[Feat] Introduce exploration modes, fast routes, skill detection

.github/plugin/marketplace.json

@@ -365,7 +365,7 @@
       "name": "gem-team",
       "source": "gem-team",
       "description": "Self-Learning Multi-agent orchestration framework for spec-driven development and automated verification.",
-      "version": "1.61.0"
+      "version": "1.64.0"
     },
     {
       "name": "git-ape",

agents/gem-browser-tester.agent.md

@@ -35,7 +35,7 @@ Execute E2E/flow tests, verify UI/UX, accessibility, visual regression. Never im
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -93,11 +93,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-code-simplifier.agent.md

@@ -35,7 +35,7 @@ Remove dead code, reduce complexity, consolidate duplicates, improve naming. Nev
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -103,11 +103,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-critic.agent.md

@@ -32,7 +32,7 @@ Challenge assumptions, find edge cases, identify over-engineering, spot logic ga
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -92,11 +92,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-debugger.agent.md

@@ -37,7 +37,7 @@ Trace root causes, analyze stacks, bisect regressions, reproduce errors. Structu
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -101,11 +101,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-designer-mobile.agent.md

@@ -34,7 +34,7 @@ Design mobile UI with HIG (iOS) and Material 3 (Android); handle safe areas, tou
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -191,11 +191,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-designer.agent.md

@@ -34,7 +34,7 @@ Create layouts, themes, color schemes, design systems; validate hierarchy, respo
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -153,10 +153,13 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-devops.agent.md

@@ -36,7 +36,7 @@ Deploy infrastructure, manage CI/CD, configure containers, ensure idempotency. N
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -150,11 +150,14 @@ Return ONLY valid JSON. CRITICAL: Omit nulls, empty arrays, zero values.
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.

agents/gem-documentation-writer.agent.md

@@ -34,7 +34,7 @@ Write technical docs, generate diagrams, maintain code-docs parity, maintain `AG
 
 ## Workflow
 
-Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
+IMPORTANT: Batch/join dependency-free steps; serialize only true dependencies while still covering every listed concern.
 
 - Start with `context_envelope_snapshot` as active execution context:
   - Use `research_digest.relevant_files` as the initial file shortlist.
@@ -152,11 +152,14 @@ changes:
 
 ## Rules
 
+IMPORTANT: These rules are mandatory for every request and apply across all workflow phases.
+
 ### Execution
 
 - Tool Execution priority: native tools → workspace tasks → scripts → raw CLI.
-- Batch by default: Plan the action graph first, then execute all independent tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively, but serialize calls that depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
-- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set.
+- Batch by default: Plan the action graph first, then execute all independent workflow steps and tool calls in the same turn/message. This applies to reads, searches, greps, lists, inspections, metadata queries, writes, edits, patches, tests, and commands. Parallelize aggressively; serialize only when calls depend on prior results, mutate the same file/resource, require validation, or may create conflicts.
+- Do not drip-feed tool calls: collect likely-needed reads/searches/inspections upfront, batch them, then continue from the combined results.
+- Discover broadly, narrow early with OR regexes/multi-globs/include/exclude filters, then parallel/ batch read the full relevant file set. Prefer one broad discovery pass over repeated narrow search/read loops.
 - Execute autonomously; ask only for true blockers.
 - 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.