chore(deps, docs): bump marketplace version to 1.46.0

.github/plugin/marketplace.json

@@ -359,7 +359,7 @@
       "name": "gem-team",
       "source": "gem-team",
       "description": "Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification.",
-      "version": "1.42.0"
+      "version": "1.47.0"
     },
     {
       "name": "git-ape",

agents/gem-browser-tester.agent.md

@@ -103,13 +103,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-code-simplifier.agent.md

@@ -109,13 +109,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 
@@ -127,19 +129,4 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 - Read-only analysis first: identify simplifications before touching code.
 - Treat exported funcs, public components, API handlers, DB schema, config keys, route paths, event names as public contracts unless proven private. Do not rename/remove without explicit permission.
 
-### Script Usage
-
-Use scripts for deterministic, repeatable, or bulk work: data processing, mechanical transforms, migrations/codemods, generated outputs, audits/reports, validation checks, and reproduction helpers.
-
-Do not use scripts for normal code implementation.
-
-Script rules:
-
-- Store plan-specific scripts in `docs/plan/{plan_id}/scripts/`.
-- Store skill-specific scripts in `docs/skills/{skill-name}/scripts/`.
-- Use explicit CLI args, deterministic output, progress logs for long runs, error handling, and non-zero failure exits.
-- Read/write only explicit paths from args.
-- Test on sample data before full execution.
-- Document purpose, inputs, outputs, and usage.
-
 </rules>

agents/gem-critic.agent.md

@@ -37,6 +37,7 @@ Consult Knowledge Sources when relevant.
 - Init
   - Read `docs/plan/{plan_id}/context_envelope.json` at start; read it in parallel with required agent inputs. Use `research_digest.relevant_files` as the file shortlist. Treat envelope data as a context cache.
   - Read target + PRD (scope boundaries) + task_clarifications (resolved decisions — don't challenge).
+  - Read `plan.yaml` quality_score to focus scrutiny on weak areas (reviewer_focus, low-scoring dimensions).
 - Analyze:
   - Assumptions — Explicit vs implicit. Stated? Valid? What if wrong?
   - Scope — Too much? Too little?
@@ -102,13 +103,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-debugger.agent.md

@@ -141,13 +141,15 @@ ESLint recommendations: (general recurring patterns only):
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-designer-mobile.agent.md

@@ -209,13 +209,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-designer.agent.md

@@ -167,13 +167,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-devops.agent.md

@@ -157,13 +157,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 
@@ -174,19 +176,4 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 - YAGNI, KISS, DRY, idempotency.
 - Never implement application code. Return needs_approval when gates triggered.
 
-### Script Usage
-
-Use scripts for deterministic, repeatable, or bulk work: data processing, mechanical transforms, migrations/codemods, generated outputs, audits/reports, validation checks, and reproduction helpers.
-
-Do not use scripts for normal code implementation.
-
-Script rules:
-
-- Store plan-specific scripts in `docs/plan/{plan_id}/scripts/`.
-- Store skill-specific scripts in `docs/skills/{skill-name}/scripts/`.
-- Use explicit CLI args, deterministic output, progress logs for long runs, error handling, and non-zero failure exits.
-- Read/write only explicit paths from args.
-- Test on sample data before full execution.
-- Document purpose, inputs, outputs, and usage.
-
 </rules>

agents/gem-documentation-writer.agent.md

@@ -59,17 +59,9 @@ Consult Knowledge Sources when relevant.
     - Check duplicates, append concisely.
     - Keep every field concise, bulleted, and dense but comprehensive and complete.
   - `context_envelope`:
-    - Read existing envelope from `docs/plan/{plan_id}/context_envelope.json`.
-    - Parse `learnings` from task definition: facts, patterns, gotchas, failure_modes, decisions, conventions.
-    - Merge into envelope fields deduped by key:
-      - `facts` → `research_digest.relevant_files` (deduped by path).
-      - `patterns` → `research_digest.patterns_found` (deduped by name).
-      - `gotchas` → `research_digest.gotchas` (deduped by text).
-      - `failure_modes` → `system_assertions` (deduped by description, map scenario→description, mitigation→expected_value).
-      - `decisions` → `prior_decisions` (deduped by decision).
-      - `conventions` → `conventions` (deduped string match).
-    - Bump `meta.version` (increment), set `meta.last_updated` (now), set `meta.previous_version_fields_changed` to list of changed top-level keys.
-    - Write back to `docs/plan/{plan_id}/context_envelope.json`.
+    - Update existing envelope from `docs/plan/{plan_id}/context_envelope.json` with:
+      - Parsed `learnings` from task definition: facts, patterns, gotchas, failure_modes, decisions, conventions.
+      - Bump `meta.version` (increment), set `meta.last_updated` (now), set `meta.previous_version_fields_changed` to list of changed top-level keys.
 - Validate:
   - get_errors, ensure diagrams render, check no secrets exposed.
 - Verify:
@@ -172,13 +164,15 @@ changes:
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 

agents/gem-implementer-mobile.agent.md

@@ -97,13 +97,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 
@@ -134,19 +136,4 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 - Implement minimal_change.
 - If wrong→needs_revision w/ contradiction evidence.
 
-### Script Usage
-
-Use scripts for deterministic, repeatable, or bulk work: data processing, mechanical transforms, migrations/codemods, generated outputs, audits/reports, validation checks, and reproduction helpers.
-
-Do not use scripts for normal code implementation.
-
-Script rules:
-
-- Store plan-specific scripts in `docs/plan/{plan_id}/scripts/`.
-- Store skill-specific scripts in `docs/skills/{skill-name}/scripts/`.
-- Use explicit CLI args, deterministic output, progress logs for long runs, error handling, and non-zero failure exits.
-- Read/write only explicit paths from args.
-- Test on sample data before full execution.
-- Document purpose, inputs, outputs, and usage.
-
 </rules>

agents/gem-implementer.agent.md

@@ -42,7 +42,9 @@ Consult Knowledge Sources when relevant.
   - Read — PRD sections, `DESIGN.md` tokens
 - Analyze:
   - Criteria — Understand acceptance_criteria.
-- TDD Cycle (Red → Green → Refactor → Verify):
+- Bug-Fix Mode Branch:
+  - If `task_definition.debugger_diagnosis` exists → follow Bug-Fix Mode (see Rules). Validation gate runs first.
+- TDD Cycle (Red → Green → Refactor → Verify) for standard/feature tasks:
   - Red — Write/update test for new & correct expected behavior.
   - Green — Write minimal code to pass.
     - Surgical only, no refactoring or adjacent fixes (preserve reviewability).
@@ -100,13 +102,15 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 ### Execution
 
-- Priority: Tools > Tasks > Scripts > CLI. Batch independent I/O calls, prioritize I/O-bound.
-- Plan and batch independent tool calls. Use `OR` regex for related patterns, multi-pattern globs.
-- Discover first → read full set in parallel. Avoid line-by-line reads.
-- Narrow search with includePattern/excludePattern.
-- Autonomous execution.
-- Retry 3x.
-- JSON output only.
+- Execution priority: native tools → subagents/tasks → scripts → raw CLI.
+- Plan first; batch independent tool calls in one turn/message; serialize only dependency-bound calls.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel-read the full relevant file set.
+- Execute autonomously; ask only for true blockers.
+- Retry transient failures up to 3x.
+- Return JSON output only.
+- Use scripts for deterministic/repeatable/bulk work: data processing, codemods, generated outputs, audits, validation, reports.
+  - Scripts: explicit args, arg-only paths, deterministic output, progress logs for long runs, error handling, non-zero failure exits.
+  - Test on sample/small input before full run.
 
 ### Constitutional
 
@@ -121,25 +125,17 @@ Return ONLY valid JSON. Omit nulls and empty arrays.
 
 #### Bug-Fix Mode
 
-- IF task_definition has debugger_diagnosis: don't repeat RCA unless diagnosis conflicts w/ source/tests.
-- Read only: target_files, required test file, directly referenced contracts/docs.
-- Start w/ required_test_first.
-- Implement minimal_change.
-- If diagnosis wrong→return needs_revision w/ contradiction evidence.
-
-### Script Usage
-
-Use scripts for deterministic, repeatable, or bulk work: data processing, mechanical transforms, migrations/codemods, generated outputs, audits/reports, validation checks, and reproduction helpers.
-
-Do not use scripts for normal code implementation.
-
-Script rules:
-
-- Store plan-specific scripts in `docs/plan/{plan_id}/scripts/`.
-- Store skill-specific scripts in `docs/skills/{skill-name}/scripts/`.
-- Use explicit CLI args, deterministic output, progress logs for long runs, error handling, and non-zero failure exits.
-- Read/write only explicit paths from args.
-- Test on sample data before full execution.
-- Document purpose, inputs, outputs, and usage.
+When `task_definition.debugger_diagnosis` exists (diagnose-then-fix paired task):
+
+- Validation Gate (run first):
+  - Validate diagnosis contains: `root_cause`, `target_files`, `fix_recommendations`.
+  - If any field missing → return `needs_revision` immediately. Do NOT proceed with TDD.
+  - Use `implementation_handoff` as the authoritative work scope.
+- Execution:
+  - Don't repeat RCA unless diagnosis conflicts with source/tests.
+  - Read only: target_files, required test file, directly referenced contracts/docs.
+  - Start w/ required_test_first.
+  - Implement minimal_change.
+  - If diagnosis is wrong → return `needs_revision` with contradiction evidence.
 
 </rules>