opencodekit 0.6.7 → 0.7.0

package/dist/template/.opencode/package.json

@@ -1,22 +1,22 @@
 {
-  "name": "opencode",
-  "version": "1.0.0",
-  "description": "Opencode plugin",
-  "type": "module",
-  "main": "index.js",
-  "scripts": {
-    "type-check": "tsc --noEmit"
-  },
-  "keywords": [],
-  "author": "",
-  "license": "ISC",
-  "dependencies": {
-    "@opencode-ai/plugin": "1.0.207"
-  },
-  "devDependencies": {
-    "@types/node": "^25.0.3",
-    "fs": "^0.0.1-security",
-    "path": "^0.12.7",
-    "typescript": "^5.9.3"
-  }
+	"name": "opencode",
+	"version": "1.0.0",
+	"description": "Opencode plugin",
+	"type": "module",
+	"main": "index.js",
+	"scripts": {
+		"type-check": "tsc --noEmit"
+	},
+	"keywords": [],
+	"author": "",
+	"license": "ISC",
+	"dependencies": {
+		"@opencode-ai/plugin": "^1.0.209"
+	},
+	"devDependencies": {
+		"@types/node": "^25.0.3",
+		"fs": "^0.0.1-security",
+		"path": "^0.12.7",
+		"typescript": "^5.9.3"
+	}
 }

package/dist/template/.opencode/skill/brainstorming/SKILL.md

@@ -46,8 +46,8 @@ Start by understanding the current project context, then ask questions one at a
 **Implementation (if continuing):**
 
 - Ask: "Ready to set up for implementation?"
-- Use use_skill("using-git-worktrees") to create isolated workspace
-- Use use_skill("writing-plans") to create detailed implementation plan
+- Use skill({ name: "using-git-worktrees" }) to create isolated workspace
+- Use skill({ name: "writing-plans" }) to create detailed implementation plan
 
 ## Key Principles
 

package/dist/template/.opencode/skill/executing-plans/SKILL.md

@@ -54,7 +54,7 @@ Based on feedback:
 After all tasks complete and verified:
 
 - Announce: "I'm using finishing-a-development-branch skill to complete this work."
-- **REQUIRED SUB-SKILL:** Use use_skill("finishing-a-development-branch")
+- **REQUIRED SUB-SKILL:** Use skill({ name: "finishing-a-development-branch" })
 - Follow that skill to verify tests, present options, execute choice
 
 ## When to Stop and Ask for Help

package/dist/template/.opencode/skill/sharing-skills/SKILL.md

@@ -14,12 +14,14 @@ Contribute skills from your local branch back to the upstream repository.
 ## When to Share
 
 **Share when:**
+
 - Skill applies broadly (not project-specific)
 - Pattern/technique others would benefit from
 - Well-tested and documented
 - Follows writing-skills guidelines
 
 **Keep personal when:**
+
 - Project-specific or organization-specific
 - Experimental or unstable
 - Contains sensitive information
@@ -28,7 +30,7 @@ Contribute skills from your local branch back to the upstream repository.
 ## Prerequisites
 
 - `gh` CLI installed and authenticated
-- Working directory is `~/.config/superpowers/skills/` (your local clone)
+- Working directory is `.opencode/skill/` (your project skills)
 - **REQUIRED:** Skill has been tested using writing-skills TDD process
 
 ## Sharing Workflow
@@ -36,7 +38,7 @@ Contribute skills from your local branch back to the upstream repository.
 ### 1. Ensure You're on Main and Synced
 
 ```bash
-cd ~/.config/superpowers/skills/
+cd .opencode/skill/
 git checkout main
 git pull upstream main
 git push origin main  # Push to your fork
@@ -105,7 +107,7 @@ Here's a complete example of sharing a skill called "async-patterns":
 
 ```bash
 # 1. Sync with upstream
-cd ~/.config/superpowers/skills/
+cd .opencode/skill/
 git checkout main
 git pull upstream main
 git push origin main
@@ -146,14 +148,16 @@ Addresses common async pitfalls like race conditions, improper error handling, a
 Once your PR is merged:
 
 1. Sync your local main branch:
+
 ```bash
-cd ~/.config/superpowers/skills/
+cd .opencode/skill/
 git checkout main
 git pull upstream main
 git push origin main
 ```
 
 2. Delete the feature branch:
+
 ```bash
 git branch -d "add-${skill_name}-skill"
 git push origin --delete "add-${skill_name}-skill"
@@ -162,18 +166,22 @@ git push origin --delete "add-${skill_name}-skill"
 ## Troubleshooting
 
 **"gh: command not found"**
+
 - Install GitHub CLI: https://cli.github.com/
 - Authenticate: `gh auth login`
 
 **"Permission denied (publickey)"**
+
 - Check SSH keys: `gh auth status`
 - Set up SSH: https://docs.github.com/en/authentication
 
 **"Skill already exists"**
+
 - You're creating a modified version
 - Consider different skill name or coordinate with the skill's maintainer
 
 **PR merge conflicts**
+
 - Rebase on latest upstream: `git fetch upstream && git rebase upstream/main`
 - Resolve conflicts
 - Force push: `git push -f origin your-branch`
@@ -183,6 +191,7 @@ git push origin --delete "add-${skill_name}-skill"
 **Do NOT batch multiple skills in one PR.**
 
 Each skill should:
+
 - Have its own feature branch
 - Have its own PR
 - Be independently reviewable

package/dist/template/.opencode/skill/subagent-driven-development/SKILL.md

@@ -113,7 +113,7 @@ After all tasks complete, dispatch final review:
 After final review passes:
 
 - Announce: "I'm using finishing-a-development-branch skill to complete this work."
-- **REQUIRED SUB-SKILL:** Use use_skill("finishing-a-development-branch")
+- **REQUIRED SUB-SKILL:** Use skill({ name: "finishing-a-development-branch" })
 - Follow that skill to verify tests, present options, execute choice
 
 ## Example Workflow

package/dist/template/.opencode/skill/systematic-debugging/SKILL.md

@@ -116,7 +116,7 @@ You MUST complete each phase before proceeding to the next.
 
    **WHEN error is deep in call stack:**
 
-   **REQUIRED SUB-SKILL:** Use use_skill("root-cause-tracing") for backward tracing technique
+   **REQUIRED SUB-SKILL:** Use skill({ name: "root-cause-tracing" }) for backward tracing technique
 
    **Quick version:**
    - Where does bad value originate?
@@ -181,7 +181,7 @@ You MUST complete each phase before proceeding to the next.
    - Automated test if possible
    - One-off test script if no framework
    - MUST have before fixing
-   - **REQUIRED SUB-SKILL:** Use use_skill("test-driven-development") for writing proper failing tests
+   - **REQUIRED SUB-SKILL:** Use skill({ name: "test-driven-development" }) for writing proper failing tests
 
 2. **Implement Single Fix**
    - Address the root cause identified

package/dist/template/.opencode/skill/using-git-worktrees/SKILL.md

@@ -27,23 +27,23 @@ ls -d worktrees 2>/dev/null      # Alternative
 
 **If found:** Use that directory. If both exist, `.worktrees` wins.
 
-### 2. Check CLAUDE.md
+### 2. Check AGENTS.md
 
 ```bash
-grep -i "worktree.*director" CLAUDE.md 2>/dev/null
+grep -i "worktree.*director" AGENTS.md 2>/dev/null
 ```
 
 **If preference specified:** Use it without asking.
 
 ### 3. Ask User
 
-If no directory exists and no CLAUDE.md preference:
+If no directory exists and no AGENTS.md preference:
 
 ```
 No worktree directory found. Where should I create worktrees?
 
 1. .worktrees/ (project-local, hidden)
-2. ~/.config/superpowers/worktrees/<project-name>/ (global location)
+2. ~/.opencode/worktrees/<project-name>/ (global location)
 
 Which would you prefer?
 ```
@@ -62,13 +62,14 @@ grep -q "^\.worktrees/$" .gitignore || grep -q "^worktrees/$" .gitignore
 **If NOT in .gitignore:**
 
 Per Jesse's rule "Fix broken things immediately":
+
 1. Add appropriate line to .gitignore
 2. Commit the change
 3. Proceed with worktree creation
 
 **Why critical:** Prevents accidentally committing worktree contents to repository.
 
-### For Global Directory (~/.config/superpowers/worktrees)
+### For Global Directory (~/.opencode/worktrees)
 
 No .gitignore verification needed - outside project entirely.
 
@@ -88,8 +89,8 @@ case $LOCATION in
   .worktrees|worktrees)
     path="$LOCATION/$BRANCH_NAME"
     ;;
-  ~/.config/superpowers/worktrees/*)
-    path="~/.config/superpowers/worktrees/$project/$BRANCH_NAME"
+  ~/.opencode/worktrees/*)
+    path="~/.opencode/worktrees/$project/$BRANCH_NAME"
     ;;
 esac
 
@@ -143,31 +144,35 @@ Ready to implement <feature-name>
 
 ## Quick Reference
 
-| Situation | Action |
-|-----------|--------|
-| `.worktrees/` exists | Use it (verify .gitignore) |
-| `worktrees/` exists | Use it (verify .gitignore) |
-| Both exist | Use `.worktrees/` |
-| Neither exists | Check CLAUDE.md → Ask user |
+| Situation                   | Action                      |
+| --------------------------- | --------------------------- |
+| `.worktrees/` exists        | Use it (verify .gitignore)  |
+| `worktrees/` exists         | Use it (verify .gitignore)  |
+| Both exist                  | Use `.worktrees/`           |
+| Neither exists              | Check AGENTS.md → Ask user  |
 | Directory not in .gitignore | Add it immediately + commit |
-| Tests fail during baseline | Report failures + ask |
-| No package.json/Cargo.toml | Skip dependency install |
+| Tests fail during baseline  | Report failures + ask       |
+| No package.json/Cargo.toml  | Skip dependency install     |
 
 ## Common Mistakes
 
 **Skipping .gitignore verification**
+
 - **Problem:** Worktree contents get tracked, pollute git status
 - **Fix:** Always grep .gitignore before creating project-local worktree
 
 **Assuming directory location**
+
 - **Problem:** Creates inconsistency, violates project conventions
-- **Fix:** Follow priority: existing > CLAUDE.md > ask
+- **Fix:** Follow priority: existing > AGENTS.md > ask
 
 **Proceeding with failing tests**
+
 - **Problem:** Can't distinguish new bugs from pre-existing issues
 - **Fix:** Report failures, get explicit permission to proceed
 
 **Hardcoding setup commands**
+
 - **Problem:** Breaks on projects using different tools
 - **Fix:** Auto-detect from project files (package.json, etc.)
 
@@ -190,14 +195,16 @@ Ready to implement auth feature
 ## Red Flags
 
 **Never:**
+
 - Create worktree without .gitignore verification (project-local)
 - Skip baseline test verification
 - Proceed with failing tests without asking
 - Assume directory location when ambiguous
-- Skip CLAUDE.md check
+- Skip AGENTS.md check
 
 **Always:**
-- Follow directory priority: existing > CLAUDE.md > ask
+
+- Follow directory priority: existing > AGENTS.md > ask
 - Verify .gitignore for project-local
 - Auto-detect and run project setup
 - Verify clean test baseline
@@ -205,9 +212,11 @@ Ready to implement auth feature
 ## Integration
 
 **Called by:**
+
 - **brainstorming** (Phase 4) - REQUIRED when design is approved and implementation follows
 - Any skill needing isolated workspace
 
 **Pairs with:**
+
 - **finishing-a-development-branch** - REQUIRED for cleanup after work complete
 - **executing-plans** or **subagent-driven-development** - Work happens in this worktree

package/dist/template/.opencode/skill/{using-superpowers → using-skills}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: using-superpowers
+name: using-skills
 description: Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
 ---
 
@@ -53,6 +53,7 @@ If a skill for your task exists, you must use it or you will fail at your task.
 If a skill has a checklist, YOU MUST create TodoWrite todos for EACH item.
 
 **Don't:**
+
 - Work through checklist mentally
 - Skip creating todos "to save time"
 - Batch multiple items into one todo
@@ -66,6 +67,7 @@ Before using a skill, announce that you are using it.
 "I'm using [Skill Name] to [what you're doing]."
 
 **Examples:**
+
 - "I'm using the brainstorming skill to refine your idea into a design."
 - "I'm using the test-driven-development skill to implement this feature."
 
@@ -92,9 +94,10 @@ Your human partner's specific instructions describe WHAT to do, not HOW.
 ## Summary
 
 **Starting any task:**
+
 1. If relevant skill exists → Use the skill
-3. Announce you're using it
-4. Follow what it says
+2. Announce you're using it
+3. Follow what it says
 
 **Skill has checklist?** TodoWrite for every item.
 

package/dist/template/.opencode/skill/writing-plans/SKILL.md

@@ -34,7 +34,7 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 ```markdown
 # [Feature Name] Implementation Plan
 
-> **For Claude:** REQUIRED SUB-SKILL: Use use_skill("executing-plans") to implement this plan task-by-task.
+> **For Claude:** REQUIRED SUB-SKILL: Use skill({ name: "executing-plans" }) to implement this plan task-by-task.
 
 **Goal:** [One sentence describing what this builds]
 
@@ -111,11 +111,11 @@ After saving the plan, offer execution choice:
 **Which approach?"**
 
 **If Subagent-Driven chosen:**
-- **REQUIRED SUB-SKILL:** Use use_skill("subagent-driven-development")
+- **REQUIRED SUB-SKILL:** Use skill({ name: "subagent-driven-development" })
 - Stay in this session
 - Fresh subagent per task + code review
 
 **If Parallel Session chosen:**
 - Guide them to open new session in worktree
-- **REQUIRED SUB-SKILL:** New session uses use_skill("executing-plans")
+- **REQUIRED SUB-SKILL:** New session uses skill({ name: "executing-plans" })
 ```

package/dist/template/.opencode/skill/writing-skills/SKILL.md

@@ -282,7 +282,7 @@ wc -w skills/path/SKILL.md
 
 Use skill name only, with explicit requirement markers:
 
-- ✅ Good: `**REQUIRED SUB-SKILL:** Use use_skill("test-driven-development")`
+- ✅ Good: `**REQUIRED SUB-SKILL:** Use skill({ name: "test-driven-development" })`
 - ✅ Good: `**REQUIRED BACKGROUND:** You MUST understand systematic-debugging`
 - ❌ Bad: `See skills/testing/test-driven-development` (unclear if required)
 - ❌ Bad: `@skills/testing/test-driven-development/SKILL.md` (force-loads, burns context)
@@ -568,7 +568,7 @@ Run same scenarios WITH skill. Agent should now comply.
 
 Agent found new rationalization? Add explicit counter. Re-test until bulletproof.
 
-**REQUIRED SUB-SKILL:** Use use_skill("testing-skills-with-subagents") for the complete testing methodology:
+**REQUIRED SUB-SKILL:** Use skill({ name: "testing-skills-with-subagents" }) for the complete testing methodology:
 
 - How to write pressure scenarios
 - Pressure types (time, sunk cost, authority, exhaustion)

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "opencodekit",
-	"version": "0.6.7",
+	"version": "0.7.0",
 	"description": "CLI tool for bootstrapping and managing OpenCodeKit projects",
 	"type": "module",
 	"repository": {
@@ -35,6 +35,7 @@
 	"dependencies": {
 		"@clack/prompts": "^0.7.0",
 		"@opencode-ai/plugin": "^1.0.141",
+		"beads-village": "^1.3.3",
 		"cac": "^6.7.14",
 		"cli-table3": "^0.6.5",
 		"ora": "^9.0.0",

package/dist/template/.opencode/memory/handoffs/2025-12-27T103000Z.md

@@ -1,76 +0,0 @@
-# Handoff: test-handoff-plugin
-
-**Created:** 2025-12-27T10:30:00Z
-**Agent:** build
-
-## Provenance
-
-| Key    | Value                                               |
-| ------ | --------------------------------------------------- |
-| Repo   | git@github.com:opencodekit/opencodekit-template.git |
-| Branch | main                                                |
-| Commit | ae38a95f899300419e9b17030268cedc60ebb44f            |
-| Clean  | no                                                  |
-
-## Session Context
-
-**Current Session:** testing handoff plugin
-**Token Usage:** ~50k estimated
-
-Next session can load context with:
-
-```
-read_session("last", project="current")
-```
-
-## Progress
-
-### Completed
-
-- [x] Released v0.6.4 (version bump, changelog, tag, GitHub release)
-- [x] Reviewed Agent-Skills-for-Context-Engineering repo (verdict: mostly theory, not worth stealing)
-- [x] Reviewed Karpathy's hn-time-capsule (verdict: useful patterns)
-- [x] Created handoff plugin (`plugin/handoff.ts`)
-- [x] Updated `/handoff` command to instruct Ctrl+K
-
-### In Progress
-
-- [ ] Testing handoff plugin - verifying it injects context on compaction
-
-### Remaining
-
-- [ ] Commit new handoff plugin and updated command
-- [ ] Test full flow: handoff → Ctrl+K → new session with context
-
-## Context
-
-### Key Files
-
-- `.opencode/plugin/handoff.ts` - New plugin that injects handoff on compaction
-- `.opencode/command/handoff.md` - Updated to tell user to press Ctrl+K
-- `.opencode/plugin/compactor.ts` - Reference for plugin structure
-
-### Decisions Made
-
-- Use `experimental.session.compacting` hook to inject handoff context
-- Only inject handoffs < 1 hour old to prevent stale context
-- Search both `.opencode/memory/handoffs/` and `.beads/artifacts/` for handoffs
-
-### Blockers/Issues
-
-- OpenCode lacks `session.start` hook (Issue #5409) - can't auto-navigate to new session
-- Workaround: User must manually press Ctrl+K after /handoff
-
-## Resume Instructions
-
-1. Commit the new handoff plugin and updated command
-2. Test the full flow: run /handoff, press Ctrl+K, verify context injected
-3. If working, consider adding to v0.6.5 release
-
-**Recommended:** Start next session with `/resume test-handoff-plugin` to auto-load this handoff + previous session context.
-
-## Artifacts
-
-- spec.md: missing
-- research.md: missing
-- plan.md: missing