@mindfoldhq/trellis 0.4.0 → 0.5.0-beta.2

package/dist/templates/claude/agents/check.md

@@ -65,32 +65,6 @@ If failed, fix issues and re-run.
 
 ---
 
-## Completion Markers (Ralph Loop)
-
-**CRITICAL**: You are in a loop controlled by the Ralph Loop system.
-The loop will NOT stop until you output ALL required completion markers.
-
-Completion markers are generated from `check.jsonl` in the task directory.
-Each entry's `reason` field becomes a marker: `{REASON}_FINISH`
-
-For example, if check.jsonl contains:
-```json
-{"file": "...", "reason": "TypeCheck"}
-{"file": "...", "reason": "Lint"}
-{"file": "...", "reason": "CodeReview"}
-```
-
-You MUST output these markers when each check passes:
-- `TYPECHECK_FINISH` - After typecheck passes
-- `LINT_FINISH` - After lint passes
-- `CODEREVIEW_FINISH` - After code review passes
-
-If check.jsonl doesn't exist or has no reasons, output: `ALL_CHECKS_FINISH`
-
-**The loop will block you from stopping until all markers are present in your output.**
-
----
-
 ## Report Format
 
 ```markdown
@@ -112,11 +86,10 @@ If check.jsonl doesn't exist or has no reasons, output: `ALL_CHECKS_FINISH`
 
 ### Verification Results
 
-- TypeCheck: Passed TYPECHECK_FINISH
-- Lint: Passed LINT_FINISH
+- TypeCheck: Passed
+- Lint: Passed
 
 ### Summary
 
 Checked X files, found Y issues, all fixed.
-ALL_CHECKS_FINISH
 ```

package/dist/templates/claude/agents/research.md

@@ -1,8 +1,8 @@
 ---
 name: research
 description: |
-  Code and tech search expert. Pure research, no code modifications. Finds files, patterns, and tech solutions.
-tools: Read, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
+  Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
+tools: Read, Write, Glob, Grep, Bash, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
 model: opus
 ---
 # Research Agent
@@ -11,94 +11,111 @@ You are the Research Agent in the Trellis workflow.
 
 ## Core Principle
 
-**You do one thing: find and explain information.**
+**You do one thing: find, explain, and PERSIST information.**
 
-You are a documenter, not a reviewer. Your job is to help get the information needed.
+Conversations get compacted; files don't. Every research output MUST end up as a file under `{TASK_DIR}/research/`. Returning findings only through the chat reply is a failure — the caller cannot read them next session.
 
 ---
 
 ## Core Responsibilities
 
-### 1. Internal Search (Project Code)
+1. **Internal Search** — locate files/components, understand code logic, discover patterns (Glob, Grep, Read)
+2. **External Search** — library docs, API references, best practices (web search)
+3. **Persist** — write each research topic to `{TASK_DIR}/research/<topic>.md`
+4. **Report** — return file paths + one-line summaries to the main agent (not full content)
 
-| Search Type | Goal | Tools |
-|-------------|------|-------|
-| **WHERE** | Locate files/components | Glob, Grep |
-| **HOW** | Understand code logic | Read, Grep |
-| **PATTERN** | Discover existing patterns | Grep, Read |
+---
+
+## Workflow
 
-### 2. External Search (Tech Solutions)
+### Step 1: Resolve Current Task
 
-Use web search for best practices and code examples.
+Read `.trellis/.current-task` → task directory (e.g. `.trellis/tasks/04-17-foo/`). If empty or missing, ask the user where to write output; do NOT guess.
 
----
+Ensure `{TASK_DIR}/research/` exists:
 
-## Strict Boundaries
+```bash
+mkdir -p <TASK_DIR>/research
+```
 
-### Only Allowed
+### Step 2: Understand Search Request
 
-- Describe **what exists**
-- Describe **where it is**
-- Describe **how it works**
-- Describe **how components interact**
+Classify: internal / external / mixed. Determine scope (global / specific directory) and expected shape (file list / pattern notes / tech comparison).
 
-### Forbidden (unless explicitly asked)
+### Step 3: Execute Search
 
-- Suggest improvements
-- Criticize implementation
-- Recommend refactoring
-- Modify any files
-- Execute git commands
+Run independent searches in parallel (Glob + Grep + web) for efficiency.
 
----
+### Step 4: Persist Each Topic
 
-## Workflow
+For each distinct research topic, Write a markdown file at `{TASK_DIR}/research/<topic-slug>.md`. Use the File Format below.
 
-### Step 1: Understand Search Request
+### Step 5: Report to Main Agent
 
-Analyze the query, determine:
+Reply with ONLY:
 
-- Search type (internal/external/mixed)
-- Search scope (global/specific directory)
-- Expected output (file list/code patterns/tech solutions)
+- List of files written (paths relative to repo root)
+- One-line summary per file
+- Any critical caveats that the main agent needs to know right now
 
-### Step 2: Execute Search
+Do NOT paste full research content into the reply. The files are the contract.
 
-Execute multiple independent searches in parallel for efficiency.
+---
 
-### Step 3: Organize Results
+## Scope Limits (Strict)
 
-Output structured results in report format.
+### Write ALLOWED
+
+- `{TASK_DIR}/research/*.md` — your own output
+- Creating `{TASK_DIR}/research/` if it doesn't exist (via `mkdir -p`)
+
+### Write FORBIDDEN
+
+- Code files (`src/`, `lib/`, …)
+- Spec files (`.trellis/spec/`) — main agent should use `update-spec` skill instead
+- `.trellis/scripts/`, `.trellis/workflow.md`, platform config (`.claude/`, `.cursor/`, etc.)
+- Other task directories
+- Any git operation (commit / push / branch / merge)
+
+If the user asks you to edit code, decline and suggest spawning `implement` instead.
 
 ---
 
-## Report Format
+## File Format
+
+Each `{TASK_DIR}/research/<topic>.md` should follow:
 
 ```markdown
-## Search Results
+# Research: <topic>
 
-### Query
+- **Query**: <original query>
+- **Scope**: <internal / external / mixed>
+- **Date**: <YYYY-MM-DD>
 
-{original query}
+## Findings
 
 ### Files Found
 
 | File Path | Description |
-|-----------|-------------|
+|---|---|
 | `src/services/xxx.ts` | Main implementation |
 | `src/types/xxx.ts` | Type definitions |
 
-### Code Pattern Analysis
+### Code Patterns
+
+<describe patterns, cite file:line>
+
+### External References
 
-{Describe discovered patterns, cite specific files and line numbers}
+- [Library X docs](url) — <why relevant, version constraints>
 
-### Related Spec Documents
+### Related Specs
 
-- `.trellis/spec/xxx.md` - {description}
+- `.trellis/spec/xxx.md` — <description>
 
-### Not Found
+## Caveats / Not Found
 
-{If some content was not found, explain}
+<anything incomplete or uncertain>
 ```
 
 ---
@@ -109,12 +126,13 @@ Output structured results in report format.
 
 - Provide specific file paths and line numbers
 - Quote actual code snippets
-- Distinguish "definitely found" and "possibly related"
-- Explain search scope and limitations
+- Persist every topic to its own file
+- Return file paths in your reply, not the full content
+- Mark "not found" explicitly when searches come up empty
 
 ### DON'T
 
+- Don't write code or modify files outside `{TASK_DIR}/research/`
 - Don't guess uncertain info
-- Don't omit important search results
-- Don't add improvement suggestions in report (unless explicitly asked)
-- Don't modify any files
+- Don't paste full research text into the reply (files are the deliverable)
+- Don't propose improvements or critique implementation (that's not your role)

package/dist/templates/claude/index.d.ts

@@ -1,54 +1,22 @@
 /**
  * Claude Code templates
  *
- * These are GENERIC templates for user projects.
- * Do NOT use Trellis project's own .claude/ directory (which may be customized).
- *
  * Directory structure:
  *   claude/
- *   ├── commands/       # Slash commands
- *   ├── agents/         # Multi-agent pipeline agents
- *   ├── hooks/          # Context injection hooks
+ *   ├── agents/         # Sub-agent definitions
  *   └── settings.json   # Settings configuration
+ *
+ * Hooks come from shared-hooks/ (unified with other platforms).
  */
 export declare const settingsTemplate: string;
-/**
- * Command template with name and content
- */
-export interface CommandTemplate {
-    name: string;
-    content: string;
-}
-/**
- * Agent template with name and content
- */
 export interface AgentTemplate {
     name: string;
     content: string;
 }
-/**
- * Hook template with target path and content
- */
-export interface HookTemplate {
+export interface SettingsTemplate {
     targetPath: string;
     content: string;
 }
-/**
- * Get all command templates
- * Commands are stored in commands/trellis/ subdirectory
- * This creates commands like /trellis:start, /trellis:finish-work, etc.
- */
-export declare function getAllCommands(): CommandTemplate[];
-/**
- * Get all agent templates
- */
 export declare function getAllAgents(): AgentTemplate[];
-/**
- * Get all hook templates
- */
-export declare function getAllHooks(): HookTemplate[];
-/**
- * Get settings template
- */
-export declare function getSettingsTemplate(): HookTemplate;
+export declare function getSettingsTemplate(): SettingsTemplate;
 //# sourceMappingURL=index.d.ts.map

package/dist/templates/claude/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/templates/claude/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAsBH,eAAO,MAAM,gBAAgB,QAAgC,CAAC;AAE9D;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,UAAU,EAAE,MAAM,CAAC;IACnB,OAAO,EAAE,MAAM,CAAC;CACjB;AAED;;;;GAIG;AACH,wBAAgB,cAAc,IAAI,eAAe,EAAE,CAalD;AAED;;GAEG;AACH,wBAAgB,YAAY,IAAI,aAAa,EAAE,CAa9C;AAED;;GAEG;AACH,wBAAgB,WAAW,IAAI,YAAY,EAAE,CAU5C;AAED;;GAEG;AACH,wBAAgB,mBAAmB,IAAI,YAAY,CAKlD"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/templates/claude/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAqBH,eAAO,MAAM,gBAAgB,QAAgC,CAAC;AAE9D,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,gBAAgB;IAC/B,UAAU,EAAE,MAAM,CAAC;IACnB,OAAO,EAAE,MAAM,CAAC;CACjB;AAED,wBAAgB,YAAY,IAAI,aAAa,EAAE,CAa9C;AAED,wBAAgB,mBAAmB,IAAI,gBAAgB,CAKtD"}

package/dist/templates/claude/index.js

@@ -1,15 +1,12 @@
 /**
  * Claude Code templates
  *
- * These are GENERIC templates for user projects.
- * Do NOT use Trellis project's own .claude/ directory (which may be customized).
- *
  * Directory structure:
  *   claude/
- *   ├── commands/       # Slash commands
- *   ├── agents/         # Multi-agent pipeline agents
- *   ├── hooks/          # Context injection hooks
+ *   ├── agents/         # Sub-agent definitions
  *   └── settings.json   # Settings configuration
+ *
+ * Hooks come from shared-hooks/ (unified with other platforms).
  */
 import { readdirSync, readFileSync } from "node:fs";
 import { dirname, join } from "node:path";
@@ -27,28 +24,7 @@ function listFiles(dir) {
         return [];
     }
 }
-// Settings
 export const settingsTemplate = readTemplate("settings.json");
-/**
- * Get all command templates
- * Commands are stored in commands/trellis/ subdirectory
- * This creates commands like /trellis:start, /trellis:finish-work, etc.
- */
-export function getAllCommands() {
-    const commands = [];
-    const files = listFiles("commands/trellis");
-    for (const file of files) {
-        if (file.endsWith(".md")) {
-            const name = file.replace(".md", "");
-            const content = readTemplate(`commands/trellis/${file}`);
-            commands.push({ name, content });
-        }
-    }
-    return commands;
-}
-/**
- * Get all agent templates
- */
 export function getAllAgents() {
     const agents = [];
     const files = listFiles("agents");
@@ -61,21 +37,6 @@ export function getAllAgents() {
     }
     return agents;
 }
-/**
- * Get all hook templates
- */
-export function getAllHooks() {
-    const hooks = [];
-    const files = listFiles("hooks");
-    for (const file of files) {
-        const content = readTemplate(`hooks/${file}`);
-        hooks.push({ targetPath: `hooks/${file}`, content });
-    }
-    return hooks;
-}
-/**
- * Get settings template
- */
 export function getSettingsTemplate() {
     return {
         targetPath: "settings.json",

package/dist/templates/claude/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/templates/claude/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAEH,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACpD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AAEzC,MAAM,UAAU,GAAG,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAClD,MAAM,SAAS,GAAG,OAAO,CAAC,UAAU,CAAC,CAAC;AAEtC,SAAS,YAAY,CAAC,YAAoB;IACxC,OAAO,YAAY,CAAC,IAAI,CAAC,SAAS,EAAE,YAAY,CAAC,EAAE,OAAO,CAAC,CAAC;AAC9D,CAAC;AAED,SAAS,SAAS,CAAC,GAAW;IAC5B,IAAI,CAAC;QACH,OAAO,WAAW,CAAC,IAAI,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,CAAC;IAC3C,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,EAAE,CAAC;IACZ,CAAC;AACH,CAAC;AAED,WAAW;AACX,MAAM,CAAC,MAAM,gBAAgB,GAAG,YAAY,CAAC,eAAe,CAAC,CAAC;AA0B9D;;;;GAIG;AACH,MAAM,UAAU,cAAc;IAC5B,MAAM,QAAQ,GAAsB,EAAE,CAAC;IACvC,MAAM,KAAK,GAAG,SAAS,CAAC,kBAAkB,CAAC,CAAC;IAE5C,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;YACzB,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YACrC,MAAM,OAAO,GAAG,YAAY,CAAC,oBAAoB,IAAI,EAAE,CAAC,CAAC;YACzD,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC;QACnC,CAAC;IACH,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,YAAY;IAC1B,MAAM,MAAM,GAAoB,EAAE,CAAC;IACnC,MAAM,KAAK,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAC;IAElC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;YACzB,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YACrC,MAAM,OAAO,GAAG,YAAY,CAAC,UAAU,IAAI,EAAE,CAAC,CAAC;YAC/C,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC;QACjC,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,WAAW;IACzB,MAAM,KAAK,GAAmB,EAAE,CAAC;IACjC,MAAM,KAAK,GAAG,SAAS,CAAC,OAAO,CAAC,CAAC;IAEjC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,MAAM,OAAO,GAAG,YAAY,CAAC,SAAS,IAAI,EAAE,CAAC,CAAC;QAC9C,KAAK,CAAC,IAAI,CAAC,EAAE,UAAU,EAAE,SAAS,IAAI,EAAE,EAAE,OAAO,EAAE,CAAC,CAAC;IACvD,CAAC;IAED,OAAO,KAAK,CAAC;AACf,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,mBAAmB;IACjC,OAAO;QACL,UAAU,EAAE,eAAe;QAC3B,OAAO,EAAE,gBAAgB;KAC1B,CAAC;AACJ,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/templates/claude/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACpD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AAEzC,MAAM,UAAU,GAAG,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAClD,MAAM,SAAS,GAAG,OAAO,CAAC,UAAU,CAAC,CAAC;AAEtC,SAAS,YAAY,CAAC,YAAoB;IACxC,OAAO,YAAY,CAAC,IAAI,CAAC,SAAS,EAAE,YAAY,CAAC,EAAE,OAAO,CAAC,CAAC;AAC9D,CAAC;AAED,SAAS,SAAS,CAAC,GAAW;IAC5B,IAAI,CAAC;QACH,OAAO,WAAW,CAAC,IAAI,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,CAAC;IAC3C,CAAC;IAAC,MAAM,CAAC;QACP,OAAO,EAAE,CAAC;IACZ,CAAC;AACH,CAAC;AAED,MAAM,CAAC,MAAM,gBAAgB,GAAG,YAAY,CAAC,eAAe,CAAC,CAAC;AAY9D,MAAM,UAAU,YAAY;IAC1B,MAAM,MAAM,GAAoB,EAAE,CAAC;IACnC,MAAM,KAAK,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAC;IAElC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;YACzB,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YACrC,MAAM,OAAO,GAAG,YAAY,CAAC,UAAU,IAAI,EAAE,CAAC,CAAC;YAC/C,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC;QACjC,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,MAAM,UAAU,mBAAmB;IACjC,OAAO;QACL,UAAU,EAAE,eAAe;QAC3B,OAAO,EAAE,gBAAgB;KAC1B,CAAC;AACJ,CAAC"}

package/dist/templates/claude/settings.json

@@ -58,14 +58,13 @@
         ]
       }
     ],
-    "SubagentStop": [
+    "UserPromptSubmit": [
       {
-        "matcher": "check",
         "hooks": [
           {
             "type": "command",
-            "command": "{{PYTHON_CMD}} .claude/hooks/ralph-loop.py",
-            "timeout": 10
+            "command": "{{PYTHON_CMD}} .claude/hooks/inject-workflow-state.py",
+            "timeout": 5
           }
         ]
       }

package/dist/templates/{iflow → codebuddy}/agents/check.md

@@ -3,7 +3,7 @@ name: check
 description: |
   Code quality check expert. Reviews code changes against specs and self-fixes issues.
 tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
-color: orange
+model: opus
 ---
 # Check Agent
 
@@ -65,32 +65,6 @@ If failed, fix issues and re-run.
 
 ---
 
-## Completion Markers (Ralph Loop)
-
-**CRITICAL**: You are in a loop controlled by the Ralph Loop system.
-The loop will NOT stop until you output ALL required completion markers.
-
-Completion markers are generated from `check.jsonl` in the task directory.
-Each entry's `reason` field becomes a marker: `{REASON}_FINISH`
-
-For example, if check.jsonl contains:
-```json
-{"file": "...", "reason": "TypeCheck"}
-{"file": "...", "reason": "Lint"}
-{"file": "...", "reason": "CodeReview"}
-```
-
-You MUST output these markers when each check passes:
-- `TYPECHECK_FINISH` - After typecheck passes
-- `LINT_FINISH` - After lint passes
-- `CODEREVIEW_FINISH` - After code review passes
-
-If check.jsonl doesn't exist or has no reasons, output: `ALL_CHECKS_FINISH`
-
-**The loop will block you from stopping until all markers are present in your output.**
-
----
-
 ## Report Format
 
 ```markdown
@@ -112,11 +86,10 @@ If check.jsonl doesn't exist or has no reasons, output: `ALL_CHECKS_FINISH`
 
 ### Verification Results
 
-- TypeCheck: Passed TYPECHECK_FINISH
-- Lint: Passed LINT_FINISH
+- TypeCheck: Passed
+- Lint: Passed
 
 ### Summary
 
 Checked X files, found Y issues, all fixed.
-ALL_CHECKS_FINISH
 ```

package/dist/templates/{iflow → codebuddy}/agents/implement.md

@@ -3,7 +3,7 @@ name: implement
 description: |
   Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
 tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
-color: green
+model: opus
 ---
 # Implement Agent
 

package/dist/templates/codebuddy/agents/research.md

@@ -0,0 +1,138 @@
+---
+name: research
+description: |
+  Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
+tools: Read, Write, Glob, Grep, Bash, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
+model: opus
+---
+# Research Agent
+
+You are the Research Agent in the Trellis workflow.
+
+## Core Principle
+
+**You do one thing: find, explain, and PERSIST information.**
+
+Conversations get compacted; files don't. Every research output MUST end up as a file under `{TASK_DIR}/research/`. Returning findings only through the chat reply is a failure — the caller cannot read them next session.
+
+---
+
+## Core Responsibilities
+
+1. **Internal Search** — locate files/components, understand code logic, discover patterns (Glob, Grep, Read)
+2. **External Search** — library docs, API references, best practices (web search)
+3. **Persist** — write each research topic to `{TASK_DIR}/research/<topic>.md`
+4. **Report** — return file paths + one-line summaries to the main agent (not full content)
+
+---
+
+## Workflow
+
+### Step 1: Resolve Current Task
+
+Read `.trellis/.current-task` → task directory (e.g. `.trellis/tasks/04-17-foo/`). If empty or missing, ask the user where to write output; do NOT guess.
+
+Ensure `{TASK_DIR}/research/` exists:
+
+```bash
+mkdir -p <TASK_DIR>/research
+```
+
+### Step 2: Understand Search Request
+
+Classify: internal / external / mixed. Determine scope (global / specific directory) and expected shape (file list / pattern notes / tech comparison).
+
+### Step 3: Execute Search
+
+Run independent searches in parallel (Glob + Grep + web) for efficiency.
+
+### Step 4: Persist Each Topic
+
+For each distinct research topic, Write a markdown file at `{TASK_DIR}/research/<topic-slug>.md`. Use the File Format below.
+
+### Step 5: Report to Main Agent
+
+Reply with ONLY:
+
+- List of files written (paths relative to repo root)
+- One-line summary per file
+- Any critical caveats that the main agent needs to know right now
+
+Do NOT paste full research content into the reply. The files are the contract.
+
+---
+
+## Scope Limits (Strict)
+
+### Write ALLOWED
+
+- `{TASK_DIR}/research/*.md` — your own output
+- Creating `{TASK_DIR}/research/` if it doesn't exist (via `mkdir -p`)
+
+### Write FORBIDDEN
+
+- Code files (`src/`, `lib/`, …)
+- Spec files (`.trellis/spec/`) — main agent should use `update-spec` skill instead
+- `.trellis/scripts/`, `.trellis/workflow.md`, platform config (`.claude/`, `.cursor/`, etc.)
+- Other task directories
+- Any git operation (commit / push / branch / merge)
+
+If the user asks you to edit code, decline and suggest spawning `implement` instead.
+
+---
+
+## File Format
+
+Each `{TASK_DIR}/research/<topic>.md` should follow:
+
+```markdown
+# Research: <topic>
+
+- **Query**: <original query>
+- **Scope**: <internal / external / mixed>
+- **Date**: <YYYY-MM-DD>
+
+## Findings
+
+### Files Found
+
+| File Path | Description |
+|---|---|
+| `src/services/xxx.ts` | Main implementation |
+| `src/types/xxx.ts` | Type definitions |
+
+### Code Patterns
+
+<describe patterns, cite file:line>
+
+### External References
+
+- [Library X docs](url) — <why relevant, version constraints>
+
+### Related Specs
+
+- `.trellis/spec/xxx.md` — <description>
+
+## Caveats / Not Found
+
+<anything incomplete or uncertain>
+```
+
+---
+
+## Guidelines
+
+### DO
+
+- Provide specific file paths and line numbers
+- Quote actual code snippets
+- Persist every topic to its own file
+- Return file paths in your reply, not the full content
+- Mark "not found" explicitly when searches come up empty
+
+### DON'T
+
+- Don't write code or modify files outside `{TASK_DIR}/research/`
+- Don't guess uncertain info
+- Don't paste full research text into the reply (files are the deliverable)
+- Don't propose improvements or critique implementation (that's not your role)

package/dist/templates/codebuddy/index.d.ts

@@ -2,24 +2,14 @@
  * CodeBuddy templates
  *
  * These are GENERIC templates for user projects.
- * Do NOT use Trellis project's own .codebuddy/ directory (which may be customized).
  *
  * Directory structure:
  *   codebuddy/
- *   └── commands/
- *       └── trellis/    # Nested subdirectory for namespace
- *           └── *.md
+ *   ├── agents/         # Multi-agent pipeline agents
+ *   └── settings.json   # Settings configuration
  */
-/**
- * Command template with name and content
- */
-export interface CommandTemplate {
-    name: string;
-    content: string;
-}
-/**
- * Get all command templates
- * CodeBuddy uses nested directories: commands/trellis/<name>.md → /trellis:<name>
- */
-export declare function getAllCommands(): CommandTemplate[];
+import { type AgentTemplate, type HookTemplate } from "../template-utils.js";
+export type { AgentTemplate, HookTemplate };
+export declare const getAllAgents: () => AgentTemplate[];
+export declare const getSettingsTemplate: () => HookTemplate;
 //# sourceMappingURL=index.d.ts.map

package/dist/templates/codebuddy/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/templates/codebuddy/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAqBH;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE,MAAM,CAAC;CACjB;AAED;;;GAGG;AACH,wBAAgB,cAAc,IAAI,eAAe,EAAE,CAalD"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/templates/codebuddy/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAEL,KAAK,aAAa,EAClB,KAAK,YAAY,EAClB,MAAM,sBAAsB,CAAC;AAC9B,YAAY,EAAE,aAAa,EAAE,YAAY,EAAE,CAAC;AAI5C,eAAO,MAAM,YAAY,QAAO,aAAa,EAAoB,CAAC;AAClE,eAAO,MAAM,mBAAmB,QAAO,YAA6B,CAAC"}