@massa-ai/codex-plugin 1.60.1 → 1.62.0

package/skills/massa-ai/workflows/{rfc.md → create-rfc.md}

@@ -1,5 +1,5 @@
 ---
-name: rfc
+name: create-rfc
 description: "Use this workflow when a significant technical, process, product, vendor, tool, or policy decision is still open and stakeholders need a structured proposal before committing."
 license: MIT
 metadata:
@@ -8,16 +8,16 @@ metadata:
 
 ### RFC (Request for Comments)
 
-Use when a significant technical, process, product, vendor, tool, or policy decision is still open and stakeholders need a structured proposal before committing to a direction. Route a finalized architecture decision to `workflows/adr.md`, settled implementation design to `workflows/tdd.md`, and broad requirements-through-delivery work to `workflows/spec-driven.md`.
+Use when a significant technical, process, product, vendor, tool, or policy decision is still open and stakeholders need a structured proposal before committing to a direction. Route a finalized architecture decision to `workflows/create-adr.md`, settled implementation design to `workflows/create-tdd.md`, and broad requirements-through-delivery work to `workflows/spec-driven.md`.
 
 Load `references/project-context.md` (intake sweep) before the first substantive read.
 
 ## Workflow
 
-1. Resolve or reuse `projectId` and `workflowSessionId=rfc-[entity]`.
+1. Resolve or reuse `projectId` and `workflowSessionId=create-rfc-[entity]`.
 2. Establish evidence before asking questions:
    - `recall` relevant constraints, existing architecture or process, related proposals, prior attempts, rejected options, stakeholder expectations, and verification patterns.
-   - Load `references/rfc/discovery-and-sizing.md`.
+   - Load `references/create-rfc/discovery-and-sizing.md`.
    - Inspect current source, project instructions, existing RFC conventions, decision records, tickets, and supplied research. Current source and approved project artifacts override stale memory.
    - When supplied Figma links, nodes, desktop selections, or screenshots materially affect mobile UI options, use `workflows/design.md` as optional child context for visual feasibility only; the RFC still owns option comparison and recommendation. Screenshots are context-only unless paired with structured Figma evidence.
    - Load `references/synapse-policy.md` when two or more related searches are expected and `references/context-firewall.md` before broad or verbose source inspection.
@@ -27,7 +27,7 @@ Load `references/project-context.md` (intake sweep) before the first substantive
    - Ask concise conversational questions when `AskQuestion` is unavailable.
    - Require title, background, full RACI roles, impact, urgency or due date, assumptions with confidence and invalidation triggers, weighted decision criteria, at least two options, and a recommendation.
    - Reuse supplied or discoverable facts; do not ask for information already present.
-5. Load `references/rfc/document-contract.md` and draft the RFC in the same language as the user's request.
+5. Load `references/create-rfc/document-contract.md` and draft the RFC in the same language as the user's request.
    - Preserve the 7 mandatory and 4 recommended sections, numeric criterion weights, honest option comparison, generated cost and effort estimates, status quo consideration, action items, and outcome placeholder.
    - Tailor conditional concerns to technical/architecture, process/workflow, product/feature, vendor/tool, or policy/compliance proposals.
    - Mark generated estimates as estimates and state their assumptions when exact project data is unavailable.
@@ -35,7 +35,7 @@ Load `references/project-context.md` (intake sweep) before the first substantive
    - If the target exists, update it only when the user explicitly requested an update; otherwise ask before overwriting.
    - When file mutation is unavailable or the user requested plan-only output, present the complete draft and intended path without writing.
 7. Run the full configured Plan Challenge Gate. Preserve all required RFC fields while revising valid critical or high findings, especially one-sided options, unsupported claims, hidden assumptions, status quo bias, weak cost estimates, and criteria chosen to justify a predetermined conclusion.
-8. Load `references/rfc/quality-and-lifecycle.md`, validate every required behavior, and resolve blocking gaps. Keep unresolved facts explicit instead of silently removing mandatory fields.
+8. Load `references/create-rfc/quality-and-lifecycle.md`, validate every required behavior, and resolve blocking gaps. Keep unresolved facts explicit instead of silently removing mandatory fields.
 9. Save the proposal with status `NOT STARTED` or `IN PROGRESS`. Set `COMPLETE` and fill the Outcome section only when an explicit human decision or authoritative project record is available.
 10. Persist proposal state after recall, deduplication, and scoring:
    - Pending or in-review proposal: scored `conversation` memory with `memory:working`.

package/skills/massa-ai/workflows/{tdd.md → create-tdd.md}

@@ -1,5 +1,5 @@
 ---
-name: tdd
+name: create-tdd
 description: "Use this workflow to write a Technical Design Document once one product direction is selected and no unresolved API, data, security, or rollout decision blocks implementation."
 license: MIT
 metadata:
@@ -8,25 +8,25 @@ metadata:
 
 ### TDD (Technical Design Document)
 
-Use when the readiness checklist is true: one product direction is selected, a named requirements source exists, and no unresolved API, data, security/privacy, migration, rollout, or public compatibility decision blocks implementation design. Route unresolved proposals or competing directions to `workflows/rfc.md`, isolated finalized architecture decisions to `workflows/adr.md`, and broad requirements-to-delivery work to `workflows/spec-driven.md`.
+Use when the readiness checklist is true: one product direction is selected, a named requirements source exists, and no unresolved API, data, security/privacy, migration, rollout, or public compatibility decision blocks implementation design. Route unresolved proposals or competing directions to `workflows/create-rfc.md`, isolated finalized architecture decisions to `workflows/create-adr.md`, and broad requirements-to-delivery work to `workflows/spec-driven.md`.
 
 Load `references/project-context.md` (intake sweep) before the first substantive read.
 
 ## Workflow
 
-1. Resolve or reuse `projectId` and `workflowSessionId=tdd-[entity]`.
+1. Resolve or reuse `projectId` and `workflowSessionId=create-tdd-[entity]`.
 2. Establish evidence before asking questions:
    - `recall` approved RFCs, ADRs, prior TDD decisions, constraints, rejected approaches, and verification patterns.
-   - Load `references/tdd/discovery-and-sizing.md`.
+   - Load `references/create-tdd/discovery-and-sizing.md`.
    - Inspect current source, tests, source sets, project instructions, architecture documents, and existing design artifacts. Current source and approved project artifacts override stale memory.
    - For testing plans, find whether each planned test file already exists and which source set owns it before choosing a location such as `commonTest`, `androidUnitTest`, `unitTest`, or the repository's actual equivalent.
    - For UI/UX-affecting method, class, enum, sealed type, mapper, or state changes, enumerate parallel rendering surfaces and mappers that consume the affected symbol.
    - When supplied Figma links, nodes, desktop selections, or screenshots materially affect supported Android, iOS, or KMP Compose Multiplatform UI design, use `workflows/design.md` as optional child context and keep this TDD as the owner of architecture, contracts, rollout, and verification strategy. Screenshots are context-only unless paired with structured Figma evidence.
    - Run a pre-TDD `Strings Audit` when mappers branch on a type and call `stringResource`; record affected string keys/resources, branches, fallback behavior, and surfaces before proposing string changes.
    - Load `references/synapse-policy.md` when two or more related searches are expected and `references/context-firewall.md` before broad or verbose source inspection.
-3. Confirm workflow fit with the readiness checklist in `references/tdd/discovery-and-sizing.md` and classify the document as Compact, Standard, or High-Risk from the exact sizing rules there. Do not size by guessed calendar duration.
-   - Record a `project_type` intake tag from this taxonomy: `integration`, `feature`, `refactor`, `infrastructure`, `payment`, `auth`, `data`. The `project_type` selects which conditional concerns in `references/tdd/document-contract.md` apply and which calibrated reference values from `references/tdd/calibrated-examples.md` are relevant; it does not mandate section counts or a fixed document shape.
-   - Apply the critical-section MANDATORY trigger mapping below. These are workflow-level selectors that point at the Conditional Concerns table in `references/tdd/document-contract.md`; they do not duplicate that table. When a trigger fires, the matching concerns are mandatory, not optional:
+3. Confirm workflow fit with the readiness checklist in `references/create-tdd/discovery-and-sizing.md` and classify the document as Compact, Standard, or High-Risk from the exact sizing rules there. Do not size by guessed calendar duration.
+   - Record a `project_type` intake tag from this taxonomy: `integration`, `feature`, `refactor`, `infrastructure`, `payment`, `auth`, `data`. The `project_type` selects which conditional concerns in `references/create-tdd/document-contract.md` apply and which calibrated reference values from `references/create-tdd/calibrated-examples.md` are relevant; it does not mandate section counts or a fixed document shape.
+   - Apply the critical-section MANDATORY trigger mapping below. These are workflow-level selectors that point at the Conditional Concerns table in `references/create-tdd/document-contract.md`; they do not duplicate that table. When a trigger fires, the matching concerns are mandatory, not optional:
      - `payment`, `auth`, PII, or regulated data → Security is mandatory.
      - production or customer-facing rollout → Monitoring and Rollback are mandatory.
      - external or cross-service integration → Dependencies and Security are mandatory.
@@ -35,7 +35,7 @@ Load `references/project-context.md` (intake sweep) before the first substantive
    - Group related questions naturally, in the user's language — no numeric cap; ask as many as the open decisions require.
    - Distinguish verified facts, evidence-backed inferences, proposed decisions, and unresolved questions.
    - Never invent owners, links, APIs, schemas, vendors, dates, thresholds, estimates, approvals, or project facts to complete a template.
-5. Load `references/tdd/document-contract.md`, plus `references/naming-standards.md` when the design names proposed components, modules, states, events, schemas, or fields, and draft the smallest decision-complete TDD for the selected depth.
+5. Load `references/create-tdd/document-contract.md`, plus `references/naming-standards.md` when the design names proposed components, modules, states, events, schemas, or fields, and draft the smallest decision-complete TDD for the selected depth.
    - Write in the user's language while preserving established project terminology and technical identifiers.
    - Focus on architecture, ownership boundaries, stable interfaces, data flow, failure behavior, and implementation strategy.
    - Include implementation detail when it defines a contract or removes material ambiguity; exclude production implementation code and incidental framework syntax.
@@ -49,12 +49,12 @@ Load `references/project-context.md` (intake sweep) before the first substantive
    - If the target exists, treat the request as an update only when the user explicitly requested one; otherwise ask before overwriting it.
    - When file mutation is unavailable or the user requested plan-only output, present the complete draft and intended path without writing.
 7. Run the configured Plan Challenge Gate. TDD plans require the full gate under the default policy; revise valid critical or high findings before finalization.
-8. Load `references/tdd/quality-and-lifecycle.md`, validate the document, and resolve blocking gaps. Keep non-blocking unknowns explicit with owners or decision points when known.
+8. Load `references/create-tdd/quality-and-lifecycle.md`, validate the document, and resolve blocking gaps. Keep non-blocking unknowns explicit with owners or decision points when known.
 9. If the implementation task table is stable and validated, discover whether Atlassian MCP has readable Jira project metadata and issue-creation capability.
    - If Atlassian MCP is unavailable or read-only, leave the table's `Jira Key` values as `Unavailable` and report that ticket creation was skipped.
    - If Atlassian MCP is available, ask whether the user wants to create Jira tickets now. If declined, set `Jira Key` to `Not requested`.
-   - If the user accepts, invoke `workflows/ticket.md`; Jira creation remains owned solely by the ticket workflow. Create one standard Jira issue per PR group. Create row-level sub-tasks only when the selected ticket hierarchy requires them.
-   - Update `Jira Key` only with confirmed Jira keys returned by the ticket workflow. Use `Pending` for approved-but-uncreated PR groups and never fabricate keys.
+   - If the user accepts, invoke `workflows/create-ticket.md`; Jira creation remains owned solely by the `create-ticket` workflow. Create one standard Jira issue per PR group. Create row-level sub-tasks only when the selected ticket hierarchy requires them.
+   - Update `Jira Key` only with confirmed Jira keys returned by the create-ticket workflow. Use `Pending` for approved-but-uncreated PR groups and never fabricate keys.
 10. Save the document as `Draft` or `In Review`. Never mark it `Approved`, invent sign-off, or begin downstream implementation without the required human decision.
 11. Persist only durable architecture constraints, accepted trade-offs, rejected approaches, compatibility requirements, and verification recipes through `remember` after recall, deduplication, and scoring. Use `decision` with `memory:semantic` for the architectural blueprint.
 12. Complete `references/evidence-gate.md` and report the artifact path, included conditional sections, unresolved questions, Jira creation outcome, memory outcome, and residual risk.

package/skills/massa-ai/workflows/{ticket.md → create-ticket.md}

@@ -1,5 +1,5 @@
 ---
-name: ticket
+name: create-ticket
 description: "Use this workflow to draft, review, create, or resume creation of Jira Epics, issues, or sub-tasks through Atlassian MCP, the only tracker and mutation path."
 license: MIT
 metadata:
@@ -14,12 +14,12 @@ Load `references/project-context.md` (intake sweep) before the first substantive
 
 ## Workflow
 
-1. Resolve or reuse `projectId` and `workflowSessionId=ticket-<entity>`.
+1. Resolve or reuse `projectId` and `workflowSessionId=create-ticket-<entity>`.
 2. Recall durable project conventions, prior Jira constraints, and ticket-writing decisions through `recall`. Treat recalled facts as leads until confirmed by the user or current Jira metadata.
 3. Load the focused contracts:
-   - `references/ticket/intake-and-sources.md` for ordered questions, reference-ticket isolation, DoR/DoD inputs, and bounded code exploration.
-   - `references/ticket/templates-and-quality.md` for title prefixes, built-in templates, decomposition, and draft validation.
-   - `references/ticket/atlassian-fix.md` before tool discovery, preflight, approval, Jira creation, resume, or cleanup.
+   - `references/create-ticket/intake-and-sources.md` for ordered questions, reference-ticket isolation, DoR/DoD inputs, and bounded code exploration.
+   - `references/create-ticket/templates-and-quality.md` for title prefixes, built-in templates, decomposition, and draft validation.
+   - `references/create-ticket/atlassian-fix.md` before tool discovery, preflight, approval, Jira creation, resume, or cleanup.
    - `references/context-firewall.md` when Jira, Confluence, supplied files, or exploration output could flood context.
 4. Discover Atlassian MCP capabilities dynamically. Require readable Jira project metadata and issue-creation capability before promising creation. If Atlassian MCP is missing or read-only, drafting may continue, but stop before approval-to-create and report the unavailable capability. Never substitute a CLI or tracker.
 5. Run ordered intake from `intake-and-sources.md`. Ask only for information not already supplied or discoverable from Atlassian metadata. Validate the exact project key without silently correcting it.

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

@@ -67,17 +67,16 @@ 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: `massa-ai-reviewer`** (role: `reviewer`) — charter `skills/agents/reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — 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
-> - permissions: read-only
 > - inputs: 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: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `verify`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: mandatory at Standard+/Spec-driven fix size, per the Independent Verification Mandate tier gate in `references/verification-ladder.md`; a Quick-tier fix takes the fallback below instead
 > - scope: the fixed divergence point from step 13, its reproduction path, and the regression test added in step 14
 > - inputs: the root cause, the reproduction evidence, the regression test, and the changed files — not spec acceptance criteria
@@ -116,7 +115,7 @@ Before the first repository mutation, load `references/implementation-delivery.m
 
 - `.specs/debug/<slug>/` unwritable at Standard+: block the `REPORT.md` write and record the blocker; never substitute a memory write or chat summary for the canonical debug artifact.
 - Fix → re-verify loop reaches the `references/verification-ladder.md` cap: stop the session `Blocked`, preserve the collected reproduction and verification evidence, and ask the user for direction.
-- Discrimination sensor mutation on the fixed divergence point is not safely reversible: mark `Blocked` unless the verification-agent can show equivalent discrimination from an existing deterministic mutation fixture.
+- Discrimination sensor mutation on the fixed divergence point is not safely reversible: mark `Blocked` unless the `code-reviewer` verifier can show equivalent discrimination from an existing deterministic mutation fixture.
 
 ## Example
 
@@ -129,4 +128,4 @@ User asks: "The login route returns 500 after deploy."
 5. Trace request → auth middleware → session lookup → response, then fix the divergence point closest to the root cause.
 6. Define the verification recipe: rerun the original route check, add or update regression coverage at the failing seam, and confirm validation assets were not weakened.
 7. If root cause is a missing `DATABASE_URL`, persist via `remember`: a semantic decision memory for the root cause and a procedural pattern memory for the deploy-env verification command.
-8. At Standard+ size, dispatch `massa-ai-verification-agent` to independently re-run the reproduction against the `DATABASE_URL` fix and confirm the regression test kills a mutant on the restored connection check before closing.
+8. At Standard+ size, dispatch `code-reviewer` in `verify` mode to independently re-run the reproduction against the `DATABASE_URL` fix and confirm the regression test kills a mutant on the restored connection check before closing.

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

@@ -28,9 +28,9 @@ Not for Flutter, React Native, web UI, generic Figma exploration, variable-only
 6. Persist only durable token/component mappings, approved deviations, source-set ownership rules, asset-pipeline rules, or reusable render recipes after Importance Calibration. Use `workflow:design` and required project/session/entity/memory tags.
 7. Complete `references/evidence-gate.md`. Model visual judgment alone cannot satisfy completion.
 
-**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `massa-ai-designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
+**Screen work — unconditional in this workflow:** every task here implements 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`).
 
-> **Dispatch: `massa-ai-designer`** (role: `designer`) — charter `skills/agents/designer/SKILL.md`
+> **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

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

@@ -51,9 +51,9 @@ When researching or resolving any technical question during exploration, follow
    - per step, state a `verify:` criterion — what concrete evidence confirms that step succeeded (a read signature, a matched call graph, a resolved data path) before moving on
    - define what evidence would be enough to answer the user
    - ask only if the objective or scope cannot be inferred from local context
-6. Recon with progressive disclosure. Dispatch `investigator` per `references/agent-orchestration.md` when the investigation justifies an isolated read-only subagent:
+6. Recon with progressive disclosure. Dispatch `code-explorer` per `references/agent-orchestration.md` when the investigation justifies an isolated read-only subagent:
 
-> **Dispatch: `massa-ai-investigator`** (role: `investigator`) — charter `skills/agents/investigator/SKILL.md`
+> **Dispatch: `code-explorer`** (role: `code-explorer`, mode: `trace`) — charter `skills/agents/code-explorer/SKILL.md`
 > - trigger: isolated read-only investigation justified; large scope, repeated searches, or context-firewall threshold exceeded
 > - scope: the exploration target — symbols, files, routes, commands, docs, or runtime artifacts to inspect
 > - permissions: read-only

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

@@ -54,25 +54,24 @@ Before the first repository mutation, load `references/implementation-delivery.m
    - When every group has a confirmed Jira key, follow the optional stacked branch flow in `references/pr-task-fix.md` (Jira-Key Stacked Branches).
    - All PR groups decomposed under this feature share one feature-level delivery go-ahead: no individual group seeks or receives its own Stage 3 sign-off — see `references/implementation-delivery.md` Stage 3.
 
-**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `massa-ai-designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
+**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
 
-> **Dispatch: `massa-ai-designer`** (role: `designer`) — charter `skills/agents/designer/SKILL.md`
+> **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: `massa-ai-reviewer`** (role: `reviewer`) — charter `skills/agents/reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — 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
-> - permissions: read-only
 > - inputs: 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: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/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 reviewer fix items; Quick tier substitutes the fallback below
+> **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
 > - 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-audit.md

@@ -38,11 +38,30 @@ Not for a single requested audit lens — route directly to that lens. Do not ed
    - For a broad/full audit, run Correctness, Architecture, Code Quality, Security, and Tests. Run Requirements only when a requirements source is available.
    - Supported lenses: Correctness -> `workflows/bugs/bugs-audit.md`; Architecture -> `workflows/architecture/architecture-audit.md`; Code Quality -> `workflows/code-quality/code-quality-audit.md`; Security -> `workflows/security/security-audit.md`; Requirements -> `workflows/requirements/requirements-audit.md`; Tests -> `workflows/tests/tests-audit.md`.
    - When a broad audit lacks requirements, ask for a source when interactive and not forbidden; otherwise mark Requirements `not evaluated: missing source`. Never report a requirements all-clear without a source.
-7. Establish child contracts and dispatch `audit-specialist` per lens through `references/agent-orchestration.md`:
+7. Establish child contracts and dispatch one agent per lens through `references/agent-orchestration.md`: `code-reviewer` for Correctness (`lens: bugs`), Architecture, Code Quality, and Security; `product-manager` for Requirements; `test-engineer` for Tests.
 
-> **Dispatch: `massa-ai-audit-specialist`** (role: `audit-specialist`) — charter `skills/agents/audit-specialist/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: broad/full audit requiring multiple lenses, or explicit multi-lens request
-> - scope: one lens per dispatch against the shared implementation scope packet (Correctness/Architecture/Code Quality/Security/Requirements/Tests)
+> - scope: one lens per dispatch against the shared implementation scope packet (Correctness as `lens: bugs`, Architecture as `lens: architecture`, Code Quality as `lens: code-quality`, Security as `lens: security`)
+> - inputs: exact `projectId`, parent `workflowSessionId`, child workflow, lens name, shared scope packet, resolved files/diff summary, relevant recalled facts, allowed surrounding-code depth, deterministic sensors, context-firewall limits, and output contract
+> - sensors: target-relevant deterministic commands (tests, builds, lint, type checks, static checks, import checks) per lens
+> - output: `Status`, `Scope checked`, `Evidence`, `Findings`, `Verification/Test Fidelity Checklist`, `Risks and skipped checks`, and `Exact next step`
+> - firewall: raw diffs/logs/search output summarized, not returned raw
+> - memory: suggest-only; children must not persist broad project memory unless assigned
+
+> **Dispatch: `product-manager`** (role: `product-manager`, mode: `audit`) — charter `skills/agents/product-manager/SKILL.md`
+> - trigger: the Requirements lens is in scope and a requirements source is available
+> - scope: the Requirements lens (`lens: requirements`) against the shared implementation scope packet and the resolved requirements source
+> - permissions: read-only
+> - inputs: exact `projectId`, parent `workflowSessionId`, child workflow, lens name, shared scope packet, resolved files/diff summary, relevant recalled facts, allowed surrounding-code depth, deterministic sensors, context-firewall limits, and output contract
+> - sensors: target-relevant deterministic commands (tests, builds, lint, type checks, static checks, import checks) per lens
+> - output: `Status`, `Scope checked`, `Evidence`, `Findings`, `Verification/Test Fidelity Checklist`, `Risks and skipped checks`, and `Exact next step`
+> - firewall: raw diffs/logs/search output summarized, not returned raw
+> - memory: suggest-only; children must not persist broad project memory unless assigned
+
+> **Dispatch: `test-engineer`** (role: `test-engineer`, mode: `audit`) — charter `skills/agents/test-engineer/SKILL.md`
+> - trigger: the Tests lens is in scope
+> - scope: the Tests lens (`lens: tests`) against the shared implementation scope packet
 > - permissions: read-only
 > - inputs: exact `projectId`, parent `workflowSessionId`, child workflow, lens name, shared scope packet, resolved files/diff summary, relevant recalled facts, allowed surrounding-code depth, deterministic sensors, context-firewall limits, and output contract
 > - sensors: target-relevant deterministic commands (tests, builds, lint, type checks, static checks, import checks) per lens

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

@@ -32,7 +32,7 @@ Do not execute from chat summaries, inline review comments, remembered findings,
    - `references/discrimination-sensor.md` before closing any finding at the tiers the verification-ladder's Independent Verification Mandate names.
    - `references/knowledge-verification-chain.md` when a finding's fix depends on external library/API behavior not already verified this session.
    - `references/brownfield-mapping.md` (Minimum Bar only) for Standard+ findings when recall returns no hit for the target and no gate command is derivable from the report's evidence.
-   - `references/agent-orchestration.md` for high-risk findings or disjoint implementation slices; the mandated verification-agent dispatch below is carved out of this trigger by agent-orchestration's Independent Verification Exception and always attempts dispatch at its own tier gate.
+   - `references/agent-orchestration.md` for high-risk findings or disjoint implementation slices; the mandated `code-reviewer` `verify` dispatch below is carved out of this trigger by agent-orchestration's Independent Verification Exception and always attempts dispatch at its own tier gate.
 3. `recall` -> load prior implementation audit decisions, known regressions, architecture/security boundaries, accepted exceptions, testing conventions, and reusable verification recipes for the target.
 4. Select the report with an explicit execution focus:
    - Establish report selector, target focus, and optional source-qualified finding IDs before selecting a report.
@@ -62,14 +62,14 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 9. Size each finding with `references/verification-ladder.md`. Quick findings may proceed locally; Standard findings require characterization and an explicit recipe; ambiguous, cross-boundary, migration-heavy, or broad redesign findings pause and route to `spec-driven`.
 10. Orchestrate conservatively. The main agent owns report parsing, scope/freshness, prioritization, questions, memory, and final evidence. Dispatch per `references/agent-orchestration.md`:
 
-**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `massa-ai-designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
+**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
 
-> **Dispatch: `massa-ai-designer`** (role: `designer`) — charter `skills/agents/designer/SKILL.md`
+> **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: `massa-ai-builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
+> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/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)
@@ -81,17 +81,16 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 
     Never run parallel writers against shared files or contracts.
 
-> **Dispatch: `massa-ai-reviewer`** (role: `reviewer`) — charter `skills/agents/reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — 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
-> - permissions: read-only
 > - inputs: 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: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `verify`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: an `Area/PREFIX-N` finding's closure meets the verification-ladder's Independent Verification Mandate tier gate — Standard+/Spec-driven size or any high/critical-severity finding
 > - scope: the closed `Area/PREFIX-N` finding's fix diff, its source-lens claim, and the validation assets the fix touches
 > - inputs: the source-qualified finding ID, the applied fix diff, the report's Verification Suggestion, and the pending closure-matrix row

package/skills/massa-ai/workflows/judge-with-debate.md

@@ -12,10 +12,10 @@ Use when the user explicitly asks to evaluate an artifact through multi-judge
 debate — "judge this", "judge-with-debate", "evaluate with debate", "run the judges on X". The
 user supplies artifact path(s) plus a task description (what the artifact was supposed to
 accomplish) and optionally evaluation context. Standalone, explicit-route workflow: never
-auto-selected by the router for generic review work (use `reviewer`, `*-audit`, or
-`plan-critic` for those).
+auto-selected by the router for generic review work (use `code-reviewer`, `*-audit`, or
+the Plan Challenge `judge` `plan-critique` dispatch for those).
 
-The protocol: a meta-judge authors a tailored evaluation specification **once**; three
+The protocol: one `judge` in `spec-author` mode authors a tailored evaluation specification **once**; three
 independent judges score the artifact against it with quoted evidence; the judges debate their
 disagreements over **up to 3 rounds**; the panel converges on a consensus verdict or reports an
 honest no-consensus. Ported from the NeoLabHQ `judge-with-debate` pattern; this file is the
@@ -57,7 +57,7 @@ Check whether the host supports **dispatch-time model selection** (a per-dispatc
 parameter on the task/subagent tool). This probe runs on every invocation — when a host gains
 the capability, per-slot diversity activates automatically with no harness edit.
 
-- Probe positive → request per-slot models at dispatch: meta-judge `kimi-k3`, Judge 1
+- Probe positive → request per-slot models at dispatch: spec-author `kimi-k3`, Judge 1
   `deepseek-v4-pro`, Judge 2 `minimax-m3`, Judge 3 `GLM-5.2`.
 - Probe negative (all four hosts today) → dispatch the charter-default artifacts and record the
   unmet per-slot requests. Every fallback is named; if any slot fell back the consensus file and
@@ -66,12 +66,12 @@ the capability, per-slot diversity activates automatically with no harness edit.
 - A pinned-but-unavailable model falls back to the host default for that slot, named loudly in
   the same way.
 
-## Step 1 — Meta-judge (exactly once)
+## Step 1 — Spec-author (exactly once)
 
-Dispatch `massa-ai-meta-judge` (read-only) with the task description, artifact type, context,
+Dispatch `judge` in `spec-author` mode (read-only) with the task description, artifact type, context,
 and artifact paths. Model request: `kimi-k3` (see Step 0.5).
 
-> **Dispatch: `massa-ai-meta-judge`** (role: `meta-judge`) — charter `skills/agents/meta-judge/SKILL.md`
+> **Dispatch: `judge`** (role: `judge`, mode: `spec-author`) — charter `skills/agents/judge/SKILL.md`
 > - trigger: judge-with-debate Step 1; runs exactly once per evaluation
 > - scope: the artifact under evaluation (paths supplied), task description, artifact type
 > - permissions: read-only
@@ -94,23 +94,23 @@ Validate the returned evaluation specification in two stages, in order; a retry
    `rubric` with anchors for scores 1, 3, 5, and a `checklist` with ≥1 item. Parseable but
    invalid specs (e.g. `scale.max: 7`) fail here, not at stage 1.
 
-On failure: retry the meta-judge **once** with the failed stage + check name. Second failure →
-stop `Blocked`. The meta-judge runs exactly once per evaluation — never re-run between rounds,
+On failure: retry the spec-author **once** with the failed stage + check name. Second failure →
+stop `Blocked`. The spec-author runs exactly once per evaluation — never re-run between rounds,
 never edited by the orchestrator; the YAML passes to all judges in all rounds **verbatim**.
 
-Feedback: `🤖 [Agent Started] Meta-Judge is authoring the evaluation specification.`
+Feedback: `🤖 [Agent Started] Judge (spec-author) is authoring the evaluation specification.`
 then `🤖 [Agent Done]` or `🤖 [Agent Blocked]` with the one-line reason.
 
 ## Step 2 — Independent analysis (3 judges in parallel)
 
-Dispatch three `massa-ai-judge` agents **in parallel** (round 0), one per judge number, each
+Dispatch three `judge` agents in `scorer` mode **in parallel** (round 0), one per judge number, each
 with: the verbatim specification YAML, task description, artifact paths, its own report path,
 `round: 0`, and its model request (Step 0.5). The fixed panel of 3 sits inside the wave cap of
 4 concurrent subagents (`references/agent-orchestration.md`, Orchestrator Working Memory).
 Each judge writes its own `audits/judge/<...> judge-N.md` per the report contract and returns
 the reply block:
 
-> **Dispatch: `massa-ai-judge`** (role: `judge`) — charter `skills/agents/judge/SKILL.md` — 3 per panel, rounds 0..3
+> **Dispatch: `judge`** (role: `judge`, mode: `scorer`) — charter `skills/agents/judge/SKILL.md` — 3 per panel, rounds 0..3
 > - trigger: judge-with-debate Steps 2 and 4; panel of exactly 3, never more
 > - scope: the artifact under evaluation, the verbatim specification YAML, own report path; debate rounds add all three report paths as peer paths and `round: R`
 > - permissions: read-only except appending to its own judge-N report file
@@ -159,7 +159,7 @@ Step 5. If no consensus and rounds remain → Step 4. If no consensus after roun
 
 ## Step 4 — Debate round (rounds 1..3, max 3)
 
-Increment the round. Dispatch three `massa-ai-judge` agents **in parallel** again, each with:
+Increment the round. Dispatch three `judge` agents **in parallel** again, each with:
 the verbatim specification YAML (unchanged), task description, artifact paths, its own report
 path, **all three** report paths as peer paths, and `round: R`. Each judge:
 
@@ -198,7 +198,7 @@ did not reach.**
 
 ## Pitfalls (each is a rule, not advice)
 
-- Never skip the meta-judge; never let judges score without the shared specification.
+- Never skip the spec-author; never let judges score without the shared specification.
 - Never modify or regenerate the specification between rounds — verbatim, every round.
 - Never let a debate judge create a new report file — append-only `## Debate Round {R}` sections.
 - Never relay reports between judges through the orchestrator — filesystem channel only.

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

@@ -58,9 +58,9 @@ Do not edit code. Route direct design implementation to `design`. Not for Flutte
 16. Persist only durable token/component mappings, source-set ownership rules, approved accessibility/platform deviations, asset-pipeline rules, or reusable render recipes after Importance Calibration. Use `workflow:mobile-figma-audit` and required tags. Never persist screenshots, hierarchy dumps, raw logs, device IDs, or user data.
 17. Complete `references/evidence-gate.md`. A model visual impression cannot satisfy the gate.
 
-**Screen work — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `massa-ai-designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
+**Screen work — unconditional in this workflow:** every task here judges 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`).
 
-> **Dispatch: `massa-ai-designer`** (role: `designer`) — charter `skills/agents/designer/SKILL.md`
+> **Dispatch: `designer`** (role: `designer`, mode: `audit`) — charter `skills/agents/designer/SKILL.md`
 > - scope: the screens, views, components, layouts, styles, and design tokens under audit — never the whole repository, and no edits
 > - permissions: read-only — this workflow is findings-only; the charter permits writes only when explicitly scoped, and its Restrictions win over the packet, so read-only governs
 > - output: per-element conformance table (element, expected, actual, verdict, severity) feeding `MFM-*` findings; a missing or unreachable design source is listed as a skipped sensor, never a silent pass

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 tier-gated builder/verification-agent dispatch in the fix loop below.
+   - `references/agent-orchestration.md` for the designer/builder 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.
@@ -58,36 +58,35 @@ Do not execute from chat summaries, screenshots alone, remembered findings, or a
    - Keep XML/Compose, UIKit/SwiftUI, and KMP/native interoperability explicit. Do not duplicate one visual rule across layers when an established shared source owns it.
    - Do not weaken screenshot tests, previews, fixtures, assertions, test tags, resource IDs, content descriptions, or Maestro selectors to hide a mismatch.
    - 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 verification-agent block below is tier-gated mandatory, not merely discretionary — carved out of ordinary delegation gating by that reference's Independent Verification Exception:
+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 — before writing or judging any user-facing screen:** when this task creates or modifies a screen, the `massa-ai-designer` dispatch below is mandatory rather than discretionary, carved out of ordinary delegation gating by the Screen Implementation Exception in `references/agent-orchestration.md`. It does not fire when the task touches no screen surface.
+**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.
 
-> **Dispatch: `massa-ai-designer`** (role: `designer`) — charter `skills/agents/designer/SKILL.md`
+> **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: `massa-ai-builder`** (role: `builder`) — charter `skills/agents/builder/SKILL.md`
-> - trigger: a selected `MFM-*` finding spans a disjoint surface or shared-root slice, or an explicit subagent request
-> - scope: one `MFM-*` finding, or a coherent surface group sharing one KMP root cause, with a disjoint write set
-> - permissions: write (disjoint write set, per-surface or per-module ownership)
+> **Dispatch: `builder`** (role: `builder`) — charter `skills/agents/builder/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)
 > - inputs: the finding's Surface ID, Figma value, resolved token/resource/asset chain, current implementation value, and simplest fix direction
 > - sensors: the remediation matrix's assigned runtime sensor and optional Maestro packet for the surface
 > - output: implementation summary, changed files, commands run, per-surface render evidence
 > - firewall: raw diffs and screenshots summarized
 > - memory: suggest-only; main agent persists reusable token/mapping patterns
 
-> **Dispatch: `massa-ai-reviewer`** (role: `reviewer`) — charter `skills/agents/reviewer/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `review`) — 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
-> - permissions: read-only
 > - inputs: 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: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `verify`) — charter `skills/agents/code-reviewer/SKILL.md`
 > - trigger: mandatory at Standard+/Spec-driven size or high/critical severity per the Independent Verification Mandate in `references/verification-ladder.md`; a Quick-tier finding runs the fallback fresh-eyes self-check below instead
 > - scope: the fixed `MFM-*` finding's surface, resolved token/value, comparison-matrix row, and closure claim
 > - inputs: the finding, the applied fix, the comparison-matrix row, the render sensor used, and validation assets

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

@@ -17,7 +17,7 @@ conflict with the base.
 Use when the user explicitly asks to review a hosted PR (Pull Request, GitHub) or
 MR (Merge Request, GitLab) — "review PR 128", "review this MR", "check pull request
 42". Explicit route only: never auto-trigger during coding. Local working-tree diff
-review stays with the audit workflows and `massa-ai-reviewer`; this workflow exists
+review stays with the audit workflows and `code-reviewer`; this workflow exists
 to **post findings back to the host**.
 
 Load `references/project-context.md` (intake sweep) before the first substantive
@@ -142,19 +142,28 @@ the severity labels, and the reply contract.
 
 | # | Dimension | Agent | Packet delta (lens / scope) | Marker `{type}` |
 | --- | --- | --- | --- | --- |
-| 1 | Security | `massa-ai-audit-specialist` | `lens: security` — secrets, authn/authz on new endpoints, injection, unsafe deserialization, PII in logs, permissive CORS, leaking payload fields | `security` |
-| 2 | Requirements & DoD (Definition of Done) | `massa-ai-audit-specialist` | `lens: requirements` — score merged Track A + Track B criteria against the diff, evidence-or-zero: ✅ implemented (`path:line`) / 🟡 partial / ❌ missing; no source ⇒ report "requirements verification skipped" | `requirements` |
-| 3 | Architecture & conventions | `massa-ai-audit-specialist` | `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 | `massa-ai-audit-specialist` | `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 | `massa-ai-audit-specialist` | `lens: tests` (dedicated 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 | `massa-ai-reviewer` | 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` |
+| 1 | Security | `code-reviewer` | `lens: security` — secrets, authn/authz on new endpoints, injection, unsafe deserialization, PII in logs, permissive CORS, leaking payload fields | `security` |
+| 2 | Requirements & DoD (Definition of Done) | `product-manager` | `mode: audit` — score merged Track A + Track B criteria against the diff, evidence-or-zero: ✅ implemented (`path:line`) / 🟡 partial / ❌ missing; no source ⇒ report "requirements verification skipped" | `requirements` |
+| 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` |
 
 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.
 
-> **Dispatch: `massa-ai-audit-specialist`** (role: `audit-specialist`) — charter `skills/agents/audit-specialist/SKILL.md`
-> - trigger: pr-review Step 2, dimension rows 1–5 (one dispatch per row)
-> - scope: the PR/MR diff and surrounding context for one dimension row; never the whole repository
+> **Dispatch: `code-reviewer`** (role: `code-reviewer`, mode: `audit`) — charter `skills/agents/code-reviewer/SKILL.md`
+> - trigger: pr-review Step 2, dimension rows 1, 3, and 4 (one dispatch per row)
+> - scope: the PR/MR diff and surrounding context for one dimension row; never the whole repository; no host CLI calls, no posting
+> - inputs: exact `projectId`, parent `workflowSessionId`, dimension row (lens + scope), DISCOVERY MAP, PR/MR intent, trimmed diff, existing-comment inventory, severity labels, reply contract
+> - sensors: second-pass sweep — re-read the full trimmed diff, list every file/hunk not commented on, and state per file why it is clean for this dimension before returning
+> - output: structured reply block — findings rows `{path, head-line, severity, marker type, title, body ≤ 6 lines, recommendation}` + exactly one positive highlight + files-swept-clean list; when uncertain a finding is real, withhold it (the source protocol's high-confidence bar, applied qualitatively)
+> - firewall: raw diff/log/search output summarized, never returned raw
+> - memory: suggest-only; the main agent persists durable outcomes
+
+> **Dispatch: `product-manager`** (role: `product-manager`, mode: `audit`) — charter `skills/agents/product-manager/SKILL.md`
+> - trigger: pr-review Step 2, dimension row 2 (requirements & DoD)
+> - scope: the PR/MR diff and surrounding context for dimension row 2; never the whole repository
 > - permissions: read-only; no host CLI calls, no posting
 > - inputs: exact `projectId`, parent `workflowSessionId`, dimension row (lens + scope), DISCOVERY MAP, PR/MR intent, trimmed diff, existing-comment inventory, severity labels, reply contract
 > - sensors: second-pass sweep — re-read the full trimmed diff, list every file/hunk not commented on, and state per file why it is clean for this dimension before returning
@@ -162,10 +171,19 @@ 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: `massa-ai-reviewer`** (role: `reviewer`) — charter `skills/agents/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
+> **Dispatch: `test-engineer`** (role: `test-engineer`, mode: `audit`) — charter `skills/agents/test-engineer/SKILL.md`
+> - trigger: pr-review Step 2, dimension row 5 (test coverage)
+> - scope: the PR/MR diff and surrounding context for dimension row 5; never the whole repository
 > - permissions: read-only; no host CLI calls, no posting
+> - inputs: exact `projectId`, parent `workflowSessionId`, dimension row (lens + scope), DISCOVERY MAP, PR/MR intent, trimmed diff, existing-comment inventory, severity labels, reply contract
+> - sensors: second-pass sweep — re-read the full trimmed diff, list every file/hunk not commented on, and state per file why it is clean for this dimension before returning
+> - output: structured reply block — findings rows `{path, head-line, severity, marker type, title, body ≤ 6 lines, recommendation}` + exactly one positive highlight + files-swept-clean list; when uncertain a finding is real, withhold it (the source protocol's high-confidence bar, applied qualitatively)
+> - 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`
+> - 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
 > - 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