ultra-builder-pro-cli 0.24.0 → 0.24.2

package/skills/ultra-doctor/SKILL.md

@@ -19,8 +19,8 @@ Call `ultra.doctor { repair: false }` and inspect:
 - projection jobs, sessions, leases, worktrees, and recovery journals;
 - installed plugin assets, MCP startup, and hook paths.
 
-An expected workflow pause, editable draft, failed semantic checkpoint, or awaiting
-owner decision is a warning, not corruption.
+An expected workflow pause, editable draft, semantic warning, or awaiting owner
+decision is not corruption.
 
 ## Repair
 

package/skills/ultra-init/references/brownfield-adoption.md

@@ -52,17 +52,20 @@ baseline is ready.
 Record every adoption gap with a stable id, evidence references, owner, blocking flag,
 and one category:
 
-- `baseline_blocker`: prevents trustworthy adoption;
+- `baseline_blocker`: the model should recommend against adoption until resolved or
+  the owner explicitly accepts the recorded risk;
 - `documentation_drift`: maintained prose conflicts with observed behavior;
 - `known_defect`: reproducible incorrect behavior;
 - `technical_debt`: accepted maintainability or quality cost;
 - `unknown`: evidence is insufficient;
 - `future_change`: desired behavior outside the current baseline.
 
-Use `open` for unresolved gaps, `accepted` for owner-accepted non-blocking debt,
+Use `open` for unresolved gaps, `accepted` for owner-accepted debt,
 `resolved` when evidence closes the gap, and `deferred` for explicitly postponed
-non-blocking work. Every open `baseline_blocker` remains blocking. Do not convert the
-ledger into hundreds of application tasks.
+work. Keep every open `baseline_blocker` visible as a semantic warning. It does not
+become a SQLite hard gate: the model explains the risk, recommends resolution, and may
+record owner-authorized adoption without erasing the gap. Do not convert the ledger
+into hundreds of application tasks.
 
 ## Record authority
 
@@ -88,9 +91,9 @@ worktree state, and material decisions to the owner. Use `ultra.record` with
 `accept_known_red` and `accept_dirty_worktree` only for the exact items the owner
 accepted.
 
-Resolve returned blockers through evidence or an owner decision, record the replacement
-snapshot, and retry. Adoption is complete only when `ultra.context` reports a current
-accepted baseline, the gap ledger has no open blocker, and project doctor has no
-authority failure. Route all selected work through `ultra-change`, including work
-described by a legacy plan. Import its accepted intent into a current Change Contract
-before planning.
+Resolve hard authority blockers, then present semantic warnings for evidence or an
+owner decision. Adoption is complete when `ultra.context` reports a current accepted
+baseline, every material open gap is visible with its owner/risk and any acceptance is
+explicit in the approval note, and project doctor has no mechanical authority failure.
+Route all selected work through `ultra-change`, including work described by a legacy
+plan. Import its accepted intent into a current Change Contract before planning.

package/skills/ultra-plan/SKILL.md

@@ -48,14 +48,16 @@ payload: planning posture, optional approval already obtained, context budget/re
 idempotency_key: stable semantic Plan checkpoint id
 ```
 
-The checkpoint compiles or reuses the content-addressed Context Envelope, derives
-coverage diagnostics, exports `plan.json` and `plan.md` inside the same recoverable
-publication, accepts one Plan revision, and publishes the team checkpoint. Do not
-export separately.
-
-If rejected, the same Plan draft stays mutable. Fix task contracts or evidence and
-retry. To replace an accepted Plan, submit a new checkpoint revision; never edit
-SQLite or open a parallel run to escape a diagnostic.
+The model decides whether decomposition, acceptance coverage, and context are
+sufficient and records any deliberate omission. The checkpoint compiles or reuses the
+content-addressed Context Envelope, reports advisory coverage diagnostics, exports
+`plan.json` and `plan.md` inside the same recoverable publication, accepts one Plan
+revision, and publishes the team checkpoint. Do not export separately.
+
+If rejected, the same Plan draft stays mutable. Fix only the reported structural,
+digest, path, or concurrency conflict and retry. To replace an accepted Plan, submit a
+new checkpoint revision; never edit SQLite or open a parallel run to escape a
+diagnostic.
 
 Return topology, executable slices, public seams, exact checks, checkpoint result, and
 the model's recommended execution order. Do not invoke `ultra-dev` automatically.

package/skills/ultra-research/SKILL.md

@@ -41,8 +41,9 @@ Use one `ultra.record` batch for typed durable facts:
 - `baseline / observe` or `baseline / accept` for baseline authority;
 - `change_contract / revise` for Change-bound findings.
 
-Every entry needs a stable idempotency key. A semantic rejection is a mutable
-diagnostic: correct the same draft and retry.
+Every entry needs a stable idempotency key. Structural or authority conflicts require
+repair; semantic warnings remain visible but do not decide whether the research is
+sufficient.
 
 ## Commit one research checkpoint
 
@@ -56,8 +57,11 @@ entries, then publish the team checkpoint with `ultra.sync { action: publish }`.
 For Change-bound research, keep all findings and delta artifacts below the Change
 root and never edit accepted baseline specs directly.
 
-If the checkpoint returns `accepted: false`, keep the same draft mutable, repair the
-reported evidence, and retry. Do not manufacture evidence or open a replacement run.
+The model decides whether the selected coverage and synthesis are sufficient, and
+states omissions or deferred areas in the payload. MCP validates declared evidence
+bytes and records that conclusion; its semantic diagnostics are advisory. If it
+returns `accepted: false`, repair the reported structural, digest, path, or concurrency
+conflict and retry the same draft.
 
 Return coverage, decisive evidence, remaining gaps, durable artifact paths, and a
 model recommendation for the next explicit capability, such as `ultra-change` after a

package/skills/ultra-review/SKILL.md

@@ -34,11 +34,13 @@ Register specialist and summary artifacts through one `ultra.record` batch using
 ## Checkpoint
 
 Call `ultra.checkpoint` once with `stage: review`, exact scope, evidence, and outputs
-tagged `spec_review`, `engineering_review`, or summary. The checkpoint compiles or
-reuses review context and derives both axes from registered artifacts.
+tagged `spec_review`, `engineering_review`, or summary. The model and bounded review
+agents own both evidence-derived axes. The checkpoint compiles or reuses review
+context, verifies declared artifact bytes and digests, and records the supplied axes
+without overriding findings.
 
-A rejected checkpoint leaves the draft mutable. Fix stale scope or evidence and retry;
-do not open a replacement run or suppress a finding.
+A rejected checkpoint leaves the draft mutable. Fix the structural, digest, path, or
+concurrency fault and retry; do not open a replacement run or suppress a finding.
 
 Return both axes, findings, reviewed scope, worker rationale, digests, and the model's
 recommended next explicit capability. Do not invoke it automatically.

package/skills/ultra-test/SKILL.md

@@ -30,11 +30,13 @@ profile, timestamp, blockers, and evidence-derived verdict. Register it with
 ## Checkpoint
 
 Call `ultra.checkpoint` once with `stage: test`, exact scope, evidence, and an output
-for the report (`kind: test-report`). The checkpoint compiles or reuses checking
-context and derives the verdict from the registered report.
+for the report (`kind: test-report`). The model owns the evidence-derived verdict and
+material exclusions. The checkpoint compiles or reuses checking context, verifies the
+declared report authority and digest, and records that verdict without re-judging it.
 
-If rejected, keep the same draft, repair evidence, and retry. Never weaken an
-assertion, hide a skip, or turn a warning into proof.
+If rejected, keep the same draft and repair the structural, digest, path, or
+concurrency fault. Never weaken an assertion, hide a skip, or turn a warning into
+proof.
 
 Return the profile, exact results, verified seams, blockers, report digest, and the
 model's recommended next explicit capability. Do not invoke it automatically.

package/skills/ultra-think/SKILL.md

@@ -30,8 +30,9 @@ Use one `ultra.record` batch with `decision / accept` and, when required,
 `supersedes_id`; accepted records remain immutable history. Store normalized decisions
 and artifact references, never transcripts or internal reasoning.
 
-A semantic rejection remains a mutable diagnostic. Correct the record; do not invent a
-new decision merely to satisfy a state machine.
+A structural or authority rejection remains a mutable diagnostic. Correct the record;
+do not invent a new decision merely to satisfy a state machine. Semantic disagreement
+belongs in the recommendation and visible decision record, not a kernel error.
 
 Return the conclusion, decisive evidence, uncertainty, affected authority, and the
 model's recommended next explicit capability. Thinking never performs unrelated

package/spec/mcp-tools.yaml

@@ -100,7 +100,7 @@ tools:
 
   - name: ultra.checkpoint
     family: ultra
-    description: Attempt one semantic stage checkpoint. Failed semantic checks return blockers and leave the draft mutable; accepted checkpoints commit durable authority once.
+    description: Commit one caller-declared stage checkpoint after validating scope, structure, idempotency, current file bytes, digests, and transactional publication. Semantic completeness remains a Skill/model judgment and is returned only as advisory diagnostics.
     phase: '24'
     writer_role: mcp
     input_schema:
@@ -122,6 +122,10 @@ tools:
       - { code: VALIDATION_ERROR, description: 'input failed structural validation' }
       - { code: STATE_CORRUPT, description: 'local authority cannot be checkpointed safely' }
       - { code: PATH_AUTHORITY_VIOLATION, description: 'checkpoint evidence escapes managed authority' }
+      - { code: CHECKPOINT_EVIDENCE_AUTHORITY_MISSING, description: 'declared checkpoint evidence is not current managed authority' }
+      - { code: CHECKPOINT_EVIDENCE_DIGEST_MISMATCH, description: 'declared checkpoint evidence bytes changed' }
+      - { code: CHECKPOINT_SCOPE_NOT_FOUND, description: 'the explicit Task or Change scope does not exist' }
+      - { code: CHECKPOINT_SCOPE_MISMATCH, description: 'the explicit Task does not belong to the supplied Change scope' }
     cli_subcommand: 'ultra checkpoint'
     emits_events: [ultra_checkpoint_accepted, ultra_checkpoint_rejected]
 
@@ -168,7 +172,7 @@ tools:
 
   - name: ultra.archive
     family: ultra
-    description: Converge and archive one accepted Change through the recoverable filesystem and database transaction boundary.
+    description: Archive one caller-declared local Change handoff through a recoverable filesystem and database transaction. The kernel validates authority, paths, digests, reconciliation structure, and recovery safety without requiring a fixed semantic stage sequence.
     phase: '24'
     writer_role: mcp
     input_schema: