@massa-ai/cursor-plugin 1.6.0 → 1.7.1

package/.cursor-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "massa-ai",
-  "version": "1.6.0",
+  "version": "1.7.1",
   "description": "massa-ai — semantic code search, memory, and context compression for Cursor"
 }

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

@@ -20,7 +20,8 @@ Provide architectural guidance by evaluating structure, suggesting boundaries, a
 ## Restrictions
 - Never implement.
 - Never rewrite code.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the module, service, or area under evaluation.

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

@@ -19,7 +19,8 @@ Execute a specialized audit through one configurable lens and return findings-on
 ## Restrictions
 - Never modify implementation.
 - One lens per dispatch; do not mix lenses in one run.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Lenses
 

package/agents/massa-ai-builder.md

@@ -21,7 +21,8 @@ Implement an approved plan or task by modifying source code with a disjoint writ
 - Never perform reviews.
 - Never generate implementation plans.
 - Never write outside the assigned disjoint write set.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: exact files and modules to modify (disjoint write set).

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

@@ -22,7 +22,8 @@ Prepare the minimum high-quality Context Packet required for another agent to do
 - Never implement.
 - Never review.
 - Never plan.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the next agent's task and target area.

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

@@ -20,7 +20,8 @@ Generate engineering documentation artifacts (README, ADR, RFC, changelog, KDoc,
 ## Restrictions
 - Never modify implementation.
 - Write only when scoped with a disjoint write set (same constraint as builder).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the doc artifact type and target area.

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

@@ -21,7 +21,8 @@ Analyze exactly one FURPS+ dimension of a PRD or ADR against its checklist secti
 - Never analyze a dimension other than the assigned one; flag cross-dimension gaps instead of expanding into them.
 - Never write files, never mutate Atlassian issues, never write memory.
 - Never return raw document dumps.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 - Do not use this role for The Fool critique (use `plan-critic`) or for code claims (use `investigator` / `verification-agent`).
 
 ## Inputs

package/agents/massa-ai-investigator.md

@@ -21,7 +21,8 @@ Read and understand the codebase to answer engineering questions without modifyi
 - Never modify code.
 - Never generate implementation.
 - Never perform reviews.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: files, modules, symbols, or questions to investigate.

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

@@ -20,7 +20,8 @@ Provide mobile-specific expertise (Android, iOS, KMP) when the workflow detects
 ## Restrictions
 - Refuse non-mobile targets (no `build.gradle`, `Podfile`, `*.kt`, `*.swift`, `ios/`, `android/`).
 - Never implement (read-only guidance only).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Topics
 

package/agents/massa-ai-navigator.md

@@ -28,7 +28,8 @@ The user's codebase is **already indexed** by massa-ai. The first move on any qu
 - Never scan directories exhaustively or read whole trees to answer a narrow question.
 - Never paste long code; summarize and cite.
 - Never call `reset_project`, `index`, or `reindex`; report the needed reindex to the parent agent instead.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `question`: the exploration question to answer.

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

@@ -22,7 +22,8 @@ Challenge a plan that already exists so its weakest assumption is exposed before
 - Never implement, refactor, or run mutating commands.
 - Never expand scope beyond the plan packet received.
 - Never request or reconstruct full conversation history.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `plan`: the concrete proposed plan text.

package/agents/massa-ai-planner.md

@@ -20,7 +20,8 @@ Transform an engineering request into a structured implementation plan.
 ## Restrictions
 - Never implement.
 - Never review code.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the request, target area, and known constraints.

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

@@ -20,7 +20,8 @@ Analyze requirements before implementation to surface ambiguity, gaps, contradic
 ## Restrictions
 - Never implement.
 - Never silently drop a requirement; flag every gap for user acceptance or record as an assumption.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the requirement set, PRD, or spec under analysis.

package/agents/massa-ai-reviewer.md

@@ -21,7 +21,8 @@ Review implementation quality by analyzing the diff and flagging bugs, regressio
 - Never implement.
 - Never rewrite files.
 - Never plan features.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the diff, changed files, or PR to review.

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

@@ -21,7 +21,8 @@ Generate a testing strategy that covers unit, integration, edge cases, negative
 - Focus only on testing.
 - No production code changes outside test files.
 - Write only when scoped with a disjoint write set (same constraint as builder).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the feature, module, or spec to test.

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

@@ -20,7 +20,8 @@ Centralize Verification Ladder logic and validate that a task's output meets its
 ## Restrictions
 - Never modify implementation.
 - Never skip a verification level without recording a concrete reason.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the task, its acceptance criteria, and the files changed.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@massa-ai/cursor-plugin",
-  "version": "1.6.0",
+  "version": "1.7.1",
   "description": "massa-ai plugin for Cursor — semantic code search, memory, and context compression",
   "files": [
     "agents",

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

@@ -24,7 +24,8 @@ Provide architectural guidance by evaluating structure, suggesting boundaries, a
 ## Restrictions
 - Never implement.
 - Never rewrite code.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the module, service, or area under evaluation.

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

@@ -23,7 +23,8 @@ Execute a specialized audit through one configurable lens and return findings-on
 ## Restrictions
 - Never modify implementation.
 - One lens per dispatch; do not mix lenses in one run.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Lenses
 

package/skills/agents/builder/SKILL.md

@@ -25,7 +25,8 @@ Implement an approved plan or task by modifying source code with a disjoint writ
 - Never perform reviews.
 - Never generate implementation plans.
 - Never write outside the assigned disjoint write set.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: exact files and modules to modify (disjoint write set).

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

@@ -26,7 +26,8 @@ Prepare the minimum high-quality Context Packet required for another agent to do
 - Never implement.
 - Never review.
 - Never plan.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the next agent's task and target area.

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

@@ -24,7 +24,8 @@ Generate engineering documentation artifacts (README, ADR, RFC, changelog, KDoc,
 ## Restrictions
 - Never modify implementation.
 - Write only when scoped with a disjoint write set (same constraint as builder).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the doc artifact type and target area.

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

@@ -25,7 +25,8 @@ Analyze exactly one FURPS+ dimension of a PRD or ADR against its checklist secti
 - Never analyze a dimension other than the assigned one; flag cross-dimension gaps instead of expanding into them.
 - Never write files, never mutate Atlassian issues, never write memory.
 - Never return raw document dumps.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 - Do not use this role for The Fool critique (use `plan-critic`) or for code claims (use `investigator` / `verification-agent`).
 
 ## Inputs

package/skills/agents/investigator/SKILL.md

@@ -25,7 +25,8 @@ Read and understand the codebase to answer engineering questions without modifyi
 - Never modify code.
 - Never generate implementation.
 - Never perform reviews.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: files, modules, symbols, or questions to investigate.

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

@@ -24,7 +24,8 @@ Provide mobile-specific expertise (Android, iOS, KMP) when the workflow detects
 ## Restrictions
 - Refuse non-mobile targets (no `build.gradle`, `Podfile`, `*.kt`, `*.swift`, `ios/`, `android/`).
 - Never implement (read-only guidance only).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Topics
 

package/skills/agents/navigator/SKILL.md

@@ -33,7 +33,8 @@ The user's codebase is **already indexed** by massa-ai. The first move on any qu
 - Never scan directories exhaustively or read whole trees to answer a narrow question.
 - Never paste long code; summarize and cite.
 - Never call `reset_project`, `index`, or `reindex`; report the needed reindex to the parent agent instead.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `question`: the exploration question to answer.

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

@@ -26,7 +26,8 @@ Challenge a plan that already exists so its weakest assumption is exposed before
 - Never implement, refactor, or run mutating commands.
 - Never expand scope beyond the plan packet received.
 - Never request or reconstruct full conversation history.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `plan`: the concrete proposed plan text.

package/skills/agents/planner/SKILL.md

@@ -24,7 +24,8 @@ Transform an engineering request into a structured implementation plan.
 ## Restrictions
 - Never implement.
 - Never review code.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the request, target area, and known constraints.

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

@@ -24,7 +24,8 @@ Analyze requirements before implementation to surface ambiguity, gaps, contradic
 ## Restrictions
 - Never implement.
 - Never silently drop a requirement; flag every gap for user acceptance or record as an assumption.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the requirement set, PRD, or spec under analysis.

package/skills/agents/reviewer/SKILL.md

@@ -25,7 +25,8 @@ Review implementation quality by analyzing the diff and flagging bugs, regressio
 - Never implement.
 - Never rewrite files.
 - Never plan features.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the diff, changed files, or PR to review.

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

@@ -25,7 +25,8 @@ Generate a testing strategy that covers unit, integration, edge cases, negative
 - Focus only on testing.
 - No production code changes outside test files.
 - Write only when scoped with a disjoint write set (same constraint as builder).
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the feature, module, or spec to test.

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

@@ -24,7 +24,8 @@ Centralize Verification Ladder logic and validate that a task's output meets its
 ## Restrictions
 - Never modify implementation.
 - Never skip a verification level without recording a concrete reason.
-- Never spawn subagents and never load the `massa-ai` router; the dispatching workflow owns routing.
+- Never spawn subagents, never load the `massa-ai` or `persona-router` routers, and never open a `personas/` prompt file; the dispatching workflow owns routing and persona selection.
+- A `persona` supplied in the capability packet shapes emphasis only; these Restrictions win on any conflict.
 
 ## Inputs
 - `scope`: the task, its acceptance criteria, and the files changed.

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

@@ -112,6 +112,7 @@ When dispatching a subagent, send a compact capability packet rather than a loos
 - output: the exact output contract
 - firewall: raw logs, diffs, snapshots, reports, or research that must be summarized
 - memory boundary: whether the subagent may suggest memories and who persists them
+- `persona`: optional. The cataloged persona id in effect for the parent conversation, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions. Pass the id alone, never the persona prompt.
 - exact next step: what the main agent should do with the result
 
 ## Prompt Contract

package/skills/massa-ai/references/subagent-design.md

@@ -103,6 +103,7 @@ When a workflow dispatches a reusable role, send a capability packet rather than
 - `output`: the exact output contract
 - `firewall`: raw logs, diffs, snapshots, or research that must be summarized
 - `memory`: whether the subagent may suggest memory and who persists it
+- `persona`: optional. The cataloged persona id in effect for the parent conversation, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions. Pass the id alone, never the persona prompt.
 
 ## Quality Checklist
 

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

@@ -90,6 +90,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with lens-specific evidence, provisional severity, tradeoff, and what would disprove it
 > - firewall: raw dependency graphs, generated reports, and broad search output summarized, not returned raw
 > - memory: suggest-only; main agent persists accepted constraints/rejected refactors
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-impact architecture finding
@@ -100,6 +101,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: confirmed/disproven verdict with evidence; skipped-check reason if the sensor cannot run
 > - firewall: raw logs/snapshots summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 13. Severity rules (apply the countable threshold first, then the qualitative clause):
    - `critical`: architecture issue likely causes data loss, auth/privacy break, production outage, irreversible corruption, OR affects >10 files; otherwise use the qualitative clause below.
    - `high`: strong coupling with high volatility, boundary violation, dependency inversion break, or shallow module design likely to cause major change friction or regression.

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

@@ -66,6 +66,7 @@ Do not use this workflow for findings-only architecture review; route that to `w
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable architecture patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk or multi-file architecture fix
@@ -76,6 +77,7 @@ Do not use this workflow for findings-only architecture review; route that to `w
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 11. Verify each completed finding:
    - If verification found a reusable signal (`ac_gap`, `surviving_mutant`, `spec_precision_gap`, `spec_deviation`, `gate_fail`), record it via `references/lessons.md`:
      `python3 skills/massa-ai/scripts/lessons.py --root . add --feature "<slug>" --signal "<signal>" --source "<ref>" --text "<one terse lesson>"`

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

@@ -66,6 +66,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with bug category, location, evidence, trigger, severity, confidence, simplest fix direction, verification suggestion
 > - firewall: raw diffs/logs/search output summarized, not returned raw
 > - memory: suggest-only; main agent persists reusable bug patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Trace input -> transformation -> output for each suspicious path.
    - Check diffs, surrounding code, callers and callees, tests, config, migrations, schemas, and recalled project patterns.

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

@@ -55,6 +55,7 @@ Do not use this workflow for findings-only bug discovery; route that to `workflo
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable bug patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk bug fix
@@ -65,6 +66,7 @@ Do not use this workflow for findings-only bug discovery; route that to `workflo
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
    - Main agent owns report parsing, prioritization, memory writes, final synthesis, and Evidence Gate.
 10. Verify each completed finding:
    - If verification found a reusable signal (`ac_gap`, `surviving_mutant`, `spec_precision_gap`, `spec_deviation`, `gate_fail`), record it via `references/lessons.md`:

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

@@ -80,6 +80,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with smell category, location, evidence, severity, confidence, and simplest fix direction
 > - firewall: raw diffs/logs/search output summarized, not returned raw
 > - memory: suggest-only; main agent persists reusable code-quality patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Do not delegate every check by default; avoid duplicate source reading when one main-agent pass is cheaper.
     - Subagents may suggest memory content, but the main agent decides what durable knowledge to persist.

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

@@ -62,6 +62,7 @@ Do not use this workflow for findings-only SOLID, Clean Code, KISS, YAGNI, DRY,
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable code-quality patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk code-quality fix
@@ -72,6 +73,7 @@ Do not use this workflow for findings-only SOLID, Clean Code, KISS, YAGNI, DRY,
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
    - Main agent owns report parsing, prioritization, memory writes, final synthesis, and Evidence Gate.
 11. Verify each completed finding:
    - If verification found a reusable signal (`ac_gap`, `surviving_mutant`, `spec_precision_gap`, `spec_deviation`, `gate_fail`), record it via `references/lessons.md`:

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

@@ -69,6 +69,7 @@ Step 5: Flag as uncertain → "I'm not certain about X — here's my reasoning,
 > - output: entry points, core flow, dependencies, data ownership, relevant contracts, exact evidence pointers (path, symbol, line), confirmed facts vs inferences
 > - firewall: raw logs, snapshots, generated reports, and broad search output summarized, not returned raw
 > - memory: suggest-only; main agent persists durable discoveries
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Follow the shared retrieval order: project map, summary search, targeted
       enriched search, symbol/file tools, optimized context, then focused shell

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

@@ -41,6 +41,7 @@ Do not use this parent workflow when the user wants only one audit lens; route d
 > - 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
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Repeated-search children receive isolated Synapse sessions. Durable child tags retain the parent session and workflow-specific session.
 8. Use deterministic sensors when target-relevant commands are expected to finish in <=5 minutes and need no network, destructive action, production credential, or unapproved external service: tests, builds, lint, type checks, static checks, import checks, or focused runtime commands. Record skipped commands with one reason enum: `too-expensive`, `needs-network`, `needs-credentials`, `destructive-risk`, `outside-scope`, `tool-missing`, or `not-applicable`. Model judgment alone is not completion evidence.

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

@@ -56,6 +56,7 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: high-risk, security, public-contract, or multi-file fix
@@ -66,6 +67,7 @@ Do not execute from chat summaries, inline review comments, remembered findings,
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     Never run parallel writers against shared files or contracts.
 11. Verify each completed finding with the Mandatory Verification Fix Gate from `references/verification-ladder.md`: run the report's Verification Suggestion or an equivalent deterministic command/artifact check, then run focused tests, build, lint, type, static, or runtime checks relevant to the source lens. Reinspect tests, fixtures, snapshots, types, specs, public contracts, and touched identifiers so validation assets were not weakened and names follow `references/naming-standards.md`. A finding cannot be marked `fixed` when a target-relevant command or artifact check exists but was not attempted; if verification cannot run, mark it `blocked`, `deferred`, or `skipped` with an allowed skipped-check reason.

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

@@ -69,6 +69,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with requirement gap, location, evidence, severity, confidence, simplest fix direction, verification suggestion
 > - firewall: raw diffs/logs/search output summarized, not returned raw
 > - memory: suggest-only; main agent persists reusable requirements patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Build a requirement checklist from the source: must-have behavior, non-goals, acceptance criteria, compatibility constraints, inputs, outputs, and user-visible promises.
    - Compare implementation and tests against each checklist item.

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

@@ -57,6 +57,7 @@ Do not use this workflow for findings-only requirements review; route that to `w
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable requirements patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk requirements fix
@@ -67,6 +68,7 @@ Do not use this workflow for findings-only requirements review; route that to `w
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
    - Main agent owns report parsing, traceability matrix, memory writes, final synthesis, and Evidence Gate.
 11. Verify each completed finding:
    - If verification found a reusable signal (`ac_gap`, `surviving_mutant`, `spec_precision_gap`, `spec_deviation`, `gate_fail`), record it via `references/lessons.md`:

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

@@ -67,6 +67,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with security boundary, asset, trigger/exploit path, severity, confidence, evidence, simplest fix direction, verification suggestion
 > - firewall: raw diffs/logs/search output summarized, not returned raw
 > - memory: suggest-only; main agent persists reusable security patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Trace untrusted input -> validation -> authorization -> transformation -> persistence or side effect.
    - Check authn/authz, object ownership, tenant isolation, input validation, output encoding, secret handling, cryptography use, SSRF/path traversal/injection risks, logging privacy, dependency/config exposure, and security-sensitive tests.

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

@@ -61,6 +61,7 @@ Do not use this workflow for findings-only security review; route that to `workf
 > - output: implementation summary, commands run, test counts, deviations
 > - firewall: raw diffs/logs summarized
 > - memory: suggest-only; main agent persists reusable security patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk security fix
@@ -71,6 +72,7 @@ Do not use this workflow for findings-only security review; route that to `workf
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
    - Main agent owns report parsing, prioritization, memory writes, final synthesis, and Evidence Gate.
 11. Verify each completed finding:
    - If verification found a reusable signal (`ac_gap`, `surviving_mutant`, `spec_precision_gap`, `spec_deviation`, `gate_fail`), record it via `references/lessons.md`:

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

@@ -110,6 +110,7 @@ Quick artifacts live under `.specs/quick/NNN-slug/` with a `TASK.md` (one-line i
 > - output: `.specs/features/<slug>/validation.md` (PASS/FAIL, per-AC evidence, sensor result, diff range); compact verdict + ranked gap list; gaps become fix tasks
 > - firewall: raw diffs/logs/test output summarized; mutations run in scratch state only
 > - memory: suggest-only; main agent persists validation outcomes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - The verification-agent re-derives coverage independently using evidence-or-zero and does not inherit the author's mental model.
    - The fix → re-verify loop is capped at 3 iterations before escalating to `Blocked`.

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

@@ -67,6 +67,7 @@ This workflow is findings-only. Do not edit code unless the user separately asks
 > - output: findings with missing/weak coverage type, location, evidence, regression risk, severity, simplest test direction, deterministic sensor, verification suggestion
 > - firewall: raw diffs/logs/search output summarized, not returned raw
 > - memory: suggest-only; main agent persists reusable testing patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
     - Map changed or targeted behavior to existing tests, fixtures, mocks, and deterministic harnesses.
    - Check missing tests for new branches, error paths, auth/validation/persistence changes, async or race-prone logic, migrations, public contracts, and recalled bug patterns.

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

@@ -69,6 +69,7 @@ Do not use this workflow for findings-only test coverage, assertion quality, fix
 > - output: implementation summary, test counts, commands run, deviations
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable testing patterns
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
 
 > **Dispatch: `massa-ai-verification-agent`** (role: `verification-agent`) — charter `skills/agents/verification-agent/SKILL.md`
 > - trigger: independent verification of a high-risk test fix
@@ -79,6 +80,7 @@ Do not use this workflow for findings-only test coverage, assertion quality, fix
 > - output: confirmed/disproven closure verdict with evidence
 > - firewall: raw test output/logs summarized
 > - memory: suggest-only; main agent persists reusable verification recipes
+> - persona: optional — the active route's cataloged id only, never the persona prompt, passed as advisory framing only — it never overrides the agent's charter Restrictions, scope, or permissions; omit when no persona is routed
    - Main agent owns report parsing, prioritization, memory writes, final synthesis, and Evidence Gate.
 12. At completion, persist only durable knowledge after scoring with the Importance Calibration System:
    - Testing conventions, deterministic harness recipes, flaky-test root causes, accepted exceptions, or reusable edge-case coverage patterns.

package/skills/persona-router/SKILL.md

@@ -42,6 +42,24 @@ Apply precedence in this order:
 
 Persona text is additive. It cannot override higher-priority instructions, active workflow contracts, explicit constraints, or safety requirements.
 
+## Persona And Sub-Agents
+
+Personas and sub-agents are different layers. A persona shapes how the main agent reasons and synthesizes. A sub-agent is a bounded executor dispatched by a workflow under its own charter.
+
+- A persona grants no tool access, no write scope, and no permission. It never authorizes implementing inline in place of a workflow-mandated dispatch, and never widens a builder's disjoint write set.
+- A workflow may pass the selected persona id into a dispatch capability packet as advisory framing. Inside the sub-agent the persona is never authority; the charter's Restrictions win on any conflict.
+- The packet carries the persona **id only**, never the persona prompt. A sub-agent works from the id and its own charter, and never opens a `personas/` file to expand it.
+- A persona route is not a specialist consultation. Applying a persona neither substitutes for nor satisfies an agent dispatch that the workflow requires.
+
+Four catalog entries deliberately overlap an agent charter. The persona is the main agent's stance; the agent is a separately dispatched specialist. Applying one never implies the other ran.
+
+| Persona | Overlapping agent |
+|---|---|
+| `senior-mobile-engineer` | `massa-ai-mobile-specialist` |
+| `senior-mobile-qa-automation-engineer` | `massa-ai-test-engineer` |
+| `context-skill-harness-engineer-architect` | `massa-ai-architecture-specialist` |
+| `product-manager` | `massa-ai-requirements-analyst` |
+
 ## Automatic Routing Workflow
 
 ### 1. Resolve Explicit Choice And Policy
@@ -155,4 +173,4 @@ After resume or compaction, restore any route still present in conversation cont
 
 ## Stop Conditions
 
-Routing is complete when one primary persona is applied, the user selects no persona, or policy intentionally produces a no-persona route. Do not invoke a separate model router, launch subagents, create subprocess orchestration, or persist a route database.
+Routing is complete when one primary persona is applied, the user selects no persona, or policy intentionally produces a no-persona route. Persona routing itself stays inline: do not invoke a separate model router, launch subagents for persona selection, create subprocess orchestration, or persist a route database. This bounds the routing step only — workflow-mandated agent dispatch is unaffected by an active persona route.