@syntesseraai/opencode-feature-factory 0.2.17 → 0.2.18

package/agents/building.md

@@ -17,7 +17,6 @@ permission:
     'ff-*': allow
     planning: allow
     reviewing: allow
-    research: allow
   edit: allow
   bash: allow
   write:
@@ -57,7 +56,7 @@ While you implement, delegate:
 
 - **@ff-unit-test** - "Generate unit tests for [feature]. Write context to .feature-factory/agents/ff-unit-test-{UUID}.md"
 - **@ff-e2e-test** - "Create E2E tests for [workflow]. Write context to .feature-factory/agents/ff-e2e-test-{UUID}.md"
-- **@research** - "Research edge cases for [technology]. Write context to .feature-factory/agents/research-{UUID}.md"
+- **@ff-research** - "Research edge cases for [technology]. Write context to .feature-factory/agents/ff-research-{UUID}.md"
 
 ### Post-Implementation (Parallel)
 
@@ -92,15 +91,15 @@ After implementation, delegate:
 When encountering unfamiliar technology during planning:
 
 1. **Pause implementation** and create research todo
-2. **Invoke `@research` agent** via Task tool:
+2. **Invoke `@ff-research` agent** via Task tool:
    ```
-   Task(research): "Research [technology/topic] for implementation. Need to understand: 1) Core concepts, 2) Best practices, 3) Integration patterns"
+   Task(ff-research): "Research [technology/topic] for implementation. Need to understand: 1) Core concepts, 2) Best practices, 3) Integration patterns"
    ```
 3. **Wait for research results** - Do not proceed without understanding
 4. **Update plan** based on research findings
 5. **Continue implementation** with new knowledge
 
-**When to invoke @research automatically:**
+**When to invoke @ff-research automatically:**
 
 - Unfamiliar library or framework encountered
 - API integration requirements unclear
@@ -158,7 +157,7 @@ Use the Task tool during building:
 
 - **Need planning help** → Invoke `@planning` to create/clarify plan
 - **Requirements unclear** → Invoke `@ff-acceptance` to validate understanding
-- **External research needed** → Invoke `@research` to investigate libraries, APIs, or implementation patterns
+- **External research needed** → Invoke `@ff-research` to investigate libraries, APIs, or implementation patterns
 - **Code review needed** → Invoke `@ff-review` for mid-build quality check
 - **Security concerns** → Invoke `@ff-security` for security audit
 - **Comprehensive validation** → Invoke `@reviewing` for final review
@@ -250,7 +249,7 @@ Use ff-severity-classification when making changes:
 6. **Delegate in parallel** (while implementing):
    - Task(ff-unit-test): "Generate unit tests"
    - Task(ff-e2e-test): "Create E2E tests"
-   - Task(research): "Research edge cases"
+   - Task(ff-research): "Research edge cases"
 7. **Execute implementation** steps
 8. **Run quality checks** (lint, typecheck, tests)
 9. **Self-assess** changes using ff-severity-classification

package/agents/{research.md → ff-research.md}

@@ -4,7 +4,9 @@ mode: subagent
 temperature: 0.2
 tools:
   read: true
-  bash: true
+  write: false
+  edit: false
+  bash: false
   skill: true
   task: true
 permission:
@@ -126,7 +128,7 @@ Use ff-report-templates skill to format findings:
 
 ## When to Use This Agent
 
-Invoke `@research` via Task tool when:
+Invoke `@ff-research` via Task tool when:
 
 - **Need to investigate a library/framework** you haven't used before
 - **Best practices are unclear** for a particular technology
@@ -151,7 +153,7 @@ Other agents should invoke you when they encounter:
 When @planning encounters an unfamiliar technology:
 
 ```
-Task(research): "Research [technology name] for our implementation. We need to understand: 1) Core concepts, 2) Best practices for 2026, 3) Integration patterns with [existing stack]"
+Task(ff-research): "Research [technology name] for our implementation. We need to understand: 1) Core concepts, 2) Best practices for 2026, 3) Integration patterns with [existing stack]"
 ```
 
 ### Building Agent Integration
@@ -159,7 +161,7 @@ Task(research): "Research [technology name] for our implementation. We need to u
 When @building needs implementation details:
 
 ```
-Task(research): "Find implementation examples for [specific feature]. Look for: 1) Official documentation, 2) Code examples, 3) Common patterns on GitHub"
+Task(ff-research): "Find implementation examples for [specific feature]. Look for: 1) Official documentation, 2) Code examples, 3) Common patterns on GitHub"
 ```
 
 ### Reviewing Agent Integration
@@ -167,7 +169,7 @@ Task(research): "Find implementation examples for [specific feature]. Look for:
 When @reviewing needs to verify current practices:
 
 ```
-Task(research): "Research current security best practices for [technology]. Check for: 1) Recent vulnerabilities, 2) Recommended configurations, 3) Current OWASP guidance"
+Task(ff-research): "Research current security best practices for [technology]. Check for: 1) Recent vulnerabilities, 2) Recommended configurations, 3) Current OWASP guidance"
 ```
 
 ## Research Guidelines

package/agents/planning.md

@@ -5,8 +5,8 @@ temperature: 0.1
 color: '#3b82f6'
 tools:
   read: true
-  write: true
-  edit: true
+  write: false
+  edit: false
   bash: false
   skill: true
   task: true
@@ -15,7 +15,6 @@ permission:
     '*': allow
   task:
     'ff-*': allow
-    research: allow
     explore: allow
   write:
     '.feature-factory/agents/*': allow
@@ -53,7 +52,7 @@ ALWAYS prefer delegation. Parallelize these tasks:
 
 Delegate these simultaneously at the start:
 
-- **@research** - "Research best practices for [technology]. Write context to .feature-factory/agents/research-{UUID}.md"
+- **@ff-research** - "Research best practices for [technology]. Write context to .feature-factory/agents/ff-research-{UUID}.md"
 - **@ff-acceptance** - "Validate acceptance criteria. Write context to .feature-factory/agents/ff-acceptance-{UUID}.md"
 - **@ff-security** - "Threat model for [feature]. Write context to .feature-factory/agents/ff-security-{UUID}.md"
 - **@explore** - "Explore codebase for similar patterns. Write context to .feature-factory/agents/explore-{UUID}.md"
@@ -175,7 +174,7 @@ Use the Task tool during planning:
 - **Code exploration needed** → Invoke `@ff-review` to understand existing patterns
 - **Security considerations** → Invoke `@ff-security` for threat modeling
 - **Architecture questions** → Invoke `@ff-well-architected` for design review
-- **External research needed** → Invoke `@research` to investigate libraries, APIs, or best practices
+- **External research needed** → Invoke `@ff-research` to investigate libraries, APIs, or best practices
 
 ## Escalation Guidelines
 
@@ -195,7 +194,7 @@ Recommend escalation to full architectural planning when:
 2. **Load required skills** (ff-delegation, ff-mini-plan, ff-todo-management, ff-report-templates)
 3. **Document context** - Write to `.feature-factory/agents/planning-{UUID}.md`
 4. **Delegate in parallel**:
-   - Task(research): "Research [technology] best practices"
+   - Task(ff-research): "Research [technology] best practices"
    - Task(ff-acceptance): "Validate acceptance criteria"
    - Task(ff-security): "Security audit for [feature]"
    - Task(explore): "Explore codebase patterns"

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.2.17",
+  "version": "0.2.18",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",

package/skills/ff-delegation/SKILL.md

@@ -17,7 +17,7 @@ Use this skill to parallelize work across multiple specialized agents using UUID
 You MUST delegate when:
 
 - **Multiple independent tasks** can be worked on simultaneously
-- **Specialized expertise** is needed (security, architecture, research)
+- **Specialized expertise** is needed (security, architecture, ff-research)
 - **Validation** is required from multiple perspectives
 - **Information gathering** can happen in parallel with planning
 
@@ -92,7 +92,7 @@ Ask: "What work can happen simultaneously?"
 
 Common parallel tasks:
 
-- **Research** + **Planning** (research tech while planning architecture)
+- **ff-research** + **Planning** (research tech while planning architecture)
 - **Security audit** + **Architecture review** (different perspectives)
 - **Multiple file modifications** (if in different modules)
 - **Test writing** + **Documentation** (while implementation continues)
@@ -107,7 +107,7 @@ Use this matrix:
 | Code quality   | @ff-review           | @general | Parallel     |
 | Architecture   | @ff-well-architected | @general | Parallel     |
 | Requirements   | @ff-acceptance       | @explore | Blocking     |
-| Research       | @research            | @general | Async        |
+| Research       | @ff-research         | @general | Async        |
 | Exploration    | @explore             | @general | Parallel     |
 | Implementation | @general             | N/A      | Sequential   |
 
@@ -123,7 +123,7 @@ Generate child UUIDs:
 
 Delegate simultaneously:
 Task(ff-security): "Security audit: Check OAuth implementation for CSRF vulnerabilities. Write context to .feature-factory/agents/ff-security-{$CHILD_1}.md"
-Task(research): "Research: Find best OAuth libraries for Node.js. Write context to .feature-factory/agents/research-{$CHILD_2}.md"
+Task(ff-research): "Research: Find best OAuth libraries for Node.js. Write context to .feature-factory/agents/ff-research-{$CHILD_2}.md"
 Task(ff-acceptance): "Validate: Check if acceptance criteria are clear. Write context to .feature-factory/agents/ff-acceptance-{$CHILD_3}.md"
 ```
 
@@ -196,7 +196,7 @@ Combine findings from all delegated agents:
 - **Key Finding:** CSRF protection required
 - **Recommendation:** Use state parameter in OAuth flow
 
-### Research (@research)
+### Research (@ff-research)
 
 - **Status:** Completed
 - **Key Finding:** Passport.js is most popular library
@@ -221,7 +221,7 @@ Or clear specific agents:
 ```
 ff-agents-clear(id: "6ba7b810-9dad-11d1-80b4-00c04fd430c8")
 ff-agents-clear(sessionID: "session-abc123")
-ff-agents-clear(agent: "research")
+ff-agents-clear(agent: "ff-research")
 ```
 
 ## Example: Planning with Parallel Research
@@ -249,7 +249,7 @@ ff-agents-clear(agent: "research")
 
 5. **Delegate in parallel**
    - Task(ff-security): "Audit OAuth..." (use $SECURITY_UUID)
-   - Task(research): "Research OAuth..." (use $RESEARCH_UUID)
+   - Task(ff-research): "Research OAuth..." (use $RESEARCH_UUID)
    - Task(ff-acceptance): "Validate..." (use $ACCEPTANCE_UUID)
 
 6. **Update my context**
@@ -307,7 +307,7 @@ If specialized agents are unavailable:
 2. **@ff-review** → @general with code review focus
 3. **@ff-well-architected** → @general with architecture focus
 4. **@ff-acceptance** → @explore for requirements gathering
-5. **@research** → @general with research focus
+5. **@ff-research** → @general with research focus
 6. **@explore** → @general with read-only tools
 
 When falling back, be more specific in your instructions to compensate for the generalist nature of @general.