@massa-ai/claude-plugin 1.62.0 → 1.63.0

package/skills/massa-ai/workflows/architecture/architecture-fix.md

@@ -73,7 +73,7 @@ Not for findings-only architecture review — route to `workflows/architecture/a
    - Update tests, docs, and imports only where required by the architecture fix.
 10. Use agent orchestration only when it improves signal — except the verifier dispatch below, which is tier-gated mandatory rather than discretionary, carved out under `references/agent-orchestration.md`'s Independent Verification Exception. Dispatch per `references/agent-orchestration.md`:
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: large/high-risk finding, disjoint implementation slice, or explicit subagent request
 > - scope: one isolated architecture finding with a disjoint write set
 > - permissions: write (disjoint write set)
@@ -83,10 +83,10 @@ Not for findings-only architecture review — route to `workflows/architecture/a
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable architecture patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation of the architecture finding complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, ARCH acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, ARCH acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become architecture fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/bugs/bugs-fix.md

@@ -62,7 +62,7 @@ Not for findings-only bug discovery — route to `workflows/bugs/bugs-audit.md`.
    - Do not weaken tests, fixtures, snapshots, types, or public contracts to make the fix pass.
 9. Use agent orchestration only when it improves signal, except independent verification of the bug fix, which is mandated at the tiers named in `references/agent-orchestration.md`'s Independent Verification Exception. Dispatch per `references/agent-orchestration.md`:
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: large/high-risk finding, disjoint implementation slice, or explicit subagent request
 > - scope: one isolated bug finding with a disjoint write set
 > - permissions: write (disjoint write set)
@@ -72,10 +72,10 @@ Not for findings-only bug discovery — route to `workflows/bugs/bugs-audit.md`.
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable bug patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/code-quality/code-quality-fix.md

@@ -62,7 +62,7 @@ Not for findings-only SOLID, Clean Code, KISS, YAGNI, DRY, maintainability, or o
    - Prefer small reversible edits; verify after each finding or coherent group.
 10. Use agent orchestration only when it improves signal — except the `code-reviewer` `verify` dispatch below, which `references/agent-orchestration.md`'s Independent Verification Exception mandates at the tiers named in its trigger regardless of signal improvement. Dispatch per `references/agent-orchestration.md`:
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: large/high-risk finding, disjoint implementation slice, or explicit subagent request
 > - scope: one isolated code-quality finding or disjoint file group
 > - permissions: write (disjoint write set)
@@ -72,10 +72,10 @@ Not for findings-only SOLID, Clean Code, KISS, YAGNI, DRY, maintainability, or o
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable code-quality patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation of the CQ finding complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, CQ acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, CQ acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become CQ fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/debug.md

@@ -67,10 +67,10 @@ Before the first repository mutation, load `references/implementation-delivery.m
    - (a) write the test first, asserting the exact previously-broken behavior at the divergence point
    - (b) at Standard+, prove the coverage discriminates: run the sensor in `references/discrimination-sensor.md` against the just-fixed code; a surviving mutant means the regression test does not yet prove the fix
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/feature.md

@@ -61,17 +61,17 @@ Before the first repository mutation, load `references/implementation-delivery.m
 > - permissions: write, scoped to UI-layer files only with a disjoint write set
 > - output: per-element conformance table (element, expected, actual, verdict, severity) plus the UI files written; a missing or unreachable design source is listed as a skipped sensor, never a silent pass
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the feature's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps
 > - memory: suggest-only; main agent persists
 
 > **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `verify`) — charter `skills/agents/code-reviewer/SKILL.md`
-> - trigger: Standard tier or above per the Independent Verification Mandate in `references/verification-ladder.md` — mandatory once every implemented PR group has cleared `code-reviewer` review fix items; Quick tier substitutes the fallback below
+> - trigger: Standard tier or above per the Independent Verification Mandate in `references/verification-ladder.md` — mandatory once every implemented PR group has cleared diff-audit fix items; Quick tier substitutes the fallback below
 > - scope: the new code landed across this feature's PR groups from step 12, plus the tests and validation assets those groups touch
 > - inputs: the 1-5 acceptance criteria captured in step 11 (or the referenced spec artifact) as the outcome source, the feature's diff surface across all PR groups, and its test suite
 > - sensors: check the diff and tests against each acceptance criterion; discrimination sensor per `references/discrimination-sensor.md` (mutate the feature's new code, one PR group at a time — covering tests must kill each mutant or that group is not verified)

package/skills/massa-ai/workflows/implementation/implementation-fix.md

@@ -69,7 +69,7 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 > - permissions: write, scoped to UI-layer files only with a disjoint write set
 > - output: per-element conformance table (element, expected, actual, verdict, severity) plus the UI files written; a missing or unreachable design source is listed as a skipped sensor, never a silent pass
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: isolated finding with disjoint write set and concrete verification
 > - scope: one isolated implementation finding with a disjoint write set
 > - permissions: write (disjoint write set)
@@ -81,10 +81,10 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 
     Never run parallel writers against shared files or contracts.
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/mobile-figma/mobile-figma-fix.md

@@ -32,7 +32,7 @@ Do not execute from chat summaries, screenshots alone, remembered findings, or a
    - `references/audit-scope.md` and `references/codebase-investigation.md` for freshness and current source.
    - `references/verification-ladder.md` before edits.
    - `references/context-firewall.md` before large design/runtime artifacts.
-   - `references/agent-orchestration.md` for the designer/builder dispatches and the tier-gated `code-reviewer` `verify` dispatch in the fix loop below.
+   - `references/agent-orchestration.md` for the designer/senior-engineer dispatches and the tier-gated `code-reviewer` `verify` dispatch in the fix loop below.
    - `references/discrimination-sensor.md` before closing any finding under the Mandatory Verification Fix Gate — the mobile-Figma token/value instantiation lives in `references/mobile-figma-matcher/core.md`'s Discrimination Sensor for Visual Parity section.
    - `references/knowledge-verification-chain.md` when a selected finding's fix direction depends on platform-API or external-library technique rather than the Figma-defined value.
    - `references/brownfield-mapping.md` (Minimum Bar only — the gate-command packet, `TESTING.md`-equivalent) when recall returns no hit for the target surface/module and no gate command is derivable from the report's evidence, for Standard+ findings; the report's Verification/Test Fidelity Checklist already carries the risk surface, so `CONCERNS.md` is satisfied-by-citation from that checklist rather than derived fresh.
@@ -60,14 +60,14 @@ Do not execute from chat summaries, screenshots alone, remembered findings, or a
    - Modify tracked Maestro flows only when the selected finding explicitly identifies the flow as incorrect or missing and the user-approved scope includes that change.
 9. Dispatch per `references/agent-orchestration.md`; the `code-reviewer` `verify` block below is tier-gated mandatory, not merely discretionary — carved out of ordinary delegation gating by that reference's Independent Verification Exception:
 
-**Screen work — unconditional in this workflow:** every task here fixes a user-facing screen, so the `designer` dispatch below always runs; it is not gated on a screen-work condition (Screen Implementation Exception in `references/agent-orchestration.md`). `designer` implements every UI-layer `MFM-*` fix; `builder` is dispatched only for an `MFM-*` finding whose fix needs non-UI-layer changes (navigation, data, resource or build wiring), with a write set disjoint from the designer's.
+**Screen work — unconditional in this workflow:** every task here fixes a user-facing screen, so the `designer` dispatch below always runs; it is not gated on a screen-work condition (Screen Implementation Exception in `references/agent-orchestration.md`). `designer` implements every UI-layer `MFM-*` fix; `senior-engineer` is dispatched only for an `MFM-*` finding whose fix needs non-UI-layer changes (navigation, data, resource or build wiring), with a write set disjoint from the designer's.
 
 > **Dispatch: `designer`** (role: `designer`, mode: `implement`) — charter `skills/agents/designer/SKILL.md`
 > - scope: the screens, views, components, layouts, styles, and design tokens in this task's UI surface — never the whole repository
 > - permissions: write, scoped to UI-layer files only with a disjoint write set
 > - output: per-element conformance table (element, expected, actual, verdict, severity) plus the UI files written; a missing or unreachable design source is listed as a skipped sensor, never a silent pass
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: a selected `MFM-*` finding whose fix needs non-UI-layer changes (navigation, data, resource or build wiring) — never for a UI-layer fix, which belongs to `designer`
 > - scope: the non-UI-layer part of one `MFM-*` finding, or of a coherent surface group sharing one KMP root cause, with a write set disjoint from the designer's
 > - permissions: write (disjoint write set, non-UI-layer files only)
@@ -77,10 +77,10 @@ Do not execute from chat summaries, screenshots alone, remembered findings, or a
 > - firewall: raw diffs and screenshots summarized
 > - memory: suggest-only; main agent persists reusable token/mapping patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/pr-review.md

@@ -147,7 +147,7 @@ the severity labels, and the reply contract.
 | 3 | Architecture & conventions | `code-reviewer` | `lens: architecture` — extract every explicit rule from the profile's CONVENTIONS/REVIEW_SKILLS docs into a numbered matrix, grade each changed file PASS/VIOLATION/N/A; no docs ⇒ minimal generic boundary sweep, stated | `architecture` |
 | 4 | Performance | `code-reviewer` | `lens: performance` — only issues clearly visible in the diff: N+1 queries, unbounded fetches, per-row lazy I/O, sequential awaits of independent calls, loop-invariant recomputation, unbatched writes | `performance` |
 | 5 | Test coverage | `test-engineer` | `mode: audit` (dedicated tests lens: coverage, regression protection, assertion quality, variation — `tests-audit.md` precedent) — new/changed behavior with no test, wrong level (unit vs integration), placement/naming vs profile TEST row, missing negative case, missing variation beyond the fixture example, assertions that exercise but never assert | `tests` |
-| 6 | Regression & hallucination | `code-reviewer` | `mode: review` — diff review — unrelated deletions, references to symbols absent from the repo, wrong signature/arity, duplicated existing logic, weakened error handling or assertions, leftover TODO/stub, dead code | `regression` |
+| 6 | Regression & hallucination | `code-reviewer` | `mode: audit`, `lens: diff` — diff review — unrelated deletions, references to symbols absent from the repo, wrong signature/arity, duplicated existing logic, weakened error handling or assertions, leftover TODO/stub, dead code | `regression` |
 
 Consolidation check (≥ 5 subagents): recorded in the feature design — rows 4 and 5
 share only the lens label, not a knowledge domain; they stay separate dispatches.
@@ -181,10 +181,10 @@ share only the lens label, not a knowledge domain; they stay separate dispatches
 > - firewall: raw diff/log/search output summarized, never returned raw
 > - memory: suggest-only; the main agent persists durable outcomes
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: pr-review Step 2, dimension row 6 (regression & hallucination)
 > - scope: the full PR/MR diff against the repository's real symbol surface; no host CLI calls, no posting
-> - inputs: exact `projectId`, parent `workflowSessionId`, dimension row 6, DISCOVERY MAP, PR/MR intent, full diff, existing-comment inventory, severity labels, reply contract
+> - inputs: `lens: diff`; exact `projectId`, parent `workflowSessionId`, dimension row 6, DISCOVERY MAP, PR/MR intent, full diff, existing-comment inventory, severity labels, reply contract
 > - sensors: verify referenced symbols exist (`search_definitions`/`get_references` when INDEX is fresh, else grep); second-pass sweep as above
 > - output: structured reply block — findings rows tagged `{unrelated-deletion | phantom-reference | wrong-signature | duplicate | weakened-check | dead-code}` + one positive highlight + files-swept-clean list; withhold uncertain findings
 > - firewall: raw diff/log/search output summarized, never returned raw

package/skills/massa-ai/workflows/refactor.md

@@ -66,17 +66,17 @@ Before the first repository mutation, load `references/implementation-delivery.m
    - Refactored architectural decisions via `remember` as scored `decision` memories
    - Identified and decoupled anti-patterns via `remember` as scored `pattern` memories
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the change's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps
 > - memory: suggest-only; main agent persists
 
 > **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `verify`) — charter `skills/agents/code-reviewer/SKILL.md`
-> - trigger: Standard+ refactor sizing or any PR-group execution per the Independent Verification Mandate in `references/verification-ladder.md` — mandatory once `code-reviewer` review fix items are resolved; Quick-sized refactors dispatch only when validation assets were touched, otherwise run the fresh-eyes fallback below and record the skip reason
+> - trigger: Standard+ refactor sizing or any PR-group execution per the Independent Verification Mandate in `references/verification-ladder.md` — mandatory once diff-audit fix items are resolved; Quick-sized refactors dispatch only when validation assets were touched, otherwise run the fresh-eyes fallback below and record the skip reason
 > - scope: the moved/transformed code across this refactor's PR groups and the characterization tests that must protect it
 > - inputs: the characterization baseline from step 6 (and step 7 for mobile refactors), the diff of moved code per PR group, and the PR-group map from step 9
 > - sensors: confirm the characterization tests still pass against the moved code's preserved behavior; discrimination sensor per `references/discrimination-sensor.md` (mutate the moved code — never new code — in scratch, one PR group at a time; characterization tests must kill each mutant)

package/skills/massa-ai/workflows/requirements/requirements-fix.md

@@ -66,7 +66,7 @@ Not for findings-only requirements review — route to `workflows/requirements/r
    - If a finding exposes a product decision gap, stop and ask rather than inventing policy.
 10. Use agent orchestration only when it improves signal, with one carve-out: the `code-reviewer` `verify` dispatch below is mandatory at its tier gate rather than discretionary, per `references/agent-orchestration.md`'s Independent Verification Exception. Dispatch per `references/agent-orchestration.md`:
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: large/high-risk finding, disjoint implementation slice, or explicit subagent request
 > - scope: one isolated requirements finding with a disjoint write set
 > - permissions: write (disjoint write set)
@@ -76,10 +76,10 @@ Not for findings-only requirements review — route to `workflows/requirements/r
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable requirements patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/security/security-fix.md

@@ -68,7 +68,7 @@ Not for findings-only security review — route to `workflows/security/security-
    - Do not weaken existing security assertions to make tests pass.
 10. Use agent orchestration only when it improves signal — except the verifier dispatch below, which is unconditional for every SEC finding closed `fixed`, carved out under `references/agent-orchestration.md`'s Independent Verification Exception as the security-fix unconditional case (other fix families use the tier-gated one). Dispatch per `references/agent-orchestration.md`:
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: large/high-risk finding, disjoint implementation slice, or explicit subagent request
 > - scope: one isolated security finding with a disjoint write set
 > - permissions: write (disjoint write set)
@@ -78,10 +78,10 @@ Not for findings-only security review — route to `workflows/security/security-
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable security patterns
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/spec-driven.md

@@ -96,9 +96,19 @@ Quick artifacts live under `.specs/quick/NNN-slug/` with a `TASK.md` (one-line i
 3. Run `Specify` with `references/spec-driven/specify.md`.
    - Capture stable requirement IDs, testable acceptance criteria, edge cases, and explicit out-of-scope items.
    - Run `references/spec-driven/discuss.md` inside Specify when gray areas, implicit requirements, persistence/state, external calls, auth, payments, concurrency, or state transitions affect behavior.
+
+> **Dispatch: `product-manager`** (role: `product-manager`, mode: `audit`) — charter `skills/agents/product-manager/SKILL.md`
+> - trigger: every Specify run, once `spec.md` is drafted, before the Requirement Closure Gate
+> - scope: the drafted `spec.md`
+> - permissions: read-only
+> - inputs: `lens: requirements`; the drafted spec; recalled requirement decisions
+> - output: findings — ambiguity, gap, contradiction, implicit-requirement, and uncovered-scenario lists — that the main agent resolves with the user or records as an accepted assumption in the Requirement Closure Gate
+> - firewall: raw spec text summarized, not returned raw
+> - memory: suggest-only; main agent persists reusable requirements patterns
+
    - For Android, iOS, or KMP Compose Multiplatform UI work, run the optional design-source intake gate from `references/mobile-context.md` (Design-Source Intake Gate).
    - WHERE one or more Figma links or node IDs are supplied for this work (any platform), lazily load `references/figma-pre-analysis.md`, `references/figma-wiring.md`, and `references/design-implementation.md` before Design/Tasks close; mobile targets additionally keep the Design-Source Intake Gate above.
-   - Apply the Requirement Closure Gate: every open requirement question is resolved with the user or recorded as an accepted assumption before execution begins.
+   - Apply the Requirement Closure Gate: every open requirement question is resolved with the user or recorded as an accepted assumption before execution begins, incorporating the `product-manager` `audit` findings above.
 **Reuse Scan — before writing new implementation code:** run the mandatory reuse scan per `references/code-reuse-scan.md` (separate read-only subagents; the reuse map's use/extend/new decisions are consumed before new code is planned or written) — or record its inline-fallback reason, verbatim.
 
 4. Decide whether `Design` is required. If yes, run `references/spec-driven/design.md`, including its deterministic validation before presenting `design.md` for confirmation; if no, record why the skip is valid. When Design is skipped and a design concern appears later, stop and create `design.md` before continuing.
@@ -123,10 +133,10 @@ Quick artifacts live under `.specs/quick/NNN-slug/` with a `TASK.md` (one-line i
 > - permissions: write, scoped to UI-layer files only with a disjoint write set
 > - output: per-element conformance table (element, expected, actual, verdict, severity) plus the UI files written; a missing or unreachable design source is listed as a skipped sensor, never a silent pass
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the task's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps

package/skills/massa-ai/workflows/tests/tests-fix.md

@@ -68,10 +68,10 @@ Not for findings-only test coverage, assertion quality, fixture health, flakines
    - Do not delete coverage, snapshots, fixtures, or benchmarks unless the audit report explicitly calls them obsolete and behavior remains protected elsewhere.
    - Prefer production-code changes only when required to expose a deterministic seam or fix a real bug found while writing the audited test.
 
-> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — charter `skills/agents/code-reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: implementation complete, before the verification gate — never optional
 > - scope: the fix's diff surface and its task/AC context
-> - inputs: diff, acceptance context, recalled code-quality conventions
+> - inputs: `lens: diff`; diff, acceptance context, recalled code-quality conventions
 > - sensors: bugs, regressions, missing edge cases, smells introduced by the diff
 > - output: ranked findings, blocking vs advisory; blocking findings become fix items before verification runs
 > - firewall: summarized findings only, never raw diff dumps
@@ -111,7 +111,7 @@ Not for findings-only test coverage, assertion quality, fixture health, flakines
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable testing patterns
 
-> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `senior-engineer`** (role: `senior-engineer`) — charter `skills/agents/senior-engineer/SKILL.md`
 > - trigger: a selected TST finding whose fix needs a production seam for deterministic testing (step 7 Standard) — never for a test-file change, which belongs to `test-engineer`, and never for a production behavior change, which routes to `workflows/spec-driven.md`
 > - scope: the seam-only production change for one TST finding, with a write set disjoint from the `test-engineer` test files
 > - permissions: write (disjoint write set, production seam files only; no behavior change)

package/skills/profile/SKILL.md

@@ -1,39 +0,0 @@
----
-name: profile
-description: Switch the installed massa-ai agents to a registry model profile (e.g. "work", "cheap", "home") or report the currently active profile per host. Use when the user asks to change/switch the model profile, asks which models the agents currently use, or asks to preview a profile switch. Do NOT use for editing the model registry itself (a registry edit is a massa-ai repository change, not a runtime switch) and do NOT claim the new profile is active before the user restarts the host session.
-license: MIT
-metadata:
-  author: Luiz Massa
-  version: 1.0.0
----
-
-# Profile Switch Skill
-
-## Mission
-Drive the one massa-ai model-profile switch engine and relay its report — never a second implementation.
-
-## When To Use
-- The user asks to switch, change, or set the model profile (by name, e.g. "work", "cheap", "home", "balanced").
-- The user asks what profile is currently active, or which profiles are shipped.
-- The user asks to preview a switch without applying it.
-
-## How To Drive It
-There is exactly one switch implementation (`@massa-ai/shared`'s switch engine); every front — this skill, the MCP tools, and both `massa-ai-config` CLIs — calls the same engine and returns the same per-host report shape. Prefer whichever front is already available in the session:
-
-- **MCP tools** (preferred when the massa-ai MCP server is connected): call `profile_list` to report shipped profiles + per-host active profile + bundle version, and `profile_set` to switch (`{profile, host?, dryRun?}`).
-- **CLI fallback**: `massa-ai-config profile list` / `massa-ai-config profile show` / `massa-ai-config profile set <name> [--host <h>] [--dry-run]`.
-
-Default to a dry run first when the user has not explicitly asked to apply the switch immediately — `dryRun: true` (MCP) or `--dry-run` (CLI) previews the per-host plan and changes nothing.
-
-## Relaying The Result
-Always relay the per-host outcome and the restart notice verbatim in substance, not just "done":
-
-- Report each host as switched / skipped (with its reason) / unsupported (with its reason) / failed (with its reason). Cursor is always reported skipped — every tier resolves to inherit, so switching it is a no-op by design, not an error.
-- When at least one host switched (non-dry-run), state explicitly that a session restart of that host is required before the new models take effect — hosts load agent definitions at session start; there is no live in-session switch.
-- On a dry run, say so and that no files changed.
-- On a fully failed request (e.g. unknown profile name), relay the named error and the list of profiles the report says are actually available — never guess a profile name.
-
-## Restrictions
-- Never invent a profile name; only use names the engine's own report lists as shipped/available.
-- Never claim a profile switch is "live" before the affected host's session restarts.
-- Never edit the model-profile registry (`skills/model-profiles.json`) to satisfy a switch request — that is a build-time registry change owned by a different workflow, not a runtime switch.