@vpxa/kb 0.1.17 → 0.1.19

package/scaffold/definitions/bodies.mjs

@@ -74,7 +74,15 @@ For each batch: Implement (parallel) → Code Review → Architecture Review (if
 3. **Parallel when independent** — never serialize what can run simultaneously
 4. **Route correctly** — brainstorming for design, decision protocol for technical choices
 5. **Never proceed without user approval** at mandatory stops
-6. **Max 2 retries** then escalate`,
+6. **Max 2 retries** then escalate
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| \`brainstorming\` | Before any creative/design work (Phase 0 Design Gate) |
+| \`session-handoff\` | When context window is filling up, session ending, or major milestone completed |
+| \`lesson-learned\` | After completing work — extract engineering principles and persist via \`remember\` |`,
 
   Planner: `**Read \`AGENTS.md\`** in the workspace root for project conventions and KB protocol.
 
@@ -110,7 +118,17 @@ For each batch: Implement (parallel) → Code Review → Architecture Review (if
 **Open Questions** / **Risks**
 \`\`\`
 
-**🛑 MANDATORY STOP** — Wait for user approval before any implementation.`,
+**🛑 MANDATORY STOP** — Wait for user approval before any implementation.
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| \`brainstorming\` | Before planning any new feature, component, or behavior change — use Visual Companion for architecture mockups |
+| \`requirements-clarity\` | When requirements are vague or complex (>2 days) — score 0-100 before committing to a plan |
+| \`c4-architecture\` | When the plan involves architectural changes — generate C4 diagrams |
+| \`adr-skill\` | When the plan involves non-trivial technical decisions — create executable ADRs |
+| \`session-handoff\` | When context window is filling up, planning session ending, or major milestone completed |`,
 
   Implementer: `**Read \`AGENTS.md\`** in the workspace root for project conventions and KB protocol.
 
@@ -191,7 +209,13 @@ For each batch: Implement (parallel) → Code Review → Architecture Review (if
 - **Tests must pass at every step** — Never break behavior
 - **Smaller is better** — Prefer many small refactors over one big one
 - **Follow existing patterns** — Consolidate toward established conventions
-- **Don't refactor what isn't asked** — Scope discipline`,
+- **Don't refactor what isn't asked** — Scope discipline
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| \`lesson-learned\` | After completing a refactor — extract principles from the before/after diff |`,
 
   Security: `**Read \`AGENTS.md\`** in the workspace root for project conventions and KB protocol.
 
@@ -248,7 +272,14 @@ For each batch: Implement (parallel) → Code Review → Architecture Review (if
 
 - **Accuracy over completeness** — Better to be correct and concise than thorough and wrong
 - **Examples always** — Every API docs section needs a code example
-- **Keep it current** — Update docs with every code change`,
+- **Keep it current** — Update docs with every code change
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| \`c4-architecture\` | When documenting system architecture — generate C4 Mermaid diagrams |
+| \`adr-skill\` | When documenting architecture decisions — create or update ADRs |`,
 
   Explorer: `**Read \`AGENTS.md\`** in the workspace root for project conventions and KB protocol.
 

package/scaffold/definitions/tools.mjs

@@ -6,6 +6,10 @@
  *          maps these to its own format (e.g., Copilot tool identifiers).
  *
  * When KB adds/removes a tool, update `kb` here — all agents pick it up.
+ *
+ * NOTE: The copilot adapter currently uses `knowledge-base/*` wildcard instead
+ * of listing individual tools. This array is kept as a reference and for future
+ * adapters that may need explicit tool lists (e.g., claude-code).
  */
 
 export const KB_TOOLS = [

package/scaffold/general/agents/Architect-Reviewer-Alpha.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Primary architecture reviewer'
 argument-hint: Files, PR, or subsystem to architecture-review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 

package/scaffold/general/agents/Architect-Reviewer-Beta.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Architecture reviewer variant — different LLM perspective for dual review'
 argument-hint: Files, PR, or subsystem to architecture-review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 

package/scaffold/general/agents/Code-Reviewer-Alpha.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Primary code reviewer'
 argument-hint: File path, PR, or code to review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 

package/scaffold/general/agents/Code-Reviewer-Beta.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Code reviewer variant — different LLM perspective for dual review'
 argument-hint: File path, PR, or code to review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 

package/scaffold/general/agents/Debugger.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Expert debugger that diagnoses issues, traces errors, and provides solutions'
 argument-hint: Error message, stack trace, or description of issue
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalSelection, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalSelection, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 

package/scaffold/general/agents/Documenter.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Documentation specialist that creates and maintains comprehensive project documentation'
 argument-hint: Component, API, feature, or area to document
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 
@@ -11,13 +11,6 @@ You are the **Documenter**, documentation specialist that creates and maintains
 
 **Read `AGENTS.md`** in the workspace root for project conventions and KB protocol.
 
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `c4-architecture` | When documenting system architecture — generate C4 Mermaid diagrams |
-| `adr-skill` | When documenting architecture decisions — create or update ADRs |
-
 ## Documentation Protocol
 
 1. **KB Recall** — Search for existing docs, conventions, architecture decisions
@@ -40,3 +33,10 @@ You are the **Documenter**, documentation specialist that creates and maintains
 - **Accuracy over completeness** — Better to be correct and concise than thorough and wrong
 - **Examples always** — Every API docs section needs a code example
 - **Keep it current** — Update docs with every code change
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| `c4-architecture` | When documenting system architecture — generate C4 Mermaid diagrams |
+| `adr-skill` | When documenting architecture decisions — create or update ADRs |

package/scaffold/general/agents/Explorer.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Rapid codebase exploration to find files, usages, dependencies, and structural context'
 argument-hint: Find files, usages, and context related to: {topic or goal}
-tools: [read/problems, read/readFile, search/changes, search/codebase, search/usages, search/fileSearch, search/listDirectory, search/textSearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [read/problems, read/readFile, search/changes, search/codebase, search/usages, search/fileSearch, search/listDirectory, search/textSearch, knowledge-base/*]
 model: Gemini 3 Flash (Preview) (copilot)
 ---
 

package/scaffold/general/agents/Frontend.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'UI/UX specialist for React, styling, responsive design, and frontend implementation'
 argument-hint: UI component, styling task, or frontend feature
-tools: [execute/createAndRunTask, execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, todo, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/createAndRunTask, execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, todo, knowledge-base/*]
 model: Gemini 3.1 Pro (Preview) (copilot)
 ---
 

package/scaffold/general/agents/Implementer.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Persistent implementation agent that writes code following TDD practices until all tasks are complete'
 argument-hint: Implementation task, feature, or phase from plan
-tools: [execute/createAndRunTask, execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, todo, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/createAndRunTask, execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, todo, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 

package/scaffold/general/agents/Orchestrator.agent.md

@@ -1,6 +1,6 @@
 ---
 description: 'Master conductor that orchestrates the full development lifecycle: Planning → Implementation → Review → Recovery → Commit'
-tools: [vscode/memory, vscode/runCommand, vscode/switchAgent, execute/killTerminal, execute/createAndRunTask, execute/runInTerminal, read/terminalSelection, read/terminalLastCommand, read/problems, read/readFile, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, todo, search/searchResults, search/textSearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [vscode/memory, vscode/runCommand, vscode/switchAgent, execute/killTerminal, execute/createAndRunTask, execute/runInTerminal, read/terminalSelection, read/terminalLastCommand, read/problems, read/readFile, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, todo, search/searchResults, search/textSearch, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 
@@ -15,14 +15,6 @@ You are the **Orchestrator**, master conductor that orchestrates the full develo
 4. **Read _shared/forge-protocol.md** for the quality gate protocol.
 5. **Use templates/adr-template.md** when writing Architecture Decision Records.
 
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `brainstorming` | Before any creative/design work (Phase 0 Design Gate) |
-| `session-handoff` | When context window is filling up, session ending, or major milestone completed |
-| `lesson-learned` | After completing work — extract engineering principles and persist via `remember` |
-
 ## Agent Arsenal
 
 | Agent | Purpose | Model | Category |
@@ -102,3 +94,11 @@ For each batch: Implement (parallel) → Code Review → Architecture Review (if
 4. **Route correctly** — brainstorming for design, decision protocol for technical choices
 5. **Never proceed without user approval** at mandatory stops
 6. **Max 2 retries** then escalate
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| `brainstorming` | Before any creative/design work (Phase 0 Design Gate) |
+| `session-handoff` | When context window is filling up, session ending, or major milestone completed |
+| `lesson-learned` | After completing work — extract engineering principles and persist via `remember` |

package/scaffold/general/agents/Planner.agent.md

@@ -1,6 +1,6 @@
 ---
 description: 'Autonomous planner that researches codebases and writes comprehensive TDD implementation plans'
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, todo, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/createFile, edit/editFiles, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, todo, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 
@@ -12,16 +12,6 @@ You are the **Planner**, autonomous planner that researches codebases and writes
 
 **Read _shared/code-agent-base.md NOW** — it contains KB recall, FORGE, and handoff protocols.
 
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `brainstorming` | Before planning any new feature, component, or behavior change — use Visual Companion for architecture mockups |
-| `requirements-clarity` | When requirements are vague or complex (>2 days) — score 0-100 before committing to a plan |
-| `c4-architecture` | When the plan involves architectural changes — generate C4 diagrams |
-| `adr-skill` | When the plan involves non-trivial technical decisions — create executable ADRs |
-| `session-handoff` | When context window is filling up, planning session ending, or major milestone completed |
-
 ## Planning Workflow
 
 1. **KB Recall** — Search for past plans, architecture decisions, known patterns
@@ -53,3 +43,13 @@ You are the **Planner**, autonomous planner that researches codebases and writes
 ```
 
 **🛑 MANDATORY STOP** — Wait for user approval before any implementation.
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| `brainstorming` | Before planning any new feature, component, or behavior change — use Visual Companion for architecture mockups |
+| `requirements-clarity` | When requirements are vague or complex (>2 days) — score 0-100 before committing to a plan |
+| `c4-architecture` | When the plan involves architectural changes — generate C4 diagrams |
+| `adr-skill` | When the plan involves non-trivial technical decisions — create executable ADRs |
+| `session-handoff` | When context window is filling up, planning session ending, or major milestone completed |

package/scaffold/general/agents/Refactor.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Code refactoring specialist that improves structure, readability, and maintainability'
 argument-hint: Code, component, or pattern to refactor
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/editFiles, search/changes, search/codebase, search/usages, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, edit/editFiles, search/changes, search/codebase, search/usages, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 
@@ -13,12 +13,6 @@ You are the **Refactor**, code refactoring specialist that improves structure, r
 
 **Read _shared/code-agent-base.md NOW** — it contains KB recall, FORGE, and handoff protocols.
 
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `lesson-learned` | After completing a refactor — extract principles from the before/after diff |
-
 ## Refactoring Protocol
 
 1. **KB Recall** — Search for established patterns and conventions
@@ -34,3 +28,9 @@ You are the **Refactor**, code refactoring specialist that improves structure, r
 - **Smaller is better** — Prefer many small refactors over one big one
 - **Follow existing patterns** — Consolidate toward established conventions
 - **Don't refactor what isn't asked** — Scope discipline
+
+## Skills (load on demand)
+
+| Skill | When to load |
+|-------|--------------|
+| `lesson-learned` | After completing a refactor — extract principles from the before/after diff |

package/scaffold/general/agents/Researcher-Alpha.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Primary deep research agent — also serves as default Researcher'
 argument-hint: Research question, problem statement, or subsystem to investigate
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 

package/scaffold/general/agents/Researcher-Beta.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Research variant for multi-model decision protocol — different LLM perspective'
 argument-hint: Research question, problem statement, or subsystem to investigate
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Claude Sonnet 4.6 (copilot)
 ---
 

package/scaffold/general/agents/Researcher-Delta.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Research variant for multi-model decision protocol — different LLM perspective'
 argument-hint: Research question, problem statement, or subsystem to investigate
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Gemini 3.1 Pro (Preview) (copilot)
 ---
 

package/scaffold/general/agents/Researcher-Gamma.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Research variant for multi-model decision protocol — different LLM perspective'
 argument-hint: Research question, problem statement, or subsystem to investigate
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: GPT-5.4 (copilot)
 ---
 

package/scaffold/general/agents/Security.agent.md

@@ -1,7 +1,7 @@
 ---
 description: 'Security specialist that analyzes code for vulnerabilities and compliance'
 argument-hint: Code, feature, or component to security review
-tools: [execute/runInTerminal, read/problems, read/readFile, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
+tools: [execute/runInTerminal, read/problems, read/readFile, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/*]
 model: Claude Opus 4.6 (copilot)
 ---
 

package/scaffold/general/agents/_shared/code-agent-base.md

@@ -40,24 +40,6 @@ You may be invoked in two modes:
 
 ---
 
-## Tool Preference (BLOCKING — Use KB Tools Over Native Tools)
-
-KB tools return **AST-analyzed structured data** — 10x fewer tokens than raw file reads. **Always prefer KB tools:**
-
-| Instead of... | Use KB Tool |
-|---------------|-------------|
-| `read_file` (full file) | `file_summary` — exports, imports, call edges, 10x fewer tokens |
-| `read_file` (section) | `compact({ path, query })` — server-side extract, 5-20x reduction |
-| `grep_search` / `textSearch` | `search` — semantic + keyword hybrid |
-| `grep_search` for symbol | `symbol` — definition + references with scope context |
-| Multiple `read_file` | `digest` — compressed multi-source summary |
-| Manual code tracing | `trace` — AST call-graph traversal |
-| Line counting | `measure` — lines, complexity, cognitive complexity |
-
-**Only use `read_file` as a last resort** when you need exact line content for editing.
-
----
-
 ## KB Learn (After Completing Work)
 
 Before returning your handoff, persist discoveries to KB:

package/scaffold/generate.mjs

@@ -10,7 +10,11 @@
  * Architecture:
  *   definitions/  — IDE-agnostic data (agents, models, tools, prompts, hooks, plugins)
  *   adapters/     — IDE-specific generators (copilot, claude-code)
- *   {ide}/        — Generated output (what `kb init` copies into workspaces)
+ *   general/      — Generated output (agents, prompts) — `kb init` copies from here
+ *
+ * The copilot adapter writes directly to general/ since all IDEs currently
+ * consume the same VS Code-format .agent.md files. When a future adapter
+ * needs a different format, it gets its own output directory.
  */
 
 import { existsSync, mkdirSync, rmSync, writeFileSync } from 'node:fs';
@@ -22,7 +26,7 @@ import { generateCopilot } from './adapters/copilot.mjs';
 const __dirname = dirname(fileURLToPath(import.meta.url));
 
 const ADAPTERS = {
-  copilot: { generate: generateCopilot, outDir: 'copilot' },
+  copilot: { generate: generateCopilot, outDir: 'general' },
   'claude-code': { generate: generateClaudeCode, outDir: 'claude-code' },
 };
 
@@ -45,9 +49,13 @@ for (const ide of idesToRun) {
 
   const outDir = resolve(__dirname, adapter.outDir);
 
-  // Clean output directory for a fresh generation
-  if (existsSync(outDir)) {
-    rmSync(outDir, { recursive: true });
+  // Clean only the subdirectories the generator manages (agents/, prompts/).
+  // This avoids wiping hand-maintained files if they coexist in general/.
+  for (const subdir of ['agents', 'prompts']) {
+    const sub = resolve(outDir, subdir);
+    if (existsSync(sub)) {
+      rmSync(sub, { recursive: true });
+    }
   }
 
   console.log(`\n─── Generating ${ide} scaffold ───`);

package/packages/cli/dist/commands/init/global.d.ts

@@ -1,34 +0,0 @@
-//#region packages/cli/src/commands/init/global.d.ts
-/**
- * `kb init --global` — configure KB as a user-level MCP server.
- *
- * Auto-detects all installed IDEs, writes user-level mcp.json for each,
- * installs skills to a global location, and creates the global data store.
- */
-/** Represents a user-level IDE config location. */
-interface UserLevelIdePath {
-  ide: string;
-  configDir: string;
-  mcpConfigPath: string;
-}
-/**
- * Detect all installed IDEs by checking if their user-level config directory exists.
- */
-declare function detectInstalledIdes(): UserLevelIdePath[];
-/**
- * Write or merge the KB server entry into a user-level mcp.json.
- * Preserves all existing non-KB entries. Backs up existing file before writing.
- */
-declare function writeUserLevelMcpConfig(idePath: UserLevelIdePath, serverName: string, force?: boolean): void;
-/**
- * Install skills to the global user-level directory (~/.kb-data/skills/).
- */
-declare function installGlobalSkills(pkgRoot: string): void;
-/**
- * Main orchestrator for `kb init --global`.
- */
-declare function initGlobal(options: {
-  force: boolean;
-}): Promise<void>;
-//#endregion
-export { UserLevelIdePath, detectInstalledIdes, initGlobal, installGlobalSkills, writeUserLevelMcpConfig };

package/packages/cli/dist/commands/init/global.js

@@ -1,5 +0,0 @@
-import{MCP_SERVER_ENTRY as e,SERVER_NAME as t,SKILL_NAMES as n}from"./constants.js";import{copyDirectoryRecursive as r}from"./scaffold.js";import{existsSync as i,mkdirSync as a,readFileSync as o,writeFileSync as s}from"node:fs";import{dirname as c,resolve as l}from"node:path";import{fileURLToPath as u}from"node:url";import{getGlobalDataDir as d,saveRegistry as f}from"../../../../core/dist/index.js";import{homedir as p}from"node:os";function m(){let e=p(),t=process.platform,n=[];if(t===`win32`){let t=process.env.APPDATA??l(e,`AppData`,`Roaming`);n.push({ide:`VS Code`,configDir:l(t,`Code`,`User`),mcpConfigPath:l(t,`Code`,`User`,`mcp.json`)},{ide:`VS Code Insiders`,configDir:l(t,`Code - Insiders`,`User`),mcpConfigPath:l(t,`Code - Insiders`,`User`,`mcp.json`)},{ide:`VSCodium`,configDir:l(t,`VSCodium`,`User`),mcpConfigPath:l(t,`VSCodium`,`User`,`mcp.json`)},{ide:`Cursor`,configDir:l(t,`Cursor`,`User`),mcpConfigPath:l(t,`Cursor`,`User`,`mcp.json`)},{ide:`Cursor Nightly`,configDir:l(t,`Cursor Nightly`,`User`),mcpConfigPath:l(t,`Cursor Nightly`,`User`,`mcp.json`)},{ide:`Windsurf`,configDir:l(t,`Windsurf`,`User`),mcpConfigPath:l(t,`Windsurf`,`User`,`mcp.json`)})}else if(t===`darwin`){let t=l(e,`Library`,`Application Support`);n.push({ide:`VS Code`,configDir:l(t,`Code`,`User`),mcpConfigPath:l(t,`Code`,`User`,`mcp.json`)},{ide:`VS Code Insiders`,configDir:l(t,`Code - Insiders`,`User`),mcpConfigPath:l(t,`Code - Insiders`,`User`,`mcp.json`)},{ide:`VSCodium`,configDir:l(t,`VSCodium`,`User`),mcpConfigPath:l(t,`VSCodium`,`User`,`mcp.json`)},{ide:`Cursor`,configDir:l(t,`Cursor`,`User`),mcpConfigPath:l(t,`Cursor`,`User`,`mcp.json`)},{ide:`Cursor Nightly`,configDir:l(t,`Cursor Nightly`,`User`),mcpConfigPath:l(t,`Cursor Nightly`,`User`,`mcp.json`)},{ide:`Windsurf`,configDir:l(t,`Windsurf`,`User`),mcpConfigPath:l(t,`Windsurf`,`User`,`mcp.json`)})}else{let t=process.env.XDG_CONFIG_HOME??l(e,`.config`);n.push({ide:`VS Code`,configDir:l(t,`Code`,`User`),mcpConfigPath:l(t,`Code`,`User`,`mcp.json`)},{ide:`VS Code Insiders`,configDir:l(t,`Code - Insiders`,`User`),mcpConfigPath:l(t,`Code - Insiders`,`User`,`mcp.json`)},{ide:`VSCodium`,configDir:l(t,`VSCodium`,`User`),mcpConfigPath:l(t,`VSCodium`,`User`,`mcp.json`)},{ide:`Cursor`,configDir:l(t,`Cursor`,`User`),mcpConfigPath:l(t,`Cursor`,`User`,`mcp.json`)},{ide:`Cursor Nightly`,configDir:l(t,`Cursor Nightly`,`User`),mcpConfigPath:l(t,`Cursor Nightly`,`User`,`mcp.json`)},{ide:`Windsurf`,configDir:l(t,`Windsurf`,`User`),mcpConfigPath:l(t,`Windsurf`,`User`,`mcp.json`)})}return n.push({ide:`Claude Code`,configDir:l(e,`.claude`),mcpConfigPath:l(e,`.claude`,`mcp.json`)}),n.filter(e=>i(e.configDir))}function h(t,n,r=!1){let{mcpConfigPath:c,configDir:l}=t,u={...e},d={};if(i(c)){try{let e=o(c,`utf-8`);d=JSON.parse(e)}catch{let e=`${c}.bak`;s(e,o(c,`utf-8`),`utf-8`),console.log(`  Backed up invalid ${c} to ${e}`),d={}}if((d.servers??d.mcpServers??{})[n]&&!r){console.log(`  ${t.ide}: ${n} already configured (use --force to update)`);return}}let f=new Set([`VS Code`,`VS Code Insiders`,`VSCodium`,`Windsurf`]).has(t.ide)?`servers`:`mcpServers`,p=d[f]??{};p[n]=u,d[f]=p,a(l,{recursive:!0}),s(c,`${JSON.stringify(d,null,2)}\n`,`utf-8`),console.log(`  ${t.ide}: configured ${n} in ${c}`)}function g(e){let t=l(d(),`skills`);for(let a of n){let n=l(e,`skills`,a);i(n)&&r(n,l(t,a),`skills/${a}`,!0)}console.log(`  Installed ${n.length} skills to ${t}`)}async function _(e){let n=t;console.log(`Initializing global KB installation...
-`);let r=d();a(r,{recursive:!0}),console.log(`  Global data store: ${r}`),f({version:1,workspaces:{}}),console.log(`  Created registry.json`);let i=m();if(i.length===0)console.log(`
-  No supported IDEs detected. You can manually add the MCP server config.`);else{console.log(`\n  Detected ${i.length} IDE(s):`);for(let t of i)h(t,n,e.force)}g(l(c(u(import.meta.url)),`..`,`..`,`..`,`..`,`..`)),console.log(`
-Global KB installation complete!`),console.log(`
-Next steps:`),console.log(`  1. Open any workspace in your IDE`),console.log(`  2. The KB server will auto-start and index the workspace`),console.log("  3. Run `kb init` in a workspace to add AGENTS.md and instructions")}export{m as detectInstalledIdes,_ as initGlobal,g as installGlobalSkills,h as writeUserLevelMcpConfig};

package/scaffold/copilot/agents/Architect-Reviewer-Alpha.agent.md

@@ -1,21 +0,0 @@
----
-description: 'Primary architecture reviewer'
-argument-hint: Files, PR, or subsystem to architecture-review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
-model: GPT-5.4 (copilot)
----
-
-# Architect-Reviewer-Alpha - The Structural Guardian
-
-You are **Architect-Reviewer-Alpha**, the primary Architect-Reviewer agent.
-
-You are **not** the Code-Reviewer agent. Code-Reviewer handles correctness, testing, security, and code quality. You handle the big picture: service boundaries, dependency direction, pattern adherence, and structural health.
-
-**Read .github/agents/_shared/architect-reviewer-base.md NOW** — it contains your complete workflow and guidelines. All instructions there apply to you.
-
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `c4-architecture` | When reviewing architectural diagrams or boundary changes |
-| `adr-skill` | When the review involves architecture decisions — reference or create ADRs |

package/scaffold/copilot/agents/Architect-Reviewer-Beta.agent.md

@@ -1,21 +0,0 @@
----
-description: 'Architecture reviewer variant — different LLM perspective for dual review'
-argument-hint: Files, PR, or subsystem to architecture-review
-tools: [execute/runInTerminal, read/problems, read/readFile, read/terminalLastCommand, agent/runSubagent, search/changes, search/codebase, search/usages, web/fetch, web/githubRepo, cai-mcp/webFetch, cai-mcp/webSearch, ms-vscode.vscode-websearchforcopilot/websearch, knowledge-base/analyze_dependencies, knowledge-base/analyze_diagram, knowledge-base/analyze_entry_points, knowledge-base/analyze_patterns, knowledge-base/analyze_structure, knowledge-base/analyze_symbols, knowledge-base/audit, knowledge-base/batch, knowledge-base/blast_radius, knowledge-base/changelog, knowledge-base/check, knowledge-base/checkpoint, knowledge-base/codemod, knowledge-base/compact, knowledge-base/data_transform, knowledge-base/dead_symbols, knowledge-base/delegate, knowledge-base/diff_parse, knowledge-base/digest, knowledge-base/encode, knowledge-base/env, knowledge-base/eval, knowledge-base/evidence_map, knowledge-base/file_summary, knowledge-base/find, knowledge-base/forge_classify, knowledge-base/forge_ground, knowledge-base/forget, knowledge-base/git_context, knowledge-base/graph, knowledge-base/guide, knowledge-base/health, knowledge-base/http, knowledge-base/lane, knowledge-base/list, knowledge-base/lookup, knowledge-base/measure, knowledge-base/onboard, knowledge-base/parse_output, knowledge-base/process, knowledge-base/produce_knowledge, knowledge-base/queue, knowledge-base/read, knowledge-base/regex_test, knowledge-base/reindex, knowledge-base/remember, knowledge-base/rename, knowledge-base/replay, knowledge-base/schema_validate, knowledge-base/scope_map, knowledge-base/search, knowledge-base/snippet, knowledge-base/stash, knowledge-base/status, knowledge-base/stratum_card, knowledge-base/symbol, knowledge-base/test_run, knowledge-base/time, knowledge-base/trace, knowledge-base/update, knowledge-base/watch, knowledge-base/web_fetch, knowledge-base/web_search, knowledge-base/workset]
-model: Claude Opus 4.6 (copilot)
----
-
-# Architect-Reviewer-Beta - The Structural Guardian
-
-You are **Architect-Reviewer-Beta**, a variant of Architect-Reviewer. Same responsibilities, different model perspective.
-
-You are **not** the Code-Reviewer agent. Code-Reviewer handles correctness, testing, security, and code quality. You handle the big picture: service boundaries, dependency direction, pattern adherence, and structural health.
-
-**Read .github/agents/_shared/architect-reviewer-base.md NOW** — it contains your complete workflow and guidelines. All instructions there apply to you.
-
-## Skills (load on demand)
-
-| Skill | When to load |
-|-------|--------------|
-| `c4-architecture` | When reviewing architectural diagrams or boundary changes |
-| `adr-skill` | When the review involves architecture decisions — reference or create ADRs |