`. Missing/empty is a dispatch bug.
 
@@ -126,7 +131,7 @@ Always pass \`agentName\`. Missing/empty is a dispatch bug.
 
 | Need | Use |
 |------|-----|
-| L0 session briefing | \`status({ includePrelude: true })\` — workspace-core available after \`onboard()\`. Flow card via flow context. |
+| Workspace session context | \`status({ includePrelude: true })\` — workspace skill + onboard context available after \`onboard()\`. Flow context via L1 withdrawal. |
 | Assess scope before dispatch | \`file_summary\` |
 | Pre-populate subagent with context | \`file_summary\` |
 | L1 flow withdrawal | \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\` — reuse before broad retrieval |
@@ -134,14 +139,14 @@ Always pass \`agentName\`. Missing/empty is a dispatch bug.
 | L3 evidence/provenance | \`search({ query })\` + \`knowledge({ action: 'lesson' })\` — focused retrieval only |
 | Understand error during emergency | \`file_summary({ files, tier: 'T2', query })\` — never raw-read |
 | Between phases: compress state | \`session_digest({ persist: true, focus: "<topic>" })\` |
- | After batch: persist summary | \`knowledge({ action: 'remember', scope: 'flow', ... })\` |
+| After batch: persist summary | \`knowledge({ action: 'remember', scope: 'flow', ... })\` |
 
 \`read_file\` is ONLY for exact edit lines. Or when diagnosing an emergency with \`git diff --stat\` + \`check({})\`. No exceptions for planning or discovery.
 
 ## Evidence + Validation
 Use forge_classify for tier. Standard+ creates one Orchestrator-owned evidence_map task_id; reviewers add CRITICAL/HIGH claims into it; only Orchestrator runs gate.
 After implementation batches: check({}) + test_run({}) once, then blast_radius for shared/public changes.
-After write flow completion: onboard({ path, update: true }) → reindex({}) → produce_knowledge({}) to sync L0 cards and vector index. Verify with status({}). Read-only/Epilogue-only flows skip (0 token cost). If re-onboard fails, log warning and surface in flow status — do not block.
+After write flow completion: onboard({ path, update: true }) → reindex({}) → produce_knowledge({}) to refresh onboard context, workspace skill inputs, and vector index. Verify with status({}). Read-only/Epilogue-only flows skip (0 token cost). If re-onboard fails, log warning and surface in flow status — do not block.
 
 ## Presentation
 Use present for summaries, reports, evidence maps, task plans, batch results, verdicts, progress, reviews, approval gates. Plain chat only for <=2 short status sentences or one simple question.
@@ -160,7 +165,7 @@ Use present for summaries, reports, evidence maps, task plans, batch results, ve
 Use web_fetch/http first. On auth failure, load repo-access; if exhausted, use AI Kit browser. Do not use system browser for agent-visible verification.
 
 ## End
-- After write flows: onboard({ path, update: true }) → reindex({}) → produce_knowledge({}). L0 card regen via \`briefing-card-compiler\` if structural change detected.
+- After write flows: onboard({ path, update: true }) → reindex({}) → produce_knowledge({}). Refresh workspace skill/onboard context if structural change detected.
 - After read-only/epilogue-only flows: no reindex (0 token cost). remember decisions as normal.
 - If re-onboard/reindex fails: log warning, surface in flow status, do not block.
 - Flow-derived promotion: evidence-backed promotion candidates from final consolidation; confidence alone never promotes.
@@ -239,7 +244,7 @@ Use web_fetch/http first. On auth failure, load repo-access; if exhausted, use A
 ## Pre-Edit Checklist
 
 1. **Understand consumers** — \`graph({action:'find_nodes', name_pattern:'<target>'})\` → \`graph({action:'neighbors', node_id, direction:'incoming'})\`
- 2. **Compress, don't raw-read (HARD RULE)** — If you catch yourself about to call \`read_file\`, stop. Choose \`file_summary({ files, tier: 'T1', query })\` for structure-only, or \`file_summary({ files, tier: 'T2', query })\` for structure+content — one call, pick the right tier. \`read_file\` is ONLY for exact line content before \`replace_string_in_file\` — never for exploration or understanding.
+2. **Compress, don't raw-read (HARD RULE)** — If you catch yourself about to call \`read_file\`, stop. Choose \`file_summary({ files, tier: 'T1', query })\` for structure-only, or \`file_summary({ files, tier: 'T2', query })\` for structure+content — one call, pick the right tier. \`read_file\` is ONLY for exact line content before \`replace_string_in_file\` — never for exploration or understanding.
 3. **Snapshot risky edits** — \`checkpoint({action:'save', label:'pre-<scope>'})\` before cross-cutting changes
 4. **Estimate blast radius** — run \`blast_radius\` before and after shared/public symbol changes
 5. **TDD when tests exist** — failing test first, then minimum code

package/scaffold/dist/definitions/flows.mjs

@@ -1,5 +1,5 @@
 const e=e=>!e||e.length===0?``:`**Skills for this step:** ${e.map(e=>`\`${e}\``).join(`, `)}.
-Load them when their preconditions are met.`,t={design:{contextProfile:`researcher`,l0CardTypes:[`workspace-core`,`architecture`],l1Fields:[`objective`,`acceptanceCriteria`,`scope`,`exclusions`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`decisions`,`retrievedRefs`,`summary`],candidateLearnings:[`Architectural decisions with evidence`,`Scope boundary lessons`],handoffArtifact:`design-decisions.md`,handoffFields:[`decisions`,`scope`,`exclusions`,`retrievedRefs`]},spec:{contextProfile:`researcher`,l0CardTypes:[`workspace-core`],l1Fields:[`objective`,`acceptanceCriteria`,`decisions`,`scope`],l2Refs:`required`,l3Evidence:`none`,updates:[`acceptanceCriteria`,`decisions`,`unresolvedClaims`],candidateLearnings:[`Requirement ambiguity lessons when evidenced`,`Contract boundary clarity`],handoffArtifact:`spec.md`,handoffFields:[`acceptanceCriteria`,`scope`,`decisions`]},plan:{contextProfile:`implementer`,l0CardTypes:[`workspace-core`,`architecture`],l1Fields:[`acceptanceCriteria`,`scope`,`decisions`,`retrievedRefs`],l2Refs:`required`,l3Evidence:`none`,updates:[`decisions`,`artifacts`,`stepSummaries`],candidateLearnings:[`Planning pattern when reusable and evidenced`],handoffArtifact:`plan.md`,handoffFields:[`artifacts`,`decisions`]},task:{contextProfile:`implementer`,l0CardTypes:[`workspace-core`],l1Fields:[`acceptanceCriteria`,`scope`,`decisions`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`artifacts`,`stepSummaries`],candidateLearnings:[],handoffArtifact:`tasks.md`,handoffFields:[`artifacts`,`stepSummaries`]},execute:{contextProfile:`implementer`,l0CardTypes:[],l1Fields:[`artifacts`,`scope`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`on-demand`,updates:[`artifacts`,`summaries`,`failures`,`successPatterns`,`verifiedClaims`,`assumedClaims`],candidateLearnings:[`Candidate only — no promotion`],handoffArtifact:`progress.md`,handoffFields:[`artifacts`,`summaries`,`failures`,`successPatterns`]},verify:{contextProfile:`reviewer`,l0CardTypes:[],l1Fields:[`acceptanceCriteria`,`artifacts`,`verifiedClaims`,`assumedClaims`,`unresolvedClaims`],l2Refs:`on-demand`,l3Evidence:`required`,updates:[`verifiedClaims`,`unresolvedClaims`,`verifiedFinalOutcome`],candidateLearnings:[`Confirm or reject candidates — no direct promotion`],handoffArtifact:`verify-report.md`,handoffFields:[`verifiedClaims`,`verifiedFinalOutcome`]},"basic-design":{contextProfile:`researcher`,l0CardTypes:[`workspace-core`],l1Fields:[`objective`,`acceptanceCriteria`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`decisions`,`summary`],candidateLearnings:[],handoffArtifact:`design-decisions.md`,handoffFields:[`decisions`]},assess:{contextProfile:`implementer`,l0CardTypes:[`workspace-core`],l1Fields:[`objective`,`scope`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`summary`,`retrievedRefs`],candidateLearnings:[],handoffArtifact:`assessment.md`,handoffFields:[`scope`,`retrievedRefs`]},"basic-implement":{contextProfile:`implementer`,l0CardTypes:[],l1Fields:[`scope`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`on-demand`,updates:[`artifacts`,`summaries`,`verifiedClaims`],candidateLearnings:[`Candidate only — no promotion`],handoffArtifact:`progress.md`,handoffFields:[`artifacts`,`summaries`]},"basic-verify":{contextProfile:`reviewer`,l0CardTypes:[],l1Fields:[`acceptanceCriteria`,`artifacts`,`verifiedClaims`],l2Refs:`none`,l3Evidence:`required`,updates:[`verifiedClaims`,`verifiedFinalOutcome`],candidateLearnings:[],handoffArtifact:`verify-report.md`,handoffFields:[`verifiedFinalOutcome`]},"docs-sync":{contextProfile:`documenter`,l0CardTypes:[],l1Fields:[`artifacts`,`stepSummaries`,`candidateLearnings`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[],candidateLearnings:[`L2 candidate mapping from durable doc changes`],handoffArtifact:``,handoffFields:[]},"lesson-learned":{contextProfile:`documenter`,l0CardTypes:[],l1Fields:[`failures`,`successPatterns`,`candidateLearnings`,`verifiedFinalOutcome`],l2Refs:`none`,l3Evidence:`on-demand`,updates:[],candidateLearnings:[`Evidence-backed candidate learnings into L1/L3`],handoffArtifact:``,handoffFields:[]}},n="### Dispatch Protocol\n- **Max 2 corrective retries** per task, then escalate.\n- Use `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })` before dispatching.\n- Context: `file_summary` (T1=structure, T2=structure+content), `digest` for multi-file synthesis.\n- Subagents: `DONE` | `DONE_WITH_CONCERNS` | `NEEDS_CONTEXT` | `BLOCKED`. No `present`. No flow advance.",r='### Evidence Gate\nStandard/Critical: Use one stable `task_id` (from Design/Assessment).\n1. `evidence_map({ action: "create", task_id: "<slug>", tier: "<tier>" })` — create once.\n2. Add CRITICAL/HIGH claims during implementation and review.\n3. Orchestrator calls `evidence_map({ action: "gate", task_id: "<slug>" })` → YIELD/HOLD/HARD_BLOCK.\n4. HOLD → fix, re-gate (max 2 retries). HARD_BLOCK → escalate.',i={_epilogue:[{file:`steps/docs-sync/README.md`,content:`---
+Load them when their preconditions are met.`,t={design:{contextProfile:`researcher`,workspaceContextInputs:[`workspace-skill`,`onboard-context`,`onboard-architecture`],l1Fields:[`objective`,`acceptanceCriteria`,`scope`,`exclusions`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`decisions`,`retrievedRefs`,`summary`],candidateLearnings:[`Architectural decisions with evidence`,`Scope boundary lessons`],handoffArtifact:`design-decisions.md`,handoffFields:[`decisions`,`scope`,`exclusions`,`retrievedRefs`]},spec:{contextProfile:`researcher`,workspaceContextInputs:[`workspace-skill`,`onboard-context`],l1Fields:[`objective`,`acceptanceCriteria`,`decisions`,`scope`],l2Refs:`required`,l3Evidence:`none`,updates:[`acceptanceCriteria`,`decisions`,`unresolvedClaims`],candidateLearnings:[`Requirement ambiguity lessons when evidenced`,`Contract boundary clarity`],handoffArtifact:`spec.md`,handoffFields:[`acceptanceCriteria`,`scope`,`decisions`]},plan:{contextProfile:`implementer`,workspaceContextInputs:[`workspace-skill`,`onboard-context`,`onboard-architecture`],l1Fields:[`acceptanceCriteria`,`scope`,`decisions`,`retrievedRefs`],l2Refs:`required`,l3Evidence:`none`,updates:[`decisions`,`artifacts`,`stepSummaries`],candidateLearnings:[`Planning pattern when reusable and evidenced`],handoffArtifact:`plan.md`,handoffFields:[`artifacts`,`decisions`]},task:{contextProfile:`implementer`,workspaceContextInputs:[`workspace-skill`,`onboard-context`],l1Fields:[`acceptanceCriteria`,`scope`,`decisions`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`artifacts`,`stepSummaries`],candidateLearnings:[],handoffArtifact:`tasks.md`,handoffFields:[`artifacts`,`stepSummaries`]},execute:{contextProfile:`implementer`,workspaceContextInputs:[],l1Fields:[`artifacts`,`scope`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`on-demand`,updates:[`artifacts`,`summaries`,`failures`,`successPatterns`,`verifiedClaims`,`assumedClaims`],candidateLearnings:[`Candidate only — no promotion`],handoffArtifact:`progress.md`,handoffFields:[`artifacts`,`summaries`,`failures`,`successPatterns`]},verify:{contextProfile:`reviewer`,workspaceContextInputs:[],l1Fields:[`acceptanceCriteria`,`artifacts`,`verifiedClaims`,`assumedClaims`,`unresolvedClaims`],l2Refs:`on-demand`,l3Evidence:`required`,updates:[`verifiedClaims`,`unresolvedClaims`,`verifiedFinalOutcome`],candidateLearnings:[`Confirm or reject candidates — no direct promotion`],handoffArtifact:`verify-report.md`,handoffFields:[`verifiedClaims`,`verifiedFinalOutcome`]},"basic-design":{contextProfile:`researcher`,workspaceContextInputs:[`workspace-skill`,`onboard-context`],l1Fields:[`objective`,`acceptanceCriteria`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`decisions`,`summary`],candidateLearnings:[],handoffArtifact:`design-decisions.md`,handoffFields:[`decisions`]},assess:{contextProfile:`implementer`,workspaceContextInputs:[`workspace-skill`,`onboard-context`],l1Fields:[`objective`,`scope`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[`summary`,`retrievedRefs`],candidateLearnings:[],handoffArtifact:`assessment.md`,handoffFields:[`scope`,`retrievedRefs`]},"basic-implement":{contextProfile:`implementer`,workspaceContextInputs:[],l1Fields:[`scope`,`retrievedRefs`],l2Refs:`on-demand`,l3Evidence:`on-demand`,updates:[`artifacts`,`summaries`,`verifiedClaims`],candidateLearnings:[`Candidate only — no promotion`],handoffArtifact:`progress.md`,handoffFields:[`artifacts`,`summaries`]},"basic-verify":{contextProfile:`reviewer`,workspaceContextInputs:[],l1Fields:[`acceptanceCriteria`,`artifacts`,`verifiedClaims`],l2Refs:`none`,l3Evidence:`required`,updates:[`verifiedClaims`,`verifiedFinalOutcome`],candidateLearnings:[],handoffArtifact:`verify-report.md`,handoffFields:[`verifiedFinalOutcome`]},"docs-sync":{contextProfile:`documenter`,workspaceContextInputs:[],l1Fields:[`artifacts`,`stepSummaries`,`candidateLearnings`],l2Refs:`on-demand`,l3Evidence:`none`,updates:[],candidateLearnings:[`L2 candidate mapping from durable doc changes`],handoffArtifact:``,handoffFields:[]},"lesson-learned":{contextProfile:`documenter`,workspaceContextInputs:[],l1Fields:[`failures`,`successPatterns`,`candidateLearnings`,`verifiedFinalOutcome`],l2Refs:`none`,l3Evidence:`on-demand`,updates:[],candidateLearnings:[`Evidence-backed candidate learnings into L1/L3`],handoffArtifact:``,handoffFields:[]}},n="### Dispatch Protocol\n- **Max 2 corrective retries** per task, then escalate.\n- Use `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })` before dispatching.\n- Context: `file_summary` (T1=structure, T2=structure+content), `digest` for multi-file synthesis.\n- Subagents: `DONE` | `DONE_WITH_CONCERNS` | `NEEDS_CONTEXT` | `BLOCKED`. No `present`. No flow advance.",r='### Evidence Gate\nStandard/Critical: Use one stable `task_id` (from Design/Assessment).\n1. `evidence_map({ action: "create", task_id: "<slug>", tier: "<tier>" })` — create once.\n2. Add CRITICAL/HIGH claims during implementation and review.\n3. Orchestrator calls `evidence_map({ action: "gate", task_id: "<slug>" })` → YIELD/HOLD/HARD_BLOCK.\n4. HOLD → fix, re-gate (max 2 retries). HARD_BLOCK → escalate.',i={_epilogue:[{file:`steps/docs-sync/README.md`,content:`---
 name: _docs-sync
 description: Synchronize project documentation after flow completion
 skills: [docs]
@@ -25,7 +25,7 @@ Follow the \`docs\` skill's **Flow-Aware Sync** workflow:
 
 ## Knowledge Contract
 
-Profile: \`documenter\`. Reads L1 artifacts and step summaries, retrieves L2 on demand, produces L2 candidate mappings from durable doc changes. Does not write to L0 or L3.
+Profile: \`documenter\`. Reads L1 artifacts and step summaries, retrieves L2 on demand, produces L2 candidate mappings from durable doc changes. Does not write to workspace context or L3.
 
 ## Completion Criteria
 
@@ -276,7 +276,7 @@ Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this
 
 ## Knowledge Contract
 
-This step has a \`researcher\` context profile. It loads \`workspace-core\` and \`architecture\` L0 cards, reads objective/criteria/scope from L1, retrieves L2 on demand, and seeds design decisions into L1. Architectural decisions with evidence are learning candidates.
+This step has a \`researcher\` context profile. It uses workspace skill plus onboard architecture context, reads objective/criteria/scope from L1, retrieves L2 on demand, and seeds design decisions into L1. Architectural decisions with evidence are learning candidates.
 
 ## Produces
 
@@ -965,7 +965,7 @@ ${n}
 
 ## Knowledge Contract
 
-This step has an \`implementer\` context profile. It loads \`workspace-core\`, reads objective and scope from L1, and retrieves L2 on demand.
+This step has an \`implementer\` context profile. It uses workspace skill plus onboard context, reads objective and scope from L1, and retrieves L2 on demand.
 
 ## Completion Criteria
 
@@ -1065,7 +1065,7 @@ Write \`{{artifacts_path}}/design-decisions.md\` to disk. **You MUST create this
 
 ## Knowledge Contract
 
-This step has a \`researcher\` context profile. It loads \`workspace-core\` L0 cards and seeds decisions into L1.
+This step has a \`researcher\` context profile. It uses workspace skill plus onboard context and seeds decisions into L1.
 
 ## Produces
 

package/scaffold/dist/definitions/protocols.mjs

@@ -19,40 +19,40 @@ ${e===`<PROFILE>`?`**Profile:** Check your role → implementer | documenter | r
 
 ---`}function n(){return"\n## Evidence Citation Protocol (tier-aware)\n\nNo FORGE `task_id` → skip `evidence_map`; use `file:line` citations only.\nDo not create your own `task_id` or run the gate.\n\n| Tier | Your responsibility |\n|------|---------------------|\n| Floor | Findings with `file.ts#Lxx` citations. No `evidence_map`. |\n| Standard | Add 2-4 CRITICAL/HIGH findings with receipts. |\n| Critical | Add all CRITICAL/HIGH findings; tag contract/security claims with `safety_gate`. |\n\n**Every response MUST include:**\n- `**FORGE Task ID:** <task_id>` (passed in by Orchestrator, or state \"not provided\")\n- `**Tier applied:** Floor | Standard | Critical`\n- `**Findings:** <list>` with `file:line` receipts\n- Verdict: `APPROVED` | `CHANGES_REQUESTED` | `BLOCKED`\n\nDo NOT create a new `evidence_map`, run `evidence_map({action:'gate'})`, or add non-critical noise."}function r(...e){return e.filter(Boolean).join(`
 
-`)}function i({title:e=`Knowledge Recall`,intro:t,commands:n,followUp:i}={}){let a=[``,`### Retrieval-First Knowledge Access`,``,`**Always follow progressive discovery: L0 → exact-topic search/refs → broad scans.**`,``,"1. **Start with L0** — `status({ includePrelude: true })` or `aikit://skill/SKILL.md` resource",'2. **Search exact topic** — `search({ query: "<specific-topic>" })` — results include `ctxc_` refs','3. **Reuse refs** — `file_summary({ ref: "ctxc_<hash>" })` restores context without re-running search',"4. **Use `enrich: true`** on search/find/symbol for graph context without extra round-trip",`5. **Broad scan last resort** — only use find/glob/raw reads when L0 + exact search + refs fail`,``,`> **Note:** L1 (flow working-context withdrawal) is handled by your Orchestrator before dispatch —`,'> do not re-withdraw `knowledge({ scope: "flow" })` yourself. L2 (curated) is covered by step 2 above.',``].join(`
+`)}function i({title:e=`Knowledge Recall`,intro:t,commands:n,followUp:i}={}){let a=[``,`### Retrieval-First Knowledge Access`,``,`**Always follow progressive discovery: workspace context → exact-topic search/refs → broad scans.**`,``,'1. **Start with workspace context** — `status({ includePrelude: true })`; if `onboard_context` is missing run `onboard({ path: ".", mode: "generate" })`; if `onboard_context.freshness.status` is `stale` or `unknown` run `onboard({ path: ".", update: true })`; read `aikit://skill/SKILL.md` only when full guidance is needed','2. **Search exact topic** — `search({ query: "<specific-topic>" })` — results include `ctxc_` refs','3. **Reuse refs** — `file_summary({ ref: "ctxc_<hash>" })` restores context without re-running search',"4. **Use `enrich: true`** on search/find/symbol for graph context without extra round-trip",`5. **Broad scan last resort** — only use find/glob/raw reads when workspace context + exact search + refs fail`,``,`> **Note:** L1 (flow working-context withdrawal) is handled by your Orchestrator before dispatch —`,'> do not re-withdraw `knowledge({ scope: "flow" })` yourself. L2 (curated) is covered by step 2 above.',``].join(`
 `);return r(`## Pre-Task: ${e} (MANDATORY)`,t,["```",...(Array.isArray(n)?n:[n]).filter(Boolean),"```"].join(`
-`),i,a)}function a(){return r(`## Post-Task: Capture Lesson`,`**HARD RULE:** Before DONE, capture 1-2 lessons unless change is pure config/formatting.`,'Quick capture:\n```\nknowledge({ action: "lesson", subAction: "create", context: "<what situation you faced>", insight: "<what principle the solution demonstrates>", evidence: "<file:line or commit that proves it>", confidence: 65 })\n```',"If recalled lesson was confirmed/invalid, use `confirm` or `contradict`.")}const o=1,s=Object.freeze({version:1,l0MemoriesDir:`memories`,sessionStart:{requiredCards:[`workspace-core`],maxAdditionalCards:1,activeFlowPreference:`workflow-card`,totalTokenBudget:2100},retrievalOrder:[`l0`,`l1`,`l2-on-demand`,`l3-evidence-only`],noFlowFallback:`l0-plus-l2-with-turn-local-context`,degradedFallback:`prelude-manifest-canonical-markdown`,lifecycleAuthority:`opaque-owner-capability`,autoKnowledgeMode:`observer-only`,l0Budgets:Object.freeze({"workspace-core":{min:800,max:1200},architecture:{min:600,max:900},"testing-release":{min:600,max:900},"known-issues":{min:400,max:700},"workflow:*":{min:500,max:900}})});function c(e={}){let{audience:t=`agent`}=e,n=s,r=`## Layered Knowledge Protocol (v${n.version})
+`),i,a)}function a(){return r(`## Post-Task: Capture Lesson`,`**HARD RULE:** Before DONE, capture 1-2 lessons unless change is pure config/formatting.`,'Quick capture:\n```\nknowledge({ action: "lesson", subAction: "create", context: "<what situation you faced>", insight: "<what principle the solution demonstrates>", evidence: "<file:line or commit that proves it>", confidence: 65 })\n```',"If recalled lesson was confirmed/invalid, use `confirm` or `contradict`.")}const o=1,s=Object.freeze({version:1,workspaceContextDir:`onboard`,sessionStart:{requiredSurfaces:[`workspace-skill`,`onboard-context`],maxAdditionalSurfaces:1,activeFlowPreference:`flow-context`,totalTokenBudget:2100},retrievalOrder:[`workspace-context`,`l1`,`l2-on-demand`,`l3-evidence-only`],noFlowFallback:`workspace-context-plus-l2-with-turn-local-context`,degradedFallback:`prelude-manifest-canonical-markdown`,lifecycleAuthority:`opaque-owner-capability`,autoKnowledgeMode:`observer-only`,workspaceContextBudgets:Object.freeze({"workspace-skill":{min:400,max:1200},"onboard-context":{min:500,max:1200},"flow-context":{min:500,max:900}})});function c(e={}){let{audience:t=`agent`}=e,n=s,r=`## Layered Knowledge Protocol (v${n.version})
 
-AI Kit delivers knowledge through four layers:
+AI Kit delivers knowledge through startup workspace context plus L1-L3:
 
-- **L0 — Generated Briefing Cards**: Fast, task-ready workspace setup. \`workspace-core\` available via \`status({ includePrelude: true })\` (compact summary), populated after \`onboard({ path, mode: 'generate' })\` runs for the workspace. Treat this card as already-loaded workspace context: consume it before broad \`search\`, \`scope_map\`, \`digest\`, or repeated \`file_summary\`. If workspaceCore null → run onboard first. If a flow is active, \`workflow:<flow>\` loaded via flow context (replaces task card). Total budget: ${n.sessionStart.totalTokenBudget} tokens.
+- **Workspace Context — Workspace Skill + Onboard Context**: Fast, task-ready workspace setup. \`status({ includePrelude: true })\` returns the workspace skill preview/resource pointer plus \`onboard_context\` (freshness verdict, package map, architecture pointers, project profile, read order). Treat fresh onboard context as already-loaded workspace context: read \`aikit://skill/SKILL.md\` when full repo-specific guidance is needed, and use onboard files before broad \`search\`, \`scope_map\`, \`digest\`, or repeated \`file_summary\`. If \`onboarded\` is false or \`onboard_context\` is null → run \`onboard({ path: ".", mode: "generate" })\` first, then status again. If \`onboard_context.freshness.status\` is \`stale\` or \`unknown\` → run \`onboard({ path: ".", update: true })\`, then status again. Total budget: ${n.sessionStart.totalTokenBudget} tokens.
 - **L1 — Flow Working Context**: Active run state, current step, and role-filtered dispatch context. Withdraw via \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\`.
 - **L2 — Canonical Curated Knowledge**: Durable workspace archive managed by CuratedKnowledgeManager. Retrieve on demand via \`search()\` or \`knowledge({ action: 'read' })\`.
 - **L3 — Evidence Archive**: Auto-knowledge observations and tool-output evidence. Inspect only for provenance, conflict review, or promotion assessment. Never auto-injected.
 
 ### Hot Path
-1. Session start → run \`status({ includePrelude: true })\` to get compact workspace-core summary. Prerequisite: \`onboard({ path, mode: 'generate' })\` must have run for the workspace. If workspaceCore null → run onboard first, then status again.
-2. Before broad repo scans, extract and reuse the L0 facts: workspace shape, package map, tool surfaces, key entry points, constraints, and known pitfalls. If L0 answers enough, skip \`scope_map\`/wide \`search\` and go straight to task-specific retrieval.
-3. If flow active, \`workflow:<flow>\` loaded via flow context; use L1 snapshot + dispatch refs before broad retrieval. If no flow, may add one task card via \`file_summary\`.
+1. Session start → run \`status({ includePrelude: true })\` to get workspace skill + onboard context. Prerequisite: \`onboard({ path, mode: 'generate' })\` must have run for the workspace. If \`onboard_context\` is null → run onboard first, then status again. If freshness is \`stale\` or \`unknown\` → run \`onboard({ path: ".", update: true })\`, then status again.
+2. Before broad repo scans, extract and reuse fresh workspace skill/onboard facts: workspace shape, package map, architecture pointers, tool surfaces, key entry points, constraints, and known pitfalls. If this context answers enough, skip \`scope_map\`/wide \`search\` and go straight to task-specific retrieval.
+3. If flow active, use L1 snapshot + dispatch refs before broad retrieval. If no flow, may add one task card via \`file_summary\`.
 4. Retrieve L2 on demand.
 5. Inspect L3 only for evidence, provenance, or promotion.
 
 ### No-Flow Fallback
-- Keep L1 absent; workspace-core available via status after onboard; optionally one task card.
+- Keep L1 absent; workspace skill + onboard context available via status after onboard; optionally one task card.
 - L2 on demand; turn-local scratch, no L1 synthesis.
 
 ### Degraded Fallback
-- Missing L0 card after regeneration → use \`status({ includePrelude: true })\` as compact fallback, then only task-specific L2 retrieval; do not replace L0 with a workspace-wide scan.
+- Missing workspace skill/onboard context after regeneration → use \`status({ includePrelude: true })\` as compact fallback, then only task-specific L2 retrieval; do not replace the missing startup context with a workspace-wide scan.
 - Unavailable L1 → read persisted FlowRunMeta without mutation.
 - Unavailable indexed L2 → read canonical curated markdown directly.
 - Mark missing evidence unresolved; block promotion.
 `;return t===`skill`?r+`
 ### Skill Routing
-- Load L0 card families listed in \`LAYERED_KNOWLEDGE_OPERATING_POLICY.l0Budgets\`.
+- Use \`status({ includePrelude: true })\` for workspace skill + onboard context; read \`aikit://skill/SKILL.md\` only when full guidance is needed.
 - Route L1 withdrawal by configured profile; never promote.
 - Emit L3 evidence as observer-only; never navigate flow state.`:t===`flow`?r+`
 ### Step Contracts
-Each built-in flow step declares knowledge inputs (L0 card types, L1 fields, L2 refs, L3 evidence), context updates, candidate learnings, and handoff artifacts. The step knowledge contract drives role-aware L1 projection.`:r}const l=r(`## Output Rules (HARD RULE)`,`**Plain text is allowed only when ALL are true:**`,` - Response is 1-2 short sentences.`,` - No table, list, checklist, plan, report, verdict, review, summary, progress, evidence map, or batch result is being returned.`,` - No user approval, mandatory stop, or choice is needed.`,"Follow the **Presentation Priority** (1st Inline Visual - `present({ schemaVersion: 1, title, blocks })` → 2nd Interactive - `present({ schemaVersion: 1, title, blocks, actions })` → 3rd Plain Text). Only tiny status/questions that pass the gate above → plain text (Priority 3). Prefer `present` for all others, especially summaries, comparisons, reports, task plans, verdicts, and progress.");function u(){return'## Tool Preference — AI Kit First (HARD RULE)\n\n**Never start with `read_file`, `grep_search`, `semantic_search`, or `run_in_terminal`. AI Kit tools replace all of these.**\n\n| Need | Use | NEVER |\n|------|-----|-------|\n| Structure of a file | `file_summary({ path })` | `read_file` to "understand" it |\n| Find specific code | `file_summary({ files, tier: \'T2\', query })` | `read_file` to search |\n| Multiple files | `digest({ sources, query })` | Multiple `read_file` calls |\n| Reuse previous output | `file_summary({ ref, query })` with `enrich:true` | Re-reading same file |\n| Search codebase | `search({ query })` | `grep_search` / `semantic_search` |\n| Find files by path/pattern | `find({ glob, pattern })` — returns paths + preview | `grep_search` / `ls` |\n| Find a symbol | `symbol({ name })` | `grep_search` |\n| Trace data flow | `trace({ items: [{start, direction}] })` | Manual code tracing |\n| Module relationships | `graph({action:\'neighbors\', node_id})` | Manual import tracing |\n| Typecheck + lint | `check({})` | `run_in_terminal tsc` / biome |\n| Run tests | `test_run({})` | `run_in_terminal vitest` |\n| Impact analysis | `blast_radius({ files })` — trace affected files from changes | Manual caller tracing |\n| Complexity metrics | `measure({ path })` | Line counting / wc |\n| L0 briefing card (workspace-core) | `status({ includePrelude: true })` (compact summary), `file_summary` | Raw file discovery |\n| L0 briefing card (known issues) | `search({ query: "known issues" })` + `knowledge({ action: "lesson" })` | Manual history review |\n| Web research | `web_search({ queries })` + `web_fetch({ urls })` | `fetch_webpage` |\n\n`read_file` is ONLY acceptable when you need exact line content FOR EDITING (before `replace_string_in_file`).\n\nEven then, use `file_summary` first to identify which lines to read.'}const d=r(`## AI Kit Tools`,"The AI Kit MCP server provides search, analysis, memory, validation, and coordination tools. Available tools vary by platform and version — run `list_tools` at session start to see the exact set on your platform. Tool names use short form (e.g. `search`, `file_summary`) in instructions; your runtime may prefix them (e.g. `mcp__aikit__search`).",``,"If AI Kit tools are unavailable or missing, run `npx -y @vpxa/aikit@latest init --user`, then reload the client."),f={"code-agent-base":`# Code Agent - Shared Kernel
+Each built-in flow step declares workspace context inputs, L1 fields, L2 refs, L3 evidence, context updates, candidate learnings, and handoff artifacts. The step knowledge contract drives role-aware L1 projection.`:r}const l=r(`## Output Rules (HARD RULE)`,`**Plain text is allowed only when ALL are true:**`,` - Response is 1-2 short sentences.`,` - No table, list, checklist, plan, report, verdict, review, summary, progress, evidence map, or batch result is being returned.`,` - No user approval, mandatory stop, or choice is needed.`,"Follow the **Presentation Priority** (1st Inline Visual - `present({ schemaVersion: 1, title, blocks })` → 2nd Interactive - `present({ schemaVersion: 1, title, blocks, actions })` → 3rd Plain Text). Only tiny status/questions that pass the gate above → plain text (Priority 3). Prefer `present` for all others, especially summaries, comparisons, reports, task plans, verdicts, and progress.");function u(){return'## Tool Preference — AI Kit First (HARD RULE)\n\n**Never start with `read_file`, `grep_search`, `semantic_search`, or `run_in_terminal`. AI Kit tools replace all of these.**\n\n| Need | Use | NEVER |\n|------|-----|-------|\n| Structure of a file | `file_summary({ path })` | `read_file` to "understand" it |\n| Find specific code | `file_summary({ files, tier: \'T2\', query })` | `read_file` to search |\n| Multiple files | `digest({ sources, query })` | Multiple `read_file` calls |\n| Reuse previous output | `file_summary({ ref, query })` with `enrich:true` | Re-reading same file |\n| Search codebase | `search({ query })` | `grep_search` / `semantic_search` |\n| Find files by path/pattern | `find({ glob, pattern })` — returns paths + preview | `grep_search` / `ls` |\n| Find a symbol | `symbol({ name })` | `grep_search` |\n| Trace data flow | `trace({ items: [{start, direction}] })` | Manual code tracing |\n| Module relationships | `graph({action:\'neighbors\', node_id})` | Manual import tracing |\n| Typecheck + lint | `check({})` | `run_in_terminal tsc` / biome |\n| Run tests | `test_run({})` | `run_in_terminal vitest` |\n| Impact analysis | `blast_radius({ files })` — trace affected files from changes | Manual caller tracing |\n| Complexity metrics | `measure({ path })` | Line counting / wc |\n| Workspace skill + onboard context | `status({ includePrelude: true })`, `aikit://skill/SKILL.md` when full guidance is needed | Raw file discovery |\n| Known issues / recurring lessons | `search({ query: "known issues" })` + `knowledge({ action: "lesson" })` | Manual history review |\n| Web research | `web_search({ queries })` + `web_fetch({ urls })` | `fetch_webpage` |\n\n`read_file` is ONLY acceptable when you need exact line content FOR EDITING (before `replace_string_in_file`).\n\nEven then, use `file_summary` first to identify which lines to read.'}const d=r(`## AI Kit Tools`,"The AI Kit MCP server provides search, analysis, memory, validation, and coordination tools. Available tools vary by platform and version — run `list_tools` at session start to see the exact set on your platform. Tool names use short form (e.g. `search`, `file_summary`) in instructions; your runtime may prefix them (e.g. `mcp__aikit__search`).",``,"If AI Kit tools are unavailable or missing, run `npx -y @vpxa/aikit@latest init --user`, then reload the client."),f={"code-agent-base":`# Code Agent - Shared Kernel
 
 > Shared protocol for code-writing agents. Role files add only role-specific behavior.
 

package/scaffold/dist/definitions/skills/aikit.mjs

@@ -1,111 +1,4 @@
-var e=[{file:`SKILL.md`,content:`---
-name: aikit
-description: "Use the @vpxa/aikit AI Kit MCP server for codebase search, context compression, validation, and persistent memory. Load at session start or before using aikit_* tools. This skill teaches tool judgment: minimize raw reads, choose the smallest useful retrieval path, and persist decisions that matter."
-metadata:
-  category: cross-cutting
-  domain: general
-  applicability: always
-  inputs: [codebase]
-  outputs: [search-results, analysis, knowledge]
-  relatedSkills: [session-handoff, present]
----
-
-# @vpxa/aikit - AI Kit
-
-Use AI Kit as compression, memory, validation, and coordination layer. Each call should reduce uncertainty or token load.
-
-## Communicating With the User
-
-**Use \`present({ schemaVersion: 1, title, blocks })\` for ALL non-trivial output.** This is the preferred way to show summaries, results, evidence maps, task plans, reviews, comparisons, dashboards, charts, timelines, and batch results to the user. Plain text is only for 1-2 sentence status updates or simple questions. The \`present\` tool renders rich, structured output that the user can interact with.
-
-## Session Loop
-
-Start:
-1. status({ includePrelude: true }).
-2. If prelude.workspaceCore is null → run \`onboard({ path, mode: 'generate' })\`, then \`status({ includePrelude: true })\` again.
-3. **L0 session start**: Run \`status({ includePrelude: true })\` for compact workspace-core summary. Extract workspace shape, package map, tool surfaces, key entry points, constraints, and known pitfalls before broad retrieval. If L0 answers enough, skip \`scope_map\`/wide \`search\`. If a flow is active, workflow card loaded via flow context. ≤ 2,100 tokens.
-4. search({ query: "SESSION CHECKPOINT", origin: "curated" }).
-5. flow({ action: 'status' }) when active flow may exist — use L1 snapshot before broad retrieval.
-6. scope_map({ task }) only when L0 + checkpoint do not identify a narrow workset.
-
-During:
-- Prefer search/file_summary/digest/symbol/trace/graph over raw reads.
-- Use stash for temporary findings; knowledge for durable decisions.
-- Run blast_radius before shared/public edits.
-- Validate with check + relevant test_run.
-
-End:
-- reindex after structural changes.
-- produce_knowledge for durable project updates.
-- session_digest({ persist: true }).
-- knowledge remember session checkpoint with done/decisions/next/blockers.
-
-## Retrieval Ladder — Layered (L0-L3)
-
-> This table maps knowledge layers to tool needs. For the canonical quick-reference tool decision table, see \`aiKitToolPreference()\` in protocols.mjs.
-
-| Layer | Need | Tool |
-|-------|------|------|
-| **L0** | Session briefing (after onboard) | \`status({ includePrelude: true })\` (compact summary). Run \`onboard\` first if card missing. Consume before broad scans. |
-| **L0** | Architecture overview | \`architecture\` briefing card |
-| **L0** | Known issues | \`known-issues\` briefing card |
-| **L0** | Flow-specific context | \`workflow:<flow>\` briefing card |
-| **L1** | Active flow state | \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>' })\` |
-| **L2** | Prior decisions/conventions | \`search\` / \`knowledge\` |
-| **L2** | File structure | \`file_summary({ files, tier: 'T1' })\` |
-| **L2** | Exact relevant section | \`file_summary({ files, tier: 'T2' })\` |
-| **L2** | Many files | \`digest\` |
-| **L2** | Symbol defs/refs | \`symbol\` |
-| **L2** | Call/data flow | \`trace\` |
-| **L2** | Module/import relationships | \`graph\` |
-| **L2** | Impact | \`blast_radius\` |
-| **L2** | Type/lint/test | \`check\` / \`test_run\` |
-| **L3** | Evidence, provenance, conflict review | \`search\` with \`knowledge({ action: 'lesson' })\` — focused only |
-| **General** | Tool choice unknown | \`list_tools({ intent: "<task>" })\` (use intent param for planner-ranked results) or \`search({ query: "tool to <do X>" })\` |
-
-Raw read_file only for exact edit lines after compressed tools identify target.
-
-## Context Reuse
-
-Before rereading path/topic, search exact path/topic first. If response gives ctxc_..., reuse with file_summary({ ref }) or file_summary({ ref, query }). Use enrich: true on tools that support it after first pass.
-
-## Patterns
-
-- New area: search -> scope_map -> file_summary -> graph/trace -> stash.
-- Bug: search -> symbol -> trace -> file_summary -> test/check -> remember.
-- Refactor shared code: blast_radius -> checkpoint -> file_summary -> rename/codemod -> check -> test_run.
-- Web/API: web_search/web_fetch/http; browser only when JS/auth interaction needed. Browser snapshots now use ~200-400 tokens, making them practical for quick page state checks.
-
-## Memory Discipline
-
-Store only high-signal facts:
-- Decisions and rationale.
-- Conventions that constrain future work.
-- Non-obvious root causes and fixes.
-- Checkpoints and blockers.
-
-Review decayed/stale entries periodically with knowledge({ action: 'flagged' }). Use lesson actions for reusable engineering lessons; load lesson-learned after implementation/review work.
-
-## Flow + FORGE
-
-Flows guide multi-step work. Read active step before acting. FORGE handles tiering/evidence/gates; load references only when main skill is too thin.
-
-### Layered Knowledge Protocol
-- **L0** → Generated briefing cards: load \`workspace-core\` at session start via \`status({ includePrelude: true })\` (compact summary). Requires \`onboard()\` first — if card null, run \`onboard\` before session start. Consume L0 as the default workspace map before \`search\`, \`scope_map\`, \`digest\`, or repeated \`file_summary\`; add \`workflow:<flow>\` if flow active, or one task card if no flow. Use \`file_summary({ tier: 'T1' })\` for structure, or \`file_summary({ tier: 'T2', query })\` for content only after L0 narrows the workset. Token-bounded.
-- **L1** → Flow working context. Withdraw before dispatch; reuse before broad retrieval.
-- **L2** → Canonical curated knowledge. Retrieve on demand; never preload broadly.
-- **L3** → Evidence/auto-knowledge. Inspect only for provenance, conflict, or promotion assessment.
-
-Reference docs:
-- references/coordination.md - queue, lanes, stash, checkpoints, signaling.
-- references/forge-protocol.md - tiering, evidence, gates.
-- references/search-patterns.md - search, trace, graph, compression recipes.
-- references/layered-knowledge-protocol.md - L0-L3 operating policy and hot path.
-
-## Self-Dogfooding
-
-When developing AI Kit itself: regenerate scaffold output, run focused checks, rebuild, then reindex so future searches see new shape.
-`},{file:`references/coordination.md`,content:`# Coordination
+var e=[{file:`SKILL.md`,content:"---\nname: aikit\ndescription: \"Use the @vpxa/aikit AI Kit MCP server for codebase search, context compression, validation, and persistent memory. Load at session start or before using aikit_* tools. This skill teaches tool judgment: minimize raw reads, choose the smallest useful retrieval path, and persist decisions that matter.\"\nmetadata:\n  category: cross-cutting\n  domain: general\n  applicability: always\n  inputs: [codebase]\n  outputs: [search-results, analysis, knowledge]\n  relatedSkills: [session-handoff, present]\n---\n\n# @vpxa/aikit - AI Kit\n\nUse AI Kit as compression, memory, validation, and coordination layer. Each call should reduce uncertainty or token load.\n\n## Communicating With the User\n\n**Use `present({ schemaVersion: 1, title, blocks })` for ALL non-trivial output.** This is the preferred way to show summaries, results, evidence maps, task plans, reviews, comparisons, dashboards, charts, timelines, and batch results to the user. Plain text is only for 1-2 sentence status updates or simple questions. The `present` tool renders rich, structured output that the user can interact with.\n\n## Session Loop\n\nStart:\n1. status({ includePrelude: true }).\n2. If `onboarded` is false or `prelude.onboardContext` / `structuredContent.onboard_context` is null → run `onboard({ path, mode: 'generate' })`, then `status({ includePrelude: true })` again.\n3. If `onboard_context.freshness.status` is `stale` or `unknown`, or `nextAction.kind === \"update_onboard\"` → run `onboard({ path, update: true })`, then `status({ includePrelude: true })` again.\n4. **Workspace context start**: Extract workspace skill + fresh onboard context from status: `workspace_skill.uri`, `prelude.workspaceSkillResource`, `onboard_context.freshness`, `onboard_context.packageMap`, `onboard_context.architecture`, and `onboard_context.recommendedReadOrder`. Read `aikit://skill/SKILL.md` when full repo-specific guidance is needed. Use fresh onboard context before broad retrieval. ≤ 2,100 tokens.\n5. search({ query: \"SESSION CHECKPOINT\", origin: \"curated\" }).\n6. flow({ action: 'status' }) when active flow may exist — use L1 snapshot before broad retrieval.\n7. scope_map({ task }) only when workspace context + checkpoint do not identify a narrow workset.\n\nDuring:\n- Prefer search/file_summary/digest/symbol/trace/graph over raw reads.\n- Use stash for temporary findings; knowledge for durable decisions.\n- Run blast_radius before shared/public edits.\n- Validate with check + relevant test_run.\n\nEnd:\n- reindex after structural changes.\n- produce_knowledge for durable project updates.\n- session_digest({ persist: true }).\n- knowledge remember session checkpoint with done/decisions/next/blockers.\n\n## Retrieval Ladder — Layered (Workspace Context + L1-L3)\n\n> This table maps knowledge layers to tool needs. For the canonical quick-reference tool decision table, see `aiKitToolPreference()` in protocols.mjs.\n\n| Layer | Need | Tool |\n|-------|------|------|\n| **Workspace Context** | Workspace skill + fresh onboard context | `status({ includePrelude: true })`; read `aikit://skill/SKILL.md` only when full guidance is needed. Run `onboard({ path, mode: 'generate' })` if `onboard_context` is missing; run `onboard({ path, update: true })` if `onboard_context.freshness.status` is `stale` or `unknown`. Consume fresh context before broad scans. |\n| **Workspace Context** | Architecture overview | `status({ includePrelude: true }).onboard_context.architecture`, then onboard `diagram.md` / `domains.md` when deeper detail is needed |\n| **Workspace Context** | Package map / repo shape | `status({ includePrelude: true }).onboard_context.packageMap`, then onboard `structure.md` / `dependencies.md` |\n| **Flow Context** | Flow-specific context | L1 flow snapshot via `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>' })` |\n| **L1** | Active flow state | `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>' })` |\n| **L2** | Prior decisions/conventions | `search` / `knowledge` |\n| **L2** | File structure | `file_summary({ files, tier: 'T1' })` |\n| **L2** | Exact relevant section | `file_summary({ files, tier: 'T2' })` |\n| **L2** | Many files | `digest` |\n| **L2** | Symbol defs/refs | `symbol` |\n| **L2** | Call/data flow | `trace` |\n| **L2** | Module/import relationships | `graph` |\n| **L2** | Impact | `blast_radius` |\n| **L2** | Type/lint/test | `check` / `test_run` |\n| **L3** | Evidence, provenance, conflict review | `search` with `knowledge({ action: 'lesson' })` — focused only |\n| **General** | Tool choice unknown | `list_tools({ intent: \"<task>\" })` (use intent param for planner-ranked results) or `search({ query: \"tool to <do X>\" })` |\n\nRaw read_file only for exact edit lines after compressed tools identify target.\n\n## Context Reuse\n\nBefore rereading path/topic, search exact path/topic first. If response gives ctxc_..., reuse with file_summary({ ref }) or file_summary({ ref, query }). Use enrich: true on tools that support it after first pass.\n\n## Patterns\n\n- New area: search -> scope_map -> file_summary -> graph/trace -> stash.\n- Bug: search -> symbol -> trace -> file_summary -> test/check -> remember.\n- Refactor shared code: blast_radius -> checkpoint -> file_summary -> rename/codemod -> check -> test_run.\n- Web/API: web_search/web_fetch/http; browser only when JS/auth interaction needed. Browser snapshots now use ~200-400 tokens, making them practical for quick page state checks.\n\n## Memory Discipline\n\nStore only high-signal facts:\n- Decisions and rationale.\n- Conventions that constrain future work.\n- Non-obvious root causes and fixes.\n- Checkpoints and blockers.\n\nReview decayed/stale entries periodically with knowledge({ action: 'flagged' }). Use lesson actions for reusable engineering lessons; load lesson-learned after implementation/review work.\n\n## Flow + FORGE\n\nFlows guide multi-step work. Read active step before acting. FORGE handles tiering/evidence/gates; load references only when main skill is too thin.\n\n### Layered Knowledge Protocol\n- **Workspace Context** → Workspace skill + fresh onboard context: load via `status({ includePrelude: true })`. Requires `onboard()` first — if `onboard_context` is null, run `onboard`; if `onboard_context.freshness.status` is `stale` or `unknown`, run `onboard({ path, update: true })`. Consume the workspace skill preview/resource pointer and fresh onboard package map/architecture/read-order before `search`, `scope_map`, `digest`, or repeated `file_summary`. Use `file_summary({ tier: 'T1' })` for structure, or `file_summary({ tier: 'T2', query })` for content only after status/onboard context narrows the workset. Token-bounded.\n- **L1** → Flow working context. Withdraw before dispatch; reuse before broad retrieval.\n- **L2** → Canonical curated knowledge. Retrieve on demand; never preload broadly.\n- **L3** → Evidence/auto-knowledge. Inspect only for provenance, conflict, or promotion assessment.\n\nReference docs:\n- references/coordination.md - queue, lanes, stash, checkpoints, signaling.\n- references/forge-protocol.md - tiering, evidence, gates.\n- references/search-patterns.md - search, trace, graph, compression recipes.\n- references/layered-knowledge-protocol.md - workspace context + L1-L3 operating policy and hot path.\n\n## Self-Dogfooding\n\nWhen developing AI Kit itself: regenerate scaffold output, run focused checks, rebuild, then reindex so future searches see new shape.\n"},{file:`references/coordination.md`,content:`# Coordination
 
 Use coordination tools when work is parallel, long-running, or easy to repeat incorrectly.
 
@@ -200,53 +93,4 @@ file_summary (T1=structure, T2=content) or digest (multi-file synthesis). Read_f
 ## Rule of Thumb
 
 If you are about to read raw code, ask whether the answer is really about structure, relevance, flow, or relationships. AI Kit has a smaller tool for each of those.
-`},{file:`references/layered-knowledge-protocol.md`,content:`# Layered Knowledge Protocol
-
-AI Kit delivers knowledge through four layers:
-
-## L0 — Generated Briefing Cards
-
-Fast, compact task setup loaded at session start.
-
-- **Auto-injected**: \`workspace-core\` (800-1200 tokens) — available via \`status({ includePrelude: true })\` after \`onboard()\` generates the card. If null → run \`onboard({ path, mode: 'generate' })\` then retry status.
-- **If flow active**: Load \`workflow:<flow>\` (500-900 tokens) via flow start refs (replaces task card)
-- **If no flow**: Optionally load one task card via \`file_summary\`
-- **Budget**: ≤ 2,100 tokens total
-- **Storage**: Generated workspace cache (path from server config)
-- **Card families**: \`workspace-core\`, \`architecture\`, \`testing-release\`, \`known-issues\`, \`workflow:<flow>\`
-- Session-start budget: workspace-core (800-1200 tokens) + 1 additional card ≤ 2,100 tokens total
-- Generated cache, not canonical — rebuildable from L2 canonical sources
-
-## L1 — Flow Working Context
-
-Active run state and role-filtered dispatch context.
-
-- Withdraw via \`knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })\`
-- Use withdrawn refs before calling \`file_summary\`, \`scope_map\`, \`blast_radius\`, or \`search\`
-- Each step has a declared \`contextProfile\` (implementer, reviewer, researcher, documenter, debugger)
-
-## L2 — Canonical Curated Knowledge
-
-Durable workspace archive managed by CuratedKnowledgeManager.
-
-- Retrieve on demand via \`search()\` or \`knowledge({ action: 'read' })\`
-- Never preload broadly at session start when L1 refs are already supplied
-- Markdown is the canonical form; vector/FTS indexes are derived
-
-## L3 — Evidence Archive
-
-High-volume observations, proofs, failures, and runtime traces.
-
-- Never auto-injected into session or step context
-- Inspect only for provenance verification, conflict review, or promotion assessment
-- Auto-knowledge extractors write to L3; they cannot navigate flow state or promote
-
-## Retrieval Order
-
-1. L0 (loaded cards at session start)
-2. L1 (flow withdrawal when active)
-3. L2 (on-demand canonical knowledge)
-4. L3 (focused evidence retrieval only)
-
-No active flow → keep L1 absent; use L0 + on-demand L2; turn-local context only.
-`}];export{e as default};
+`},{file:`references/layered-knowledge-protocol.md`,content:"# Layered Knowledge Protocol\n\nAI Kit delivers knowledge through startup workspace context plus L1-L3:\n\n## Workspace Context — Workspace Skill + Onboard Context\n\nFast, compact task setup loaded at session start.\n\n- **Auto-injected/discoverable**: `status({ includePrelude: true })` returns workspace skill preview/resource pointer and `onboard_context` after `onboard()` generates artifacts. If `onboard_context` is null → run `onboard({ path, mode: 'generate' })` then retry status. If `onboard_context.freshness.status` is `stale` or `unknown` → run `onboard({ path, update: true })` then retry status.\n- **Full workspace skill**: Read `aikit://skill/SKILL.md` only when full conventions, commands, or lessons are needed.\n- **Onboard files**: Use `onboard_context.recommendedReadOrder` and paths for `synthesis-guide.md`, `structure.md`, `dependencies.md`, `diagram.md`, `domains.md`, `entry-points.md`, and `code-map.md`.\n- **If flow active**: Load L1 via `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>' })` and reuse supplied refs before broad retrieval.\n- **If no flow**: Optionally load one task card via `file_summary`\n- **Budget**: ≤ 2,100 tokens total\n- **Storage**: Workspace skill plus generated onboard artifacts under the status `onboardDir`\n- Generated workspace context, not canonical — rebuildable from L2 canonical sources and current repo analysis\n\n## L1 — Flow Working Context\n\nActive run state and role-filtered dispatch context.\n\n- Withdraw via `knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })`\n- Use withdrawn refs before calling `file_summary`, `scope_map`, `blast_radius`, or `search`\n- Each step has a declared `contextProfile` (implementer, reviewer, researcher, documenter, debugger)\n\n## L2 — Canonical Curated Knowledge\n\nDurable workspace archive managed by CuratedKnowledgeManager.\n\n- Retrieve on demand via `search()` or `knowledge({ action: 'read' })`\n- Never preload broadly at session start when L1 refs are already supplied\n- Markdown is the canonical form; vector/FTS indexes are derived\n\n## L3 — Evidence Archive\n\nHigh-volume observations, proofs, failures, and runtime traces.\n\n- Never auto-injected into session or step context\n- Inspect only for provenance verification, conflict review, or promotion assessment\n- Auto-knowledge extractors write to L3; they cannot navigate flow state or promote\n\n## Retrieval Order\n\n1. Workspace context (workspace skill + onboard context at session start)\n2. L1 (flow withdrawal when active)\n3. L2 (on-demand canonical knowledge)\n4. L3 (focused evidence retrieval only)\n\nNo active flow → keep L1 absent; use workspace context + on-demand L2; turn-local context only.\n"}];export{e as default};

package/scaffold/dist/definitions/skills/c4-architecture.mjs

@@ -141,15 +141,15 @@ Default: Context + Container. Add Component only for a complex container and a c
 2. Identify audience and decision the diagram supports.
 3. **Gather evidence with AI Kit - check onboard cache FIRST:**
    a. **Check onboard cache:**
-      - Run status({ includePrelude: true }) - if workspaceCore shows onboard data available:
-        - Read cache from ~/.aikit/workspaces/<hash>/onboard/:
+     - Run status({ includePrelude: true }) - if structuredContent.onboard_context is present and onboard_context.freshness.status == "fresh":
+        - Use onboard_context.recommendedReadOrder and read cache files from onboardDir:
           - structure.md - module tree, layers, directory shape
           - dependencies.md - internal/external dependency graph
+          - diagram.md / domains.md - architecture boundaries
           - symbols.md - exported symbols, type signatures
           - entry-points.md - API surface, CLI entry points
-        - Freshness: cache fresh if status().onboarded == true and index recent.
-          For finer control: compare git diff --stat pending change count.
-          Default: <50 pending changes -> serve from cache | >=50 -> refresh.
+        - Freshness: trust status().onboard_context.freshness.status, not timestamps inferred by the model.
+          If freshness is stale/unknown, run onboard({ path: ".", update: true }) and status again before using onboard files.
    b. **Use cache data for C4:**
       - Extract layers from structure analysis (layer-detector classifications)
       - Extract modules/containers from directory tree

package/scaffold/dist/definitions/skills/docs.mjs

@@ -155,8 +155,9 @@ Detailed workflow for acquiring and documenting project knowledge into \`docs/ar
 
 ### Phase 1: Scan and Read Intent (IR-aware)
 
-Pre-flight — load L0 + L1 context:
+Pre-flight — load workspace context + L1 context:
 - \`status({ includePrelude: true })\`
+- If \`onboard_context\` is missing, run \`onboard({ path: ".", mode: "generate" })\`; if \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, run \`onboard({ path: ".", update: true })\`; then status again.
 - \`knowledge({ action: 'withdraw', scope: 'flow', profile: 'documenter', budget: 6000 })\`
 
 Then check \`docs/.docs-state.json\` (the Committed Docs IR):
@@ -789,7 +790,7 @@ Use this template for any generated section that includes factual claims:
 
 ### Update Mode Template (\`docs/.docs-state.json\`)
 
-Committed state file for incremental documentation updates. L0 regeneratable cache,
+Committed state file for incremental documentation updates. Workspace-context regeneratable cache,
 committed to git so clones have warm cache.
 
 **Design: extends existing schema (backward compatible).** NO parallel \`_lastSynced\` block.
@@ -798,7 +799,7 @@ Adds \`signatureHash\`, \`contractHash\` (optional), and \`syncedAt\` to the exi
 \`\`\`json
 {
   "version": "1.1",
-  "layer": "l0",
+  "layer": "workspace-context",
   "timestamp": "ISO-8601",
   "lastCommitSha": "git rev-parse HEAD of last documented commit",
 
@@ -1732,7 +1733,7 @@ Orchestrate phased documentation generation with document-type-specific outputs
 
 Before executing the generation pipeline, load available context from across the infrastructure:
 
-- L0: \`status({ includePrelude: true })\` — workspace context (lessons, conventions)
+- Workspace context: \`status({ includePrelude: true })\` — workspace skill, onboard context, lessons, conventions
 - L1: \`knowledge({ action: 'withdraw', scope: 'flow', profile: 'documenter', budget: 6000 })\` — flow context
 - L2: \`search({ origin: 'curated' })\` + \`knowledge({ action: 'lesson', subAction: 'list-lessons' })\` — curated knowledge
 - L3: Evidence archive (provenance only, never auto-injected)
@@ -1741,8 +1742,9 @@ Before executing the generation pipeline, load available context from across the
 
 ### Phase 1 — Docs IR Producer (deterministic)
 
-Pre-flight: load L0 + L1 context from infrastructure.
-- \`status({ includePrelude: true })\` — L0 prelude
+Pre-flight: load workspace context + L1 context from infrastructure.
+- \`status({ includePrelude: true })\` — workspace skill + onboard context prelude
+- If \`onboard_context\` is missing, generate onboard. If \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, update onboard, then status again.
 - \`knowledge({ action: 'withdraw', scope: 'flow', profile: 'documenter', budget: 6000 })\` — L1 flow context
 
 Step 1: Check \`docs/.docs-state.json\` (the Committed Docs IR):
@@ -1810,7 +1812,7 @@ Step 2: Doc inventory (always runs, not cached):
 - \`blast_radius({ files: changedFiles })\` — stale doc detection
 
 The IR (\`docs/.docs-state.json\`) stores:
-- \`version\` + \`layer: "l0"\` (regeneratable cache, not curated; committed to git)
+- \`version\` + \`layer: "workspace-context"\` (regeneratable cache, not curated; committed to git)
 - \`lastCommitSha\` (committed = warm clones, no cold starts)
 - \`onboardRef\` (pointer to onboard cache, NO duplicated analysis data)
 - \`sourceFiles\` (per-file contentHash, signatureHash, contractHash, syncedAt, changeClass)
@@ -3304,7 +3306,7 @@ Each doc type uses specific tools. Load the tools before generating.
 Documentation is the bridge between AI Kit's layered knowledge and human readers.
 
 \`\`\`
-L0 (Briefing Cards) ─→ docs/ — Human-readable summaries of workspace state
+Workspace skill + onboard context ─→ docs/ — Human-readable summaries of workspace state
        │
 L1 (Flow Context) ───→ docs/architecture/flows/ — Flow design decisions → durable docs
        │                      │
@@ -3315,7 +3317,7 @@ L3 (Evidence Archive) ──→ docs/reference/ — Verified claims with tool re
 
 | Layer | Docs Role | Action |
 |---|---|---|
-| L0 | Regenerate via briefing-card-compiler when topics change | Card invalidation trigger |
+| Workspace context | Regenerate via onboard/status/skill compiler when topics change | Onboard + workspace skill freshness trigger |
 | L1 | Withdraw flow context, extract decisions/artifacts → docs/ | \`knowledge({action:'withdraw',scope:'flow'})\` |
 | L2 | Candidate for promotion from verified docs | Consolidation adjudication |
 | L3 | Evidence chain for every doc claim | \`knowledge({action:'lesson'})\` + receipts |
@@ -3439,7 +3441,7 @@ Report: "No documentation updates needed" + brief reason.
     - If \`syncedAt\` missing on doc → treat as stale (conservative), emit warning
     - If no recent lessons match → continue silently
     - Session dedup: maintain \`Set<string>\` of checked topic+entry IDs per session; skip if already checked
-2. **Load layered context**: \`status({ includePrelude: true })\` → L0. \`knowledge({ action: 'withdraw', scope: 'flow', profile: 'documenter', budget: 6000 })\` → L1.
+2. **Load layered context**: \`status({ includePrelude: true })\` → fresh workspace context (generate/update onboard first if missing/stale/unknown). \`knowledge({ action: 'withdraw', scope: 'flow', profile: 'documenter', budget: 6000 })\` → L1.
 3. Gather intent/evidence from flow artifacts, git diff, blast_radius, produce_knowledge, analyze, changelog, or search.
 4. Classify target docs with Diataxis or extended doc type table.
 5. Map changed capability to doc action.

package/scaffold/dist/definitions/skills/multi-agents-development.mjs

@@ -467,8 +467,8 @@ Every subagent prompt includes:
 2. Goal + acceptance criteria.
 3. Files/boundary + do-not-touch list.
 4. Compressed context: relevant snippets, conventions, decisions, active flow paths.
-5. **L0/L1 refs**: Include \`selectedCardRefs\`, \`retrievedRefs\`, and L1 \`FlowContextSnapshotV1\` fields relevant to the role.
-6. **Hard rule — no broad card reload**: Subagent must reuse supplied refs first. Must NOT independently reload \`workspace-core\`, architecture, testing-release, or known-issues cards when the dispatch already carries applicable refs.
+5. **Workspace/L1 refs**: Include supplied workspace skill/onboard context, \`retrievedRefs\`, and L1 \`FlowContextSnapshotV1\` fields relevant to the role.
+6. **Hard rule — no broad rediscovery**: Subagent must reuse supplied refs first. Must NOT independently rediscover workspace basics or reload architecture context when the dispatch already carries applicable refs.
 7. Constraints: skills to load, libraries/patterns, no present, no flow advance.
 8. FORGE: tier, task_id, evidence claims to add.
 9. Validation: expected check, test_run, or reason skipped.
@@ -480,10 +480,10 @@ Use references/implementer-prompt.md for implementation dispatches and reference
 
 Before dispatch:
 - knowledge({ action: 'withdraw', scope: 'flow', profile: '<role>', budget: 6000 })
-- Include \`selectedCardRefs\` (L0 card refs) and \`retrievedRefs\` (from L1) in the dispatch envelope.
+- Include supplied workspace/onboard context refs and \`retrievedRefs\` (from L1) in the dispatch envelope.
 - Add only missing snippets with file_summary/digest.
 - Paste context into dispatch; do not tell subagent to rediscover basics.
-- **Hard rule**: Subagent must reuse supplied L0/L1 refs before broad retrieval. Block if it reloads \`workspace-core\` or architecture cards independently.
+- **Hard rule**: Subagent must reuse supplied workspace/L1 refs before broad retrieval. Block if it independently rediscovers workspace basics already present in the dispatch.
 
 After subagent work:
 - Store durable findings with knowledge({ action: 'remember', scope: 'flow', ... }).

package/scaffold/dist/definitions/skills/orchestrator.mjs

@@ -27,14 +27,19 @@ YOU MUST FOLLOW THIS PROTOCOL ON EVERY TASK. You are an orchestrator, not an imp
 
 Execute these before ANY other work:
 1. \`flow({ action: 'status' })\` — Check active flow state.
-2. \`status({ includePrelude: true })\` — Load L0 workspace context plus workspace skill summary.
-3. If workspaceCore null → \`onboard({ path: "." })\` first, then status again.
-4. \`skill({ name: 'aikit' })\` — Load the AI Kit skill for tool routing, retrieval ladder, and communication patterns.
+2. \`status({ includePrelude: true })\` — Load workspace skill summary plus onboard context.
+3. If \`onboarded\` is false or \`onboard_context\` is null → \`onboard({ path: ".", mode: "generate" })\` first, then status again.
+4. If \`onboard_context.freshness.status\` is \`stale\` or \`unknown\`, or \`nextAction.kind === "update_onboard"\` → \`onboard({ path: ".", update: true })\` first, then status again.
+5. \`skill({ name: 'aikit' })\` — Load the AI Kit skill for tool routing, retrieval ladder, and communication patterns.
 
 On platforms without native \`skill()\` support, the AI Kit instructions are already in your system prompt via other channels.
 
 **Workspace skill:** \`status({ includePrelude: true })\` gives you the compact summary. For full content (conventions, commands, lessons): read \`aikit://skill/SKILL.md\` MCP resource on demand.
 
+## User-Facing Presentation
+
+Use \`present({ schemaVersion: 1, title, blocks })\` for almost every substantive response to the user. If the response is more than 3 sentences, contains a list/table/checklist/plan/status/verdict/summary/progress/evidence map, or asks for approval/choice, use \`present\`. Prefer \`present\` even without actions for read-only summaries; add \`actions\` for approvals, confirmations, and selections. Plain text only for tiny status updates or one simple question that fits in 3 short sentences.
+
 ## Delegation Rules
 
 **RULE 1 — Decompose everything.** Break every task into independent, parallelizable subtasks.