opencodekit 0.6.7 → 0.7.0

package/dist/template/.opencode/AGENTS.md

@@ -5,7 +5,7 @@
 1. Security constraints (always first)
 2. Anti-hallucination rule (overrides all except security)
 3. Delegation rules (check before tool calls)
-4. Skills check (`find_skills` → `use_skill`)
+4. Skills check (native `skill` tool)
 5. User explicit requests
 6. Base prompt behaviors
 7. Global rules (this file)
@@ -302,9 +302,58 @@ Use all three:
 
 **Philosophy**: Beads is execution, not planning. Plan elsewhere, track in Beads.
 
+## Beads Village (Multi-Agent Coordination)
+
+MCP server for task coordination and file locking between agents.
+
+### When to Use
+
+- **Multi-agent work**: Multiple agents on same codebase
+- **File conflict prevention**: Reserve files before editing
+- **Cross-workspace coordination**: FE/BE/Mobile agents communicating
+
+### Core Workflow
+
+```
+init() → claim() → reserve(paths) → [work] → done(id, msg) → RESTART
+```
+
+### Key Tools
+
+**Session Management**
+
+Start every session by calling `init` with your team name and role. This registers you in the workspace and enables role-based task filtering. For example, `init(team="project", role="fe")` joins as a frontend agent.
+
+Check workspace state with `status(include_agents=true)` to see active agents, file locks, and pending messages.
+
+**Task Operations**
+
+Call `claim` to get the next ready task assigned to your role. It auto-filters based on task tags matching your role.
+
+When work is complete, call `done(id="bd-42", msg="Implemented feature X")` to close the task and notify other agents. After `done`, restart your session for a fresh context.
+
+**File Reservations**
+
+Before editing files, call `reserve(paths=["src/auth.ts"])` to lock them. This prevents other agents from modifying the same files. Call `release` when finished to unlock.
+
+**Messaging**
+
+Send messages with `msg(subj="API Ready", global=true, to="all")` for cross-workspace announcements. Check incoming messages with `inbox(unread=true)`.
+
+### Integration with Commands
+
+Use `/create` for the full spec workflow instead of the Village `add` tool. When implementing, `claim` gets your task and `reserve` locks files - Village handles the coordination while your `/implement` command handles the actual work. When finishing, `done` syncs state and notifies other agents.
+
+### Rules
+
+- **Always `init()` first** in any session using Village tools
+- **Reserve before edit** to prevent conflicts
+- **One task per session** - restart after `done()`
+- **Use `msg(global=true)`** for cross-workspace announcements
+
 ## Skills System
 
-Use `find_skills` → `use_skill` when:
+OpenCode has a native `skill` tool that auto-discovers skills from `.opencode/skill/` and `~/.config/opencode/skill/`. Use `skill({ name: "skill-name" })` when:
 
 - Creating something new → `brainstorming`
 - Bug or unexpected behavior → `systematic-debugging`
@@ -321,16 +370,12 @@ Use `find_skills` → `use_skill` when:
 
 Skip for simple questions, quick edits, or conversations.
 
-### Progressive Skill Loading
-
-Skills consume context. Manage them actively:
-
-1. **Load on-demand**: Only load skills when starting relevant work
-2. **Read linked files lazily**: Don't load all skill references immediately—read only when needed
-3. **Unload after completion**: When task completes, skill context is no longer needed
-4. **One skill at a time**: Avoid loading multiple skills unless task requires it
+### How It Works
 
-**IMPORTANT**: Always unload irrelevant skills to free context space. Loaded skills that aren't actively needed are context debt.
+1. Available skills are listed in the `skill` tool description (auto-discovered)
+2. Load a skill: `skill({ name: "brainstorming" })`
+3. Skills consume context - load on-demand, one at a time
+4. Skill permissions can be configured in `opencode.json` (`allow`/`deny`/`ask`)
 
 ## Core Constraints
 

package/dist/template/.opencode/README.md

@@ -41,7 +41,7 @@ opencode
 │
 ├── agent/                 # Custom agents (5 total)
 ├── command/               # Custom commands (26 workflows)
-├── superpowers/skills/    # Domain expertise (16 skills)
+├── skill/                 # Domain expertise (27 skills)
 ├── tool/                  # Custom MCP tools (memory-*, observation, ast-grep)
 ├── plugin/                # Background plugins (enforcer, compactor, truncator)
 └── memory/                # Persistent context
@@ -105,22 +105,23 @@ GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json
 
 - `/commit` - Intelligent git commits
 - `/pr` - Create pull requests
-- `/design` - Thoughtful design with brainstorming
-- `/fix` - Systematic debugging
-- `/research` - Deep documentation search
-- `/review-codebase` - Comprehensive audit
+- `/design` - Thoughtful design with brainstorming expertise
+- `/fix` - Systematic debugging with root-cause analysis
+- `/implement` - High-quality implementation with TDD and subagents
+- `/finish` - Verified completion with structured integration options
 
 **See:** `.opencode/command/` for all commands
 
 ---
 
-## Skills System (16 skills)
+## Skills System (27 skills)
 
-**Core:** brainstorming, writing-plans, executing-plans, verification-before-completion
-**Code:** requesting-code-review, receiving-code-review, root-cause-tracing
-**Advanced:** gemini-large-context, subagent-driven-development, dispatching-parallel-agents
+**Core:** brainstorming, writing-plans, executing-plans, verification-before-completion, using-superpowers, finishing-a-development-branch
+**Code:** requesting-code-review, receiving-code-review, root-cause-tracing, test-driven-development, testing-anti-patterns, condition-based-waiting, defense-in-depth, systematic-debugging
+**UI/UX:** frontend-aesthetics, mockup-to-code, visual-analysis, ui-ux-research, accessibility-audit, design-system-audit
+**Workflow:** gemini-large-context, subagent-driven-development, dispatching-parallel-agents, using-git-worktrees, sharing-skills, writing-skills, testing-skills-with-subagents
 
-**Note:** Skills load via `use_skill()` in commands
+**Note:** Skills load via native `skill()` tool. Commands auto-load relevant expertise.
 
 ---
 
@@ -287,9 +288,10 @@ fi
 
 **"Skills not loading":**
 
-- Skills load via commands with `use_skill()`
+- Skills load via native `skill()` tool (auto-discovered)
 - Use /design to load brainstorming
-- Use /fix to load debugging skills
+- Use /fix to load systematic-debugging
+- Check `.opencode/skill/` directory exists
 
 ---
 
@@ -324,12 +326,12 @@ fi
 - **OpenCode Docs:** https://opencode.ai/docs
 - **Context7 API:** https://context7.com
 - **Exa API:** https://exa.ai
-- **Skills Documentation:** `superpowers/skills/`
+- **Skills Documentation:** `.opencode/skill/`
 - **Architecture Guide:** `AGENTS.md`
 
 ---
 
-**OpenCodeKit v0.3.0**  
+**OpenCodeKit v0.7.0**  
 **Architecture:** Two-Layer (Memory + Beads + Git)  
-**New in v0.3.0:** Background plugins (enforcer, compactor, truncator) + ast-grep tool  
-**Last Updated:** December 17, 2025
+**New in v0.7.0:** Native skill tool integration, Beads Village MCP, 27 skills, enhanced commands  
+**Last Updated:** December 30, 2025

package/dist/template/.opencode/command/accessibility-check.md

@@ -7,7 +7,7 @@ model: proxypal/gemini-3-flash-preview
 
 # Accessibility Check: $ARGUMENTS
 
-use_skill("accessibility-audit")
+skill({ name: "accessibility-audit" })
 
 Perform WCAG accessibility audit.
 

package/dist/template/.opencode/command/analyze-mockup.md

@@ -7,7 +7,7 @@ model: proxypal/gemini-3-flash-preview
 
 # Analyze Mockup: $ARGUMENTS
 
-use_skill("visual-analysis")
+skill({ name: "visual-analysis" })
 
 Analyze the provided UI mockup or screenshot.
 

package/dist/template/.opencode/command/analyze-project.md

@@ -5,6 +5,8 @@ agent: planner
 
 # Analyze Project
 
+**For large codebases:** `skill({ name: "gemini-large-context" })`
+
 ## Quick Status
 
 1. **Git:** `git status` - current branch, changes

package/dist/template/.opencode/command/brainstorm.md

@@ -6,7 +6,7 @@ agent: build
 
 # Brainstorm: $ARGUMENTS
 
-use_skill("brainstorming")
+skill({ name: "brainstorming" })
 
 Follow the skill for ideation, then explore the codebase to validate feasibility. Create quick prototypes or code spikes if helpful.
 

package/dist/template/.opencode/command/commit.md

@@ -5,7 +5,7 @@ argument-hint: "[bead-id]"
 
 # Commit
 
-use_skill("verification-before-completion")
+skill({ name: "verification-before-completion" })
 
 ## Workflow
 

package/dist/template/.opencode/command/create.md

@@ -40,6 +40,7 @@ Creating:
   Type: [type]
   Priority: [0-4]
   Complexity: [quick/deep]
+  Role: [fe/be/mobile/devops/qa] (optional, for multi-agent)
 
 Approve? (yes/modify)
 ```
@@ -50,6 +51,14 @@ On approval:
 bd create "[title]" -t [type] -p [priority] -d "[description]" --json
 ```
 
+**If using Beads Village for multi-agent coordination:** Add role tags so tasks can be auto-assigned to the right agent:
+
+```
+add(title="[title]", tags=["[role]"], priority=[0-4])
+```
+
+This makes the task claimable by agents with matching roles.
+
 ## Phase 4: Create Spec
 
 ```bash

package/dist/template/.opencode/command/design-audit.md

@@ -7,7 +7,7 @@ model: proxypal/gemini-3-pro-preview
 
 # Design Audit: $ARGUMENTS
 
-use_skill("design-system-audit")
+skill({ name: "design-system-audit" })
 
 Perform a comprehensive design system audit.
 

package/dist/template/.opencode/command/design.md

@@ -6,7 +6,7 @@ agent: vision
 
 # Design: $ARGUMENTS
 
-use_skill("frontend-aesthetics")
+skill({ name: "frontend-aesthetics" })
 
 Focus on visual design: typography, color, spacing, layout, accessibility. Avoid AI slop aesthetics.
 

package/dist/template/.opencode/command/finish.md

@@ -6,6 +6,11 @@ agent: build
 
 # Finish
 
+**Load skills:**
+
+- `skill({ name: "verification-before-completion" })`
+- `skill({ name: "finishing-a-development-branch" })`
+
 ## Phase 1: Load Bead
 
 ```bash
@@ -170,6 +175,16 @@ Closes: <bead-id>"
 
 ## Phase 7: Close Bead
 
+**If using Beads Village:** Complete the task and notify other agents:
+
+```
+done(id="$ARGUMENTS", msg="Implemented: [1-liner summary]")
+```
+
+This closes the bead, releases any file reservations, and broadcasts completion to the workspace.
+
+**Otherwise:** Close via CLI:
+
 ```bash
 bd close $ARGUMENTS --reason "Implemented: [1-liner summary]"
 ```
@@ -223,6 +238,8 @@ Task complete. For best performance:
 Next: Create PR or merge to main
 ```
 
+**If using Beads Village:** After calling `done()`, restart your session for a fresh context. The one-task-per-session pattern keeps agents fast and focused.
+
 **If work was interrupted or partially complete:**
 
 ```

package/dist/template/.opencode/command/fix-ci.md

@@ -3,6 +3,10 @@ description: Analyze Github Actions logs and fix issues with bead tracking
 argument-hint: "[github-actions-url]"
 ---
 
+**Load skill:** `skill({ name: "systematic-debugging" })`
+
+For deep tracing: `skill({ name: "root-cause-tracing" })`
+
 ## Github Actions URL
 
 <url>$ARGUMENTS</url>

package/dist/template/.opencode/command/fix-types.md

@@ -5,6 +5,8 @@ argument-hint: "[bead-id]"
 
 # Fix Type Errors
 
+**Load skill:** `skill({ name: "systematic-debugging" })`
+
 Run `bun run typecheck` and fix all type errors.
 
 ## Rules

package/dist/template/.opencode/command/fix-ui.md

@@ -6,7 +6,7 @@ agent: build
 
 # Fix UI: $ARGUMENTS
 
-use_skill("frontend-aesthetics")
+skill({ name: "frontend-aesthetics" })
 
 1. **Analyze:** Delegate to @vision for initial assessment
    - If screenshots/videos provided, @vision describes issue in detail

package/dist/template/.opencode/command/fix.md

@@ -10,7 +10,7 @@ agent: build
 
 **Complex (unclear cause, multiple files):**
 
-use_skill("systematic-debugging")
+skill({ name: "systematic-debugging" })
 
 Follow four phases:
 

package/dist/template/.opencode/command/handoff.md

@@ -6,6 +6,8 @@ agent: build
 
 # Handoff
 
+**Load skill:** `skill({ name: "verification-before-completion" })`
+
 ## Phase 1: Gather State
 
 ```bash

package/dist/template/.opencode/command/implement.md

@@ -6,6 +6,10 @@ agent: build
 
 # Implement
 
+**Load skill:** `skill({ name: "test-driven-development" })`
+
+For large tasks with 3+ phases, also load: `skill({ name: "subagent-driven-development" })`
+
 ## Phase 1: Setup Workspace
 
 ```bash
@@ -27,6 +31,16 @@ Create branch if not on bead branch:
 git checkout -b <bead-id>
 ```
 
+**Multi-agent coordination (if Beads Village available):**
+
+Initialize your agent session and claim the task:
+
+```
+init(team="project", role="<your-role>")
+```
+
+This registers you in the workspace. If another agent is working on the same task, you'll be notified.
+
 ## Phase 2: Load Context
 
 **Check for previous session work:**
@@ -96,6 +110,16 @@ Mode: [Quick/Planned]
 
 ## Phase 4: Implementation
 
+**Reserve files before editing (if Beads Village available):**
+
+Before making changes, lock the files you'll modify to prevent conflicts with other agents:
+
+```
+reserve(paths=["src/auth.ts", "src/utils/**"])
+```
+
+This creates an advisory lock. Other agents will see your reservation and avoid those files.
+
 ### With Plan (Planned Mode)
 
 For each unchecked step in plan.md:
@@ -139,7 +163,13 @@ If "pause" or "stop": Run `/handoff <bead-id>`.
 
 ## Phase 6: Complete
 
-When done:
+When done, release any file reservations (if Beads Village available):
+
+```
+release()
+```
+
+Then report:
 
 ```
 Implementation Complete: <bead-id>

package/dist/template/.opencode/command/import-plan.md

@@ -6,6 +6,8 @@ agent: build
 
 # Import Plan
 
+**Load skill:** `skill({ name: "executing-plans" })`
+
 Import a markdown plan into Beads epics and issues. Follows Steve Yegge's "plan outside, import inside" pattern.
 
 ## Phase 1: Load Plan

package/dist/template/.opencode/command/integration-test.md

@@ -6,7 +6,11 @@ agent: build
 
 # Integration Test: $ARGUMENTS
 
-Use `use_skill("test-driven-development")` for integration testing.
+**Load skills:**
+
+- `skill({ name: "test-driven-development" })`
+- `skill({ name: "condition-based-waiting" })` (for async tests)
+- `skill({ name: "testing-anti-patterns" })` (avoid common mistakes)
 
 ## Task Validation
 
@@ -16,7 +20,7 @@ Use `use_skill("test-driven-development")` for integration testing.
 
 ## Workflow
 
-1. **Load skill** - `use_skill("test-driven-development")`
+1. **Load skill** - `skill({ name: "test-driven-development" })`
 2. **Follow TDD cycle:**
    - Write failing integration test first
    - Verify it fails for the right reason

package/dist/template/.opencode/command/new-feature.md

@@ -7,6 +7,8 @@ model: proxypal/gemini-3-flash-preview
 
 # New Feature: $ARGUMENTS
 
+**Load skill:** `skill({ name: "brainstorming" })`
+
 Create a complete feature track with bead, specification, and implementation plan.
 
 ## Instructions

package/dist/template/.opencode/command/plan.md

@@ -6,6 +6,8 @@ agent: planner
 
 # Plan
 
+**Load skill:** `skill({ name: "writing-plans" })`
+
 ## Phase 1: Load Context
 
 ```bash

package/dist/template/.opencode/command/pr.md

@@ -3,6 +3,8 @@ description: Create and submit pull request with bead traceability
 argument-hint: "[bead-id]"
 ---
 
+**Load skill:** `skill({ name: "verification-before-completion" })`
+
 ## Create Pull Request
 
 **Current Branch:** `!git branch --show-current`

package/dist/template/.opencode/command/research-and-implement.md

@@ -16,6 +16,6 @@ Fix directly with clear comments. Commit.
 2. Load constraints from `.beads/artifacts/$ARGUMENTS/spec.md`
 3. Research within scope: `/research $ARGUMENTS`
 4. Plan approach: `/plan $ARGUMENTS`
-5. Implement with TDD: `use_skill("test-driven-development")`
+5. Implement with TDD: `skill({ name: "test-driven-development" })`
 6. Complete review: `.beads/artifacts/$ARGUMENTS/review.md`
 7. Run `/finish $ARGUMENTS`

package/dist/template/.opencode/command/research-ui.md

@@ -7,7 +7,7 @@ model: proxypal/gemini-3-flash-preview
 
 # Research UI: $ARGUMENTS
 
-use_skill("ui-ux-research")
+skill({ name: "ui-ux-research" })
 
 Research UI/UX patterns, implementations, or design topics.
 

package/dist/template/.opencode/command/resume.md

@@ -6,6 +6,8 @@ agent: build
 
 # Resume
 
+**Load skill:** `skill({ name: "executing-plans" })`
+
 ## Phase 1: Load Previous Session Context
 
 **Check recent sessions:**

package/dist/template/.opencode/command/revert-feature.md

@@ -7,6 +7,8 @@ model: proxypal/gemini-3-flash-preview
 
 # Revert Feature: $ARGUMENTS
 
+**Load skill:** `skill({ name: "verification-before-completion" })`
+
 Intelligently revert changes for a bead with git awareness.
 
 ## Instructions

package/dist/template/.opencode/command/review-codebase.md

@@ -6,7 +6,7 @@ agent: review
 
 # Review: $ARGUMENTS
 
-use_skill("requesting-code-review")
+skill({ name: "requesting-code-review" })
 
 If bead exists, review against `.beads/artifacts/$ARGUMENTS/spec.md` constraints.
 

package/dist/template/.opencode/command/skill-create.md

@@ -6,11 +6,11 @@ agent: build
 
 # Create Skill: $ARGUMENTS
 
-Use `use_skill("writing-skills")` to create a new skill.
+Use `skill({ name: "writing-skills" })` to create a new skill.
 
 ## Workflow
 
-1. **Load skill** - `use_skill("writing-skills")`
+1. **Load skill** - `skill({ name: "writing-skills" })`
 2. **Follow by TDD process** - Test with subagents before writing
 3. **Save to** `.opencode/skill/$ARGUMENTS/`
 
@@ -25,5 +25,5 @@ Use `use_skill("writing-skills")` to create a new skill.
 
 ## After Creation
 
-- Test with `use_skill("testing-skills-with-subagents")`
-- Share upstream with `use_skill("sharing-skills")`
+- Test with `skill({ name: "testing-skills-with-subagents" })`
+- Share upstream with `skill({ name: "sharing-skills" })`

package/dist/template/.opencode/command/skill-optimize.md

@@ -6,14 +6,14 @@ agent: build
 
 # Optimize Skill: $ARGUMENTS
 
-Use `use_skill("writing-skills")` to optimize an existing skill.
+Use `skill({ name: "writing-skills" })` to optimize an existing skill.
 
 ## Workflow
 
 1. **Read current skill** from `.opencode/skill/$ARGUMENTS/` or `.opencode/superpowers/skills/$ARGUMENTS/`
-2. **Load skill** - `use_skill("writing-skills")`
+2. **Load skill** - `skill({ name: "writing-skills" })`
 3. **Apply TDD process** - Test, refine, verify
-4. **Test changes** with `use_skill("testing-skills-with-subagents")`
+4. **Test changes** with `skill({ name: "testing-skills-with-subagents" })`
 
 ## Optimization Goals
 
@@ -25,4 +25,4 @@ Use `use_skill("writing-skills")` to optimize an existing skill.
 ## After Optimization
 
 - Verify with subagent testing
-- Share improvements upstream with `use_skill("sharing-skills")`
+- Share improvements upstream with `skill({ name: "sharing-skills" })`

package/dist/template/.opencode/command/ui-review.md

@@ -7,8 +7,8 @@ model: proxypal/gemini-3-pro-preview
 
 # UI Review: $ARGUMENTS
 
-use_skill("frontend-aesthetics")
-use_skill("visual-analysis")
+skill({ name: "frontend-aesthetics" })
+skill({ name: "visual-analysis" })
 
 Review UI/UX design for quality, aesthetics, and best practices.