@massa-ai/cursor-plugin 1.13.0 → 1.15.0

package/.cursor-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "massa-ai",
-  "version": "1.13.0",
+  "version": "1.15.0",
   "description": "massa-ai — semantic code search, memory, and context compression for Cursor"
 }

package/agents/massa-ai-architecture-specialist.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-architecture-specialist
 description: Read-only architecture guidance agent. Evaluate architecture, suggest boundaries, recommend abstractions, evaluate trade-offs, and suggest modularization. Folds the existing domain-mapper, coupling-auditor, and deepening-architect roles into one specialist. Triggers when a workflow needs architectural guidance before or during design. Never implements or rewrites code.
-tools: ["Read","Grep","Glob","Bash"]
-model: MiniMax M3
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Architecture Specialist Agent Skill
 
@@ -54,9 +53,6 @@ Provide architectural guidance by evaluating structure, suggesting boundaries, a
 - Synapse: own ephemeral session when evaluation spans multiple modules with repeated searches.
 - References: `references/architecture-lenses.md`, `references/architecture-domain-lens.md`, `references/architecture-coupling-lens.md`, `references/architecture-deepening-lens.md`.
 
-## Model Hint
-MiniMax M3 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` or metric pointer.
 - Trade-offs name at least two alternatives.

package/agents/massa-ai-audit-specialist.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-audit-specialist
 description: Configurable read-only audit agent. Execute specialized audits through six lenses — bugs, architecture, security, requirements, code-quality, performance — selected via the lens field in the capability packet. Triggers when a workflow needs a findings-only audit. Never modifies implementation.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Audit Specialist Agent Skill
 
@@ -69,9 +68,6 @@ All lenses share `references/audit-scope.md` (scope rules) and `references/audit
 - Synapse: own ephemeral session when the audit spans multiple modules with repeated searches.
 - References: `references/audit-scope.md`, `references/audit-report-io.md`, plus the per-lens references above.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` pointer.
 - Findings follow the project audit-report format (`references/audit-report-io.md`).

package/agents/massa-ai-builder.md

@@ -1,9 +1,7 @@
 ---
 name: massa-ai-builder
 description: Write-permitted implementation agent. Implement approved plans by modifying source code, creating files, and updating existing code while following project conventions. Triggers when a workflow has an approved plan or task with a disjoint write set. Never redesigns architecture, performs reviews, or generates implementation plans.
-tools: ["Read","Grep","Glob","Bash","Write","Edit"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
 ---
 # Builder Agent Skill
 
@@ -56,9 +54,6 @@ Implement an approved plan or task by modifying source code with a disjoint writ
 - Synapse: none (implementation is not a repeated-search task).
 - References: `references/agent-orchestration.md`, `references/naming-standards.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Verification commands from the plan pass (tests, build, typecheck, lint).
 - Diff stays within the assigned write set.

package/agents/massa-ai-context-curator.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-context-curator
 description: Read-only context preparation agent. Decide which files to open, retrieve memories, use Synapse when appropriate, apply Context Firewall rules, and produce a concise Context Packet consumed by other agents. Triggers when a workflow needs the minimum high-quality context before dispatching a planner, builder, or reviewer. Never implements, reviews, or plans.
-tools: ["Read","Grep","Glob","Bash"]
-model: DeepSeek V4 Pro
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Context Curator Agent Skill
 
@@ -56,9 +55,6 @@ Prepare the minimum high-quality Context Packet required for another agent to do
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
 - References: `references/context-firewall.md`, `references/synapse-policy.md`, `references/mcp-tools.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every file in the Context Packet exists (`test -f`).
 - Every reference in the packet exists in the symlinked skill tree.

package/agents/massa-ai-documentation-agent.md

@@ -1,9 +1,7 @@
 ---
 name: massa-ai-documentation-agent
 description: Engineering documentation agent. Generate README, ADR, RFC, changelog, KDoc, and architecture documentation. Default read-only; writes only doc files when explicitly scoped with a disjoint write set. Triggers when a workflow needs documentation artifacts. Never modifies implementation.
-tools: ["Read","Grep","Glob","Bash","Write","Edit"]
-model: DeepSeek V4 Pro
-reasoningEffort: max
+model: inherit
 ---
 # Documentation Agent Skill
 
@@ -54,9 +52,6 @@ Generate engineering documentation artifacts (README, ADR, RFC, changelog, KDoc,
 - Synapse: none (documentation is not a repeated-search task).
 - References: `references/adr-authoring.md`, `references/rfc/`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Stale-reference scan passes (no dead links to removed files).
 - Doc format matches the project ADR/RFC template.

package/agents/massa-ai-furps-analyst.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-furps-analyst
 description: Read-only FURPS+ dimension analyst. Analyze exactly one FURPS+ dimension (F, U, R, P, S, or X) of a PRD or ADR against its checklist section and return structured refinement findings. Triggers when the furps-refinement workflow fans out per-dimension analysis. Never analyzes other dimensions, never writes files, never mutates Atlassian issues.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # FURPS-Analyst Agent Skill
 
@@ -58,9 +57,6 @@ Analyze exactly one FURPS+ dimension of a PRD or ADR against its checklist secti
 - Synapse: own ephemeral session when >= 2 searches are expected, per `references/synapse-policy.md`.
 - References: `references/furps/checklist.md`, `references/furps/report-contract.md`, `references/furps/intake.md`, `references/agent-orchestration.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Source-location proof (quote plus section) for every `covered`/`partial` claim.
 - Absent-claim detection for every `missing` claim.

package/agents/massa-ai-investigator.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-investigator
 description: Read-only codebase investigation agent. Locate implementations, trace execution flow, identify dependencies, estimate change impact, and answer engineering questions. Triggers when a workflow needs to understand existing code before planning or implementing. Never modifies code, never generates implementation, never performs reviews.
-tools: ["Read","Grep","Glob","Bash"]
-model: DeepSeek V4 Pro
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Investigator Agent Skill
 
@@ -57,9 +56,6 @@ Read and understand the codebase to answer engineering questions without modifyi
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
 - References: `references/codebase-investigation.md`, `references/agent-orchestration.md`, `references/synapse-policy.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Source-backed evidence for every claim (`path:line`).
 - Dependency references confirmed via `get_references` or equivalent.

package/agents/massa-ai-judge.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-judge
 description: Read-only debate-panel evaluator for judge-with-debate. Score an artifact against the meta-judge's evaluation specification with quoted evidence, then defend or revise scores across up to 3 debate rounds until the panel reaches consensus. Writes only its own judge-N report file per dispatch. Never judges outside the specification, never revises without quoted evidence.
-tools: ["Read","Grep","Glob","Bash"]
-model: deepseek-v4-pro
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Judge Agent Skill
 
@@ -79,11 +78,12 @@ next_step: <string>
 - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
-deepseek-v4-pro (advisory charter default — the Judge-1 slot model). Per-slot diversity is
-assigned by the workflow at dispatch: Judge 1 `deepseek-v4-pro`, Judge 2 `minimax-m3`, Judge 3
-`GLM-5.2`. Hosts without dispatch-time model selection run this charter default for every slot;
-the orchestrator records that as `DIVERSITY DEGRADED` per the workflow contract. Fallback to the
-workflow's configured default model if the pinned model is unavailable.
+This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
+model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
+model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
+the single source for the current slot assignments, not this file. When dispatch-time selection
+is unavailable, every slot runs the charter default and the orchestrator records
+`DIVERSITY DEGRADED` per the workflow contract.
 
 ## Validation Sensors
 - Every criterion score carries an exact quotation from the artifact.

package/agents/massa-ai-meta-judge.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-meta-judge
 description: Read-only evaluation-specification author for judge-with-debate. Generate the tailored rubric, criteria, weights, and checklists that a panel of judge agents uses to evaluate an artifact through independent analysis and multi-round debate. Runs exactly once per evaluation. Never scores the artifact, never edits the specification after emission.
-tools: ["Read","Grep","Glob","Bash"]
-model: kimi-k3
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Meta-Judge Agent Skill
 
@@ -70,8 +69,11 @@ overall: weighted-mean
 - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
-kimi-k3 (advisory). Fallback to the workflow's configured default model if unavailable; the
-fallback is recorded by the orchestrator as a diversity warning per the workflow contract.
+This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
+model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
+model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
+is the single source for the current assignment, not this file. When dispatch-time selection is
+unavailable, the orchestrator records a diversity warning per the workflow contract.
 
 ## Validation Sensors
 - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.

package/agents/massa-ai-mobile-specialist.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-mobile-specialist
 description: Conditional mobile expertise agent. Provide Android, Kotlin, Compose, KMP, Swift, iOS, Gradle, CocoaPods, performance, lifecycle, and offline-sync guidance. Invoked only when the workflow detects a mobile-related project. Read-only. Triggers on mobile detection signals; refuses non-mobile targets.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Mobile Specialist Agent Skill
 
@@ -71,9 +70,6 @@ If none are present, refuse with: `Non-mobile target. Refusing mobile-specialist
 - Synapse: own ephemeral session when guidance spans multiple mobile modules with repeated searches.
 - References: `references/mobile-context.md`, `references/mobile-diagnosis.md`, `references/maestro.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - At least one detection signal is confirmed present before guidance is given.
 - Every finding has a `path:line` pointer or a platform constraint citation.

package/agents/massa-ai-navigator.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-navigator
 description: Code exploration specialist that leverages the massa-ai semantic index instead of brute-force file reads. Use when the user asks "where is X?", "how does Y work?", "who calls Z?", or for any question about an indexed codebase. Starts every investigation by consulting the massa-ai index (project map, definitions, references) before falling back to Read/Grep.
-tools: ["mcp__massa-ai__*","Read","Grep","Glob","Bash(pwd)"]
-model: DeepSeek V4 Pro
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Navigator Agent Skill
 
@@ -63,9 +62,6 @@ The user's codebase is **already indexed** by massa-ai. The first move on any qu
 - Massa-ai Memory: suggest durable navigation facts (entry points, ownership boundaries) only when reusable; the main agent persists.
 - References: `references/mcp-tools.md`, `references/codebase-investigation.md`, `references/synapse-policy.md`, `references/context-firewall.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every claim carries a `path:line` or symbol pointer.
 - Index-derived claims carry freshness evidence, or are labeled reduced-confidence.

package/agents/massa-ai-plan-critic.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-plan-critic
 description: Read-only plan-challenge agent. Stress-test a constructed plan, surface the assumption most likely to fail, name the deterministic check that would falsify success, and return a bounded critique for the lite or full Plan Challenge gate. Triggers after a concrete plan exists. Never edits the plan, never implements, never expands scope.
-tools: ["Read","Grep","Glob","Bash"]
-model: MiniMax M3
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Plan-Critic Agent Skill
 
@@ -77,9 +76,6 @@ Never receives full conversation context.
 - Policy: the main agent owns mode selection, synthesis, plan revision, and the Evidence Gate; this agent owns the critique only.
 - References: `references/agent-orchestration.md`, `references/the-fool/`, `references/verification-ladder.md`.
 
-## Model Hint
-MiniMax M3 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every challenge ties to a plan section plus a concrete evidence gap or falsifiable check.
 - No challenge rests on missing conversation history that the packet intentionally excluded.

package/agents/massa-ai-planner.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-planner
 description: Read-only planning agent. Transform engineering requests into implementation plans by breaking work into steps, identifying dependencies and risks, suggesting execution order, and producing an implementation strategy. Triggers when a workflow needs a plan before implementation. Never implements or reviews code.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Planner Agent Skill
 
@@ -54,9 +53,6 @@ Transform an engineering request into a structured implementation plan.
 - Synapse: none (planning is not a repeated-search task).
 - References: `references/agent-orchestration.md`, `references/subagent-design.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every step in the plan references a concrete file, module, or task.
 - Every risk has a mitigation or accepted-risk note.

package/agents/massa-ai-requirements-analyst.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-requirements-analyst
 description: Read-only requirements analysis agent. Detect ambiguity, missing requirements, contradictions, implicit requirements, and uncovered scenarios before implementation. Triggers during the Specify phase when gray areas, persistence, external calls, auth, payments, concurrency, or state transitions affect behavior. Never implements.
-tools: ["Read","Grep","Glob","Bash"]
-model: DeepSeek V4 Pro
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Requirements Analyst Agent Skill
 
@@ -53,9 +52,6 @@ Analyze requirements before implementation to surface ambiguity, gaps, contradic
 - Synapse: none (analysis is not a repeated-search task).
 - References: `references/spec-driven/specify.md`, `references/furps/`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding cites a requirement ID or spec section.
 - Every implicit requirement is flagged for user acceptance or recorded as an assumption.

package/agents/massa-ai-reviewer.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-reviewer
 description: Read-only diff review agent. Analyze diffs to detect bugs, regressions, code smells, missing edge cases, and suggest improvements. Triggers after a builder completes a task and before the verification gate. Never implements, rewrites files, or plans features.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Reviewer Agent Skill
 
@@ -55,9 +54,6 @@ Review implementation quality by analyzing the diff and flagging bugs, regressio
 - Synapse: none (review is not a repeated-search task).
 - References: `references/agent-orchestration.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` pointer.
 - Static checks (lint, typecheck) run when available.

package/agents/massa-ai-test-engineer.md

@@ -1,9 +1,7 @@
 ---
 name: massa-ai-test-engineer
 description: Testing strategy agent. Generate unit, integration, edge-case, negative-scenario, and acceptance-coverage test plans. Default read-only; writes only test files when explicitly scoped with a disjoint write set. Triggers when a workflow needs a test strategy or test plan. Focuses only on testing; no production code changes outside test files.
-tools: ["Read","Grep","Glob","Bash","Write","Edit"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
 ---
 # Test Engineer Agent Skill
 
@@ -55,9 +53,6 @@ Generate a testing strategy that covers unit, integration, edge cases, negative
 - Synapse: none (test planning is not a repeated-search task).
 - References: `references/verification-ladder.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every acceptance criterion maps to at least one test case.
 - Edge cases and negative scenarios are enumerated.

package/agents/massa-ai-verification-agent.md

@@ -1,9 +1,8 @@
 ---
 name: massa-ai-verification-agent
 description: Read-only verification agent. Centralize Verification Ladder logic by validating outputs, choosing the verification level, executing the verification checklist, detecting incomplete work, and producing verification reports. Triggers as the mandatory final gate before a task is claimed complete. Never modifies implementation.
-tools: ["Read","Grep","Glob","Bash"]
-model: GLM-5.2
-reasoningEffort: max
+model: inherit
+readonly: true
 ---
 # Verification Agent Skill
 
@@ -53,9 +52,6 @@ Centralize Verification Ladder logic and validate that a task's output meets its
 - Synapse: none (verification is not a repeated-search task).
 - References: `references/verification-ladder.md`, `references/evidence-gate.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every acceptance criterion has a PASS/FAIL verdict with evidence.
 - Skipped checks have a concrete reason.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@massa-ai/cursor-plugin",
-  "version": "1.13.0",
+  "version": "1.15.0",
   "description": "massa-ai plugin for Cursor — semantic code search, memory, and context compression",
   "files": [
     "agents",

package/skills/agents/architecture-specialist/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: MiniMax M3
+  model_tier: deep
   permission: read-only
 ---
 
@@ -58,9 +58,6 @@ Provide architectural guidance by evaluating structure, suggesting boundaries, a
 - Synapse: own ephemeral session when evaluation spans multiple modules with repeated searches.
 - References: `references/architecture-lenses.md`, `references/architecture-domain-lens.md`, `references/architecture-coupling-lens.md`, `references/architecture-deepening-lens.md`.
 
-## Model Hint
-MiniMax M3 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` or metric pointer.
 - Trade-offs name at least two alternatives.

package/skills/agents/audit-specialist/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: read-only
 ---
 
@@ -73,9 +73,6 @@ All lenses share `references/audit-scope.md` (scope rules) and `references/audit
 - Synapse: own ephemeral session when the audit spans multiple modules with repeated searches.
 - References: `references/audit-scope.md`, `references/audit-report-io.md`, plus the per-lens references above.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` pointer.
 - Findings follow the project audit-report format (`references/audit-report-io.md`).

package/skills/agents/builder/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: write
 ---
 
@@ -60,9 +60,6 @@ Implement an approved plan or task by modifying source code with a disjoint writ
 - Synapse: none (implementation is not a repeated-search task).
 - References: `references/agent-orchestration.md`, `references/naming-standards.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Verification commands from the plan pass (tests, build, typecheck, lint).
 - Diff stays within the assigned write set.

package/skills/agents/context-curator/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: DeepSeek V4 Pro
+  model_tier: light
   permission: read-only
 ---
 
@@ -60,9 +60,6 @@ Prepare the minimum high-quality Context Packet required for another agent to do
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
 - References: `references/context-firewall.md`, `references/synapse-policy.md`, `references/mcp-tools.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every file in the Context Packet exists (`test -f`).
 - Every reference in the packet exists in the symlinked skill tree.

package/skills/agents/documentation-agent/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: DeepSeek V4 Pro
+  model_tier: light
   permission: write
 ---
 
@@ -58,9 +58,6 @@ Generate engineering documentation artifacts (README, ADR, RFC, changelog, KDoc,
 - Synapse: none (documentation is not a repeated-search task).
 - References: `references/adr-authoring.md`, `references/rfc/`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Stale-reference scan passes (no dead links to removed files).
 - Doc format matches the project ADR/RFC template.

package/skills/agents/furps-analyst/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: read-only
 ---
 
@@ -62,9 +62,6 @@ Analyze exactly one FURPS+ dimension of a PRD or ADR against its checklist secti
 - Synapse: own ephemeral session when >= 2 searches are expected, per `references/synapse-policy.md`.
 - References: `references/furps/checklist.md`, `references/furps/report-contract.md`, `references/furps/intake.md`, `references/agent-orchestration.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Source-location proof (quote plus section) for every `covered`/`partial` claim.
 - Absent-claim detection for every `missing` claim.

package/skills/agents/investigator/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: DeepSeek V4 Pro
+  model_tier: light
   permission: read-only
 ---
 
@@ -61,9 +61,6 @@ Read and understand the codebase to answer engineering questions without modifyi
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
 - References: `references/codebase-investigation.md`, `references/agent-orchestration.md`, `references/synapse-policy.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Source-backed evidence for every claim (`path:line`).
 - Dependency references confirmed via `get_references` or equivalent.

package/skills/agents/judge/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: deepseek-v4-pro
+  model_tier: deep
   permission: read-only
 ---
 
@@ -83,11 +83,12 @@ next_step: <string>
 - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
-deepseek-v4-pro (advisory charter default — the Judge-1 slot model). Per-slot diversity is
-assigned by the workflow at dispatch: Judge 1 `deepseek-v4-pro`, Judge 2 `minimax-m3`, Judge 3
-`GLM-5.2`. Hosts without dispatch-time model selection run this charter default for every slot;
-the orchestrator records that as `DIVERSITY DEGRADED` per the workflow contract. Fallback to the
-workflow's configured default model if the pinned model is unavailable.
+This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
+model selection is unavailable. The `judge-with-debate` workflow additionally requests per-slot
+model diversity at dispatch time on hosts that support it — `workflows/judge-with-debate.md` is
+the single source for the current slot assignments, not this file. When dispatch-time selection
+is unavailable, every slot runs the charter default and the orchestrator records
+`DIVERSITY DEGRADED` per the workflow contract.
 
 ## Validation Sensors
 - Every criterion score carries an exact quotation from the artifact.

package/skills/agents/meta-judge/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: kimi-k3
+  model_tier: deep
   permission: read-only
 ---
 
@@ -74,8 +74,11 @@ overall: weighted-mean
 - References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
-kimi-k3 (advisory). Fallback to the workflow's configured default model if unavailable; the
-fallback is recorded by the orchestrator as a diversity warning per the workflow contract.
+This charter's `metadata.model_tier` (`deep`) is the fallback every host runs when dispatch-time
+model selection is unavailable. The `judge-with-debate` workflow additionally requests a specific
+model for this slot at dispatch time on hosts that support it — `workflows/judge-with-debate.md`
+is the single source for the current assignment, not this file. When dispatch-time selection is
+unavailable, the orchestrator records a diversity warning per the workflow contract.
 
 ## Validation Sensors
 - Output parses as YAML; weights sum to 1.0 (±0.001); every criterion carries id, name, weight, scale (min 1, max 5), rubric anchors for 1/3/5, and a non-empty checklist.

package/skills/agents/mobile-specialist/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: read-only
 ---
 
@@ -75,9 +75,6 @@ If none are present, refuse with: `Non-mobile target. Refusing mobile-specialist
 - Synapse: own ephemeral session when guidance spans multiple mobile modules with repeated searches.
 - References: `references/mobile-context.md`, `references/mobile-diagnosis.md`, `references/maestro.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - At least one detection signal is confirmed present before guidance is given.
 - Every finding has a `path:line` pointer or a platform constraint citation.

package/skills/agents/navigator/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: DeepSeek V4 Pro
+  model_tier: light
   permission: read-only
   tools: mcp-index
 ---
@@ -68,9 +68,6 @@ The user's codebase is **already indexed** by massa-ai. The first move on any qu
 - Massa-ai Memory: suggest durable navigation facts (entry points, ownership boundaries) only when reusable; the main agent persists.
 - References: `references/mcp-tools.md`, `references/codebase-investigation.md`, `references/synapse-policy.md`, `references/context-firewall.md`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every claim carries a `path:line` or symbol pointer.
 - Index-derived claims carry freshness evidence, or are labeled reduced-confidence.

package/skills/agents/plan-critic/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: MiniMax M3
+  model_tier: deep
   permission: read-only
 ---
 
@@ -81,9 +81,6 @@ Never receives full conversation context.
 - Policy: the main agent owns mode selection, synthesis, plan revision, and the Evidence Gate; this agent owns the critique only.
 - References: `references/agent-orchestration.md`, `references/the-fool/`, `references/verification-ladder.md`.
 
-## Model Hint
-MiniMax M3 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every challenge ties to a plan section plus a concrete evidence gap or falsifiable check.
 - No challenge rests on missing conversation history that the packet intentionally excluded.

package/skills/agents/planner/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: deep
   permission: read-only
 ---
 
@@ -58,9 +58,6 @@ Transform an engineering request into a structured implementation plan.
 - Synapse: none (planning is not a repeated-search task).
 - References: `references/agent-orchestration.md`, `references/subagent-design.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every step in the plan references a concrete file, module, or task.
 - Every risk has a mitigation or accepted-risk note.

package/skills/agents/requirements-analyst/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: DeepSeek V4 Pro
+  model_tier: standard
   permission: read-only
 ---
 
@@ -57,9 +57,6 @@ Analyze requirements before implementation to surface ambiguity, gaps, contradic
 - Synapse: none (analysis is not a repeated-search task).
 - References: `references/spec-driven/specify.md`, `references/furps/`.
 
-## Model Hint
-DeepSeek V4 Pro (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding cites a requirement ID or spec section.
 - Every implicit requirement is flagged for user acceptance or recorded as an assumption.

package/skills/agents/reviewer/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: read-only
 ---
 
@@ -59,9 +59,6 @@ Review implementation quality by analyzing the diff and flagging bugs, regressio
 - Synapse: none (review is not a repeated-search task).
 - References: `references/agent-orchestration.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every finding has a `path:line` pointer.
 - Static checks (lint, typecheck) run when available.

package/skills/agents/test-engineer/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: write
 ---
 
@@ -59,9 +59,6 @@ Generate a testing strategy that covers unit, integration, edge cases, negative
 - Synapse: none (test planning is not a repeated-search task).
 - References: `references/verification-ladder.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every acceptance criterion maps to at least one test case.
 - Edge cases and negative scenarios are enumerated.

package/skills/agents/verification-agent/SKILL.md

@@ -5,7 +5,7 @@ license: MIT
 metadata:
   author: S1LV4, luizgmassa
   version: "1.0.0"
-  model_hint: GLM-5.2
+  model_tier: standard
   permission: read-only
 ---
 
@@ -57,9 +57,6 @@ Centralize Verification Ladder logic and validate that a task's output meets its
 - Synapse: none (verification is not a repeated-search task).
 - References: `references/verification-ladder.md`, `references/evidence-gate.md`.
 
-## Model Hint
-GLM-5.2 (advisory). Fallback to the workflow's configured default model if unavailable.
-
 ## Validation Sensors
 - Every acceptance criterion has a PASS/FAIL verdict with evidence.
 - Skipped checks have a concrete reason.

package/skills/massa-ai/references/agent-orchestration.md

@@ -79,25 +79,31 @@ dispatch.
 
 Before adding a new reusable role, load `references/subagent-design.md` and write a bounded role charter. For one-off tasks, use an existing role plus the prompt contract below instead of inventing a new role.
 
-| Role | Host agent name | Use For | Read/Write | Charter |
-|---|---|---|---|---|
-| `investigator` | `massa-ai-investigator` | Trace code paths, find entry points, summarize current behavior | read-only | `skills/agents/investigator/SKILL.md` |
-| `navigator` | `massa-ai-navigator` | Answer "where is X / who calls Y" from the massa-ai index before reading files | read-only | `skills/agents/navigator/SKILL.md` |
-| `implementer` → `builder` | `massa-ai-builder` | Execute one atomic task with a disjoint write set | write | `skills/agents/builder/SKILL.md` |
-| `verifier` → `verification-agent` | `massa-ai-verification-agent` | Independently run sensors and inspect whether claims hold | read-only | `skills/agents/verification-agent/SKILL.md` |
-| `domain-mapper` → `architecture-specialist` | `massa-ai-architecture-specialist` | Identify subdomains, bounded contexts, language conflicts, cohesion | read-only | `skills/agents/architecture-specialist/SKILL.md` (lens: `domain`) |
-| `coupling-auditor` → `architecture-specialist` | `massa-ai-architecture-specialist` | Analyze strength, distance, volatility, and risky dependencies | read-only | `skills/agents/architecture-specialist/SKILL.md` (lens: `coupling`) |
-| `deepening-architect` → `architecture-specialist` | `massa-ai-architecture-specialist` | Find shallow modules and deepening opportunities | read-only | `skills/agents/architecture-specialist/SKILL.md` (lens: `deepening`) |
-| `audit-specialist` | `massa-ai-audit-specialist` | Findings-only audit through one selected `lens` | read-only | `skills/agents/audit-specialist/SKILL.md` |
-| `plan-critic` | `massa-ai-plan-critic` | Stress-test a constructed plan using The Fool mode and return bounded critique | read-only | `skills/agents/plan-critic/SKILL.md` |
-| `furps-analyst` | `massa-ai-furps-analyst` | Analyze one FURPS+ dimension of a PRD/ADR against the checklist and return structured findings | read-only | `skills/agents/furps-analyst/SKILL.md` |
-
-The remaining charters — `planner`, `reviewer`, `context-curator`,
-`requirements-analyst`, `test-engineer`, `documentation-agent`,
-`mobile-specialist` — follow the same `massa-ai-<role>` convention and are
-listed in the Agent Table of `skills/AGENTS.md`.
-
-**Role mapping:** `investigator`→`investigator` (identical); `implementer`→`builder` (renamed); `verifier`→`verification-agent` (renamed, centralizes Verification Ladder); `domain-mapper`+`coupling-auditor`+`deepening-architect`→`architecture-specialist` (three roles folded into one specialist; the `lens` input field selects the sub-mode). Workflows dispatch the new agent names via named dispatch blocks; the old role names above are kept for traceability only.
+## Roles
+
+**The roster lives in one place: the Agent Table of `skills/AGENTS.md`**, which names
+every shipped specialist with its purpose, trigger, permission, and charter path. Do not
+restate it here. A second roster in this file is what let `judge` and `meta-judge` go
+undocumented for a whole release with every gate green — the guard checked that the
+charter paths *mentioned* here resolve, which a charter that is never mentioned cannot
+fail.
+
+This file owns dispatch mechanics. The one roster fact it owns is the **legacy role
+vocabulary**: names earlier workflows dispatched by, kept so an old reference still
+resolves to a current agent.
+
+| Legacy role | Current agent | Note |
+|---|---|---|
+| `implementer` | `massa-ai-builder` | renamed |
+| `verifier` | `massa-ai-verification-agent` | renamed; also centralizes the Verification Ladder |
+| `domain-mapper` | `massa-ai-architecture-specialist` | folded in; `lens: domain` |
+| `coupling-auditor` | `massa-ai-architecture-specialist` | folded in; `lens: coupling` |
+| `deepening-architect` | `massa-ai-architecture-specialist` | folded in; `lens: deepening` |
+
+`investigator`, `plan-critic` and `furps-analyst` kept their own names; every other
+specialist is new and never had a legacy one. Workflows dispatch the current
+`massa-ai-<role>` name through a named dispatch block — the legacy column is traceability
+only, never a dispatch target.
 
 ## Capability Packet
 

package/skills/massa-ai/references/maestro/fact-ledger.md

@@ -7,7 +7,7 @@ Use this before making Maestro claims. It defines source authority, fact tags, l
 1. `official-doc`: current official Maestro documentation, preferably `.md` pages under `https://docs.maestro.dev/`.
 2. `live-help`: successful local CLI transcript from the installed Maestro binary, including command, exit code, stdout, and stderr.
 3. `repo-convention`: current repository flows, config, CI, scripts, report paths, and existing naming/tag patterns.
-4. `excluded/unverified`: NotebookLM answers, `/Users/luizmassa/Downloads/questions.md`, blog posts, memory, or assumptions that are not confirmed by the first three sources.
+4. `excluded/unverified`: NotebookLM answers, a user-supplied coverage checklist, blog posts, memory, or assumptions that are not confirmed by the first three sources.
 
 If sources conflict, prefer `official-doc` for product behavior and `live-help` for installed CLI syntax. Mention version drift when `live-help` differs from docs.
 
@@ -39,7 +39,7 @@ If PATH cannot resolve `maestro`, mark local CLI validation blocked. If the bina
 
 ## Coverage Checklist Handling
 
-Use `/Users/luizmassa/Downloads/questions.md` as a checklist to ask "did we cover this surface?" Never cite it as source truth.
+When the user supplies a coverage checklist, use it to ask "did we cover this surface?" Never cite it as source truth, and never assume one exists — if the user supplied none, this section imposes no requirement.
 
 Checklist-only facts that must stay non-normative unless independently verified:
 

package/skills/massa-ai/references/maestro.md

@@ -6,7 +6,7 @@ Use this small index from `workflows/maestro/maestro.md`, `workflows/maestro/mae
 
 Load `references/maestro/fact-ledger.md` before making any normative Maestro claim. Every Maestro claim must be tagged as `official-doc`, `live-help`, `repo-convention`, or `excluded/unverified`.
 
-Use `/Users/luizmassa/Downloads/questions.md` only as a coverage checklist. If a checklist item is not supported by official Maestro docs, live CLI help, or repository convention, quarantine it as `excluded/unverified`.
+Use a user-supplied coverage checklist, when the user provides one, only as a coverage checklist. If a checklist item is not supported by official Maestro docs, live CLI help, or repository convention, quarantine it as `excluded/unverified`.
 
 Official source anchors: