opencodekit 0.0.1

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

@@ -0,0 +1,127 @@
+---
+description: Resume work on a bead from handoff
+argument-hint: "<bead-id>"
+agent: build
+---
+
+# Resume
+
+## Phase 1: Load Previous Session Context
+
+**Check recent sessions:**
+
+```bash
+list_sessions(project="current", limit=5)
+```
+
+**Load last session context:**
+
+```bash
+read_session("last", project="current")
+```
+
+Review:
+
+- What was implemented
+- File changes made
+- Where work stopped
+
+## Phase 2: Load Bead
+
+```bash
+bd show $ARGUMENTS --json
+```
+
+## Phase 3: Find Latest Handoff
+
+```bash
+ls -t .beads/artifacts/<bead-id>/handoffs/ 2>/dev/null | head -1
+```
+
+If no handoffs: "No handoff found. Use `/start <bead-id>` instead."
+
+Read latest handoff:
+
+```bash
+cat .beads/artifacts/<bead-id>/handoffs/<latest>.md
+```
+
+## Phase 4: Verify Git State
+
+Check current state matches handoff:
+
+```bash
+git branch --show-current
+git rev-parse HEAD
+git status --porcelain
+```
+
+**If branch mismatch:**
+
+```bash
+git checkout <bead-id>
+```
+
+**If commit mismatch:**
+
+```
+Warning: Current commit differs from handoff.
+Handoff: [hash from handoff]
+Current: [current hash]
+
+Continue anyway? (yes/no)
+```
+
+## Phase 5: Load Context
+
+Read all artifacts:
+
+```bash
+cat .beads/artifacts/<bead-id>/spec.md
+cat .beads/artifacts/<bead-id>/research.md 2>/dev/null
+cat .beads/artifacts/<bead-id>/plan.md 2>/dev/null
+```
+
+## Phase 6: Report & Continue
+
+```
+Resuming: <bead-id>
+━━━━━━━━━━━━━━━━━
+
+Title: [title]
+Branch: [branch]
+Handoff: [timestamp]
+Last Session: [from read_session]
+
+## Progress
+
+Completed:
+- [x] [from handoff]
+
+In Progress:
+- [ ] [from handoff] - [where stopped]
+
+Remaining:
+- [ ] [from handoff]
+
+## Previous Session Summary
+
+[Key points from read_session output]
+
+## Resume Instructions
+
+[Instructions from handoff]
+
+## Next Action
+
+[Based on progress, suggest next command]
+```
+
+**Determine next action:**
+
+| State                      | Action                 |
+| -------------------------- | ---------------------- |
+| No research.md             | `/research <bead-id>`  |
+| No plan.md                 | `/plan <bead-id>`      |
+| Has plan, incomplete steps | `/implement <bead-id>` |
+| All steps complete         | `/finish <bead-id>`    |

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

@@ -0,0 +1,13 @@
+---
+description: Review code for quality and compliance
+argument-hint: "[path or task-id]"
+agent: review
+---
+
+# Review: $ARGUMENTS
+
+use_skill("requesting-code-review")
+
+If bead exists, review against `.beads/artifacts/$ARGUMENTS/spec.md` constraints.
+
+Otherwise, general code quality review.

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

@@ -0,0 +1,29 @@
+---
+description: Create custom skills for agents
+argument-hint: "[skill-name]"
+agent: build
+---
+
+# Create Skill: $ARGUMENTS
+
+Use `use_skill("writing-skills")` to create a new skill.
+
+## Workflow
+
+1. **Load skill** - `use_skill("writing-skills")`
+2. **Follow the TDD process** - Test with subagents before writing
+3. **Save to** `.opencode/skills/$ARGUMENTS/`
+
+## Skill Structure
+
+```
+.opencode/skills/$ARGUMENTS/
+├── SKILL.md          (Main skill definition)
+├── instructions.md   (Detailed instructions)
+└── tests/            (Test scenarios)
+```
+
+## After Creation
+
+- Test with `use_skill("testing-skills-with-subagents")`
+- Share upstream with `use_skill("sharing-skills")`

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

@@ -0,0 +1,28 @@
+---
+description: Optimize an existing agent skill
+argument-hint: "[skill-name]"
+agent: build
+---
+
+# Optimize Skill: $ARGUMENTS
+
+Use `use_skill("writing-skills")` to optimize an existing skill.
+
+## Workflow
+
+1. **Read current skill** from `.opencode/skills/$ARGUMENTS/` or `.opencode/superpowers/skills/$ARGUMENTS/`
+2. **Load skill** - `use_skill("writing-skills")`
+3. **Apply TDD process** - Test, refine, verify
+4. **Test changes** with `use_skill("testing-skills-with-subagents")`
+
+## Optimization Goals
+
+- Reduce verbosity
+- Close rationalization loopholes
+- Add missing constraints
+- Improve clarity
+
+## After Optimization
+
+- Verify with subagent testing
+- Share improvements upstream with `use_skill("sharing-skills")`

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

@@ -0,0 +1,109 @@
+---
+description: Show task and project status
+agent: explore
+---
+
+# Project Status
+
+## Quick Summary
+
+1. **Git:** Current branch, uncommitted changes
+2. **Tasks:** `bd list` - count by status
+3. **CI:** Any build issues
+4. **Sessions:** Recent activity
+
+## Recent Session Activity
+
+```bash
+list_sessions(project="current", since="today", limit=5)
+```
+
+Show:
+
+- Session IDs and timestamps
+- Message counts
+- File changes per session
+- Active work periods
+
+**Output:**
+
+```
+TODAY'S SESSIONS
+
+1. ses_abc123 - 2:30 PM
+   Messages: 45, Files: 12
+   Changes: +234/-56
+
+2. ses_def456 - 11:00 AM
+   Messages: 28, Files: 8
+   Changes: +112/-23
+
+Activity: 2 sessions, 73 messages, 20 files modified
+```
+
+## Task Compliance
+
+```bash
+bd list --status open
+```
+
+For each bead, check `.beads/artifacts/<bead-id>/`:
+
+- [ ] spec.md exists
+- [ ] research.md exists (if needed)
+- [ ] plan.md exists (if needed)
+
+**Output:**
+
+```
+TASK COMPLIANCE
+
+Complete (spec + plan):
+- bd-a1b2: In Progress - [title]
+- bd-c3d4: Open - [title]
+
+Incomplete (missing files):
+- bd-e5f6: Missing spec.md
+
+Compliance: X/Y beads complete
+```
+
+## Active Tasks
+
+For `bd list --status in-progress`:
+
+- Bead ID, Title, Priority
+- Goal from spec.md
+- Progress from plan.md checkboxes
+- Last session activity (if available via read_session)
+
+## Required Actions
+
+| State           | Action                 |
+| --------------- | ---------------------- |
+| Missing spec    | `/create`              |
+| Has spec        | `/start <bead-id>`     |
+| In Progress     | `/implement <bead-id>` |
+| Ready to finish | `/finish <bead-id>`    |
+
+## Session Insights
+
+**If token usage high (>120k):**
+
+```
+⚠️  Current session: [current token count]
+
+Recommend: Start fresh session for next task
+- Current work will be in read_session("last")
+- Lower cost, better performance
+```
+
+**If multiple incomplete sessions:**
+
+```
+Recent incomplete work:
+- ses_abc123: [title from last message]
+- ses_def456: [title from last message]
+
+Consider: Review with read_session("<id>") to decide continue or close
+```

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

@@ -0,0 +1,28 @@
+---
+description: Review UI/UX design or mockup
+argument-hint: "[path to image or component]"
+agent: review
+---
+
+# UI Review: $ARGUMENTS
+
+use_skill("ui-ux-research")
+use_skill("frontend-aesthetics")
+
+## How to Analyze
+
+First, determine what you're reviewing. If it's an image or screenshot, start Gemini in interactive mode and reference the image to analyze it. If it's component code, analyze it directly with local tools. For large codebases spanning many files, use Gemini's non-interactive mode to scan the entire directory.
+
+## What to Look For
+
+Check typography first—generic fonts like Inter or Roboto are signs of "AI slop" aesthetics. Look at the color palette for overused patterns like purple gradients or flat white backgrounds. Assess whether the UI has any motion or micro-interactions, and whether backgrounds feel atmospheric or just flat.
+
+For accessibility, verify color contrast meets WCAG AA minimum, check for ARIA labels on interactive elements, ensure keyboard navigation works, and confirm focus indicators are visible.
+
+## Recommendations
+
+Provide specific, actionable improvements: suggest alternative fonts, propose color palette changes, identify opportunities for subtle animations, and recommend layout enhancements. Include code snippets when they would help clarify the suggestion.
+
+## Output
+
+Summarize what issues you found, what specific changes you recommend, and show before/after comparisons for significant improvements.

package/dist/template/.opencode/dcp.jsonc

@@ -0,0 +1,34 @@
+{
+  // Enable or disable the plugin
+  "enabled": true,
+  // Enable debug logging to ~/.config/opencode/logs/dcp/
+  "debug": false,
+  // Override model for analysis (format: "provider/model", e.g. "anthropic/claude-haiku-4-5")
+  // "model": "anthropic/claude-haiku-4-5",
+  // Show toast notifications when model selection fails
+  "showModelErrorToasts": true,
+  // Only run AI analysis with session model or configured model (disables fallback models)
+  "strictModelSelection": true,
+  // AI analysis strategies (deduplication runs automatically on every request)
+  "strategies": {
+    // Strategies to run when session goes idle
+    "onIdle": ["ai-analysis"],
+    // Strategies to run when AI calls prune tool
+    "onTool": ["ai-analysis"],
+  },
+  // Summary display: "off", "minimal", or "detailed"
+  // Note: "detailed" may cause issues with extended thinking models
+  "pruning_summary": "off",
+  // How often to nudge the AI to prune (every N tool results, 0 = disabled)
+  "nudge_freq": 10,
+  // Tools that are never pruned (plugin defaults)
+  "protectedTools": [
+    "task",
+    "todowrite",
+    "todoread",
+    "prune",
+    "batch",
+    "write",
+    "edit",
+  ],
+}

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

@@ -0,0 +1,128 @@
+# Memory System README
+
+## Overview
+
+The memory/ directory provides persistent cross-session context for OpenCode agents. This enables continuity and learning over time.
+
+## Structure
+
+```
+memory/
+├── _templates/                  # Document templates
+│   ├── spec.md                 # Template for task specifications
+│   ├── research.md             # Template for research documents
+│   └── session.md              # Template for session memory
+├── memory.md                    # Current project state and session learnings
+├── todo.md                      # Task tracking and progress
+├── development-guidelines.md    # Code conventions and patterns
+├── architecture-decisions.md    # Why we built it this way
+├── blockers.md                  # Known issues and workarounds
+│
+├── research/                    # Research findings and analysis
+│   ├── YYYY-MM-DD-topic.md     # Research documents
+│   └── cache-topic.md          # Research cache files
+│
+├── design-guidelines.md        # Design system and UI standards
+├── decisions/                   # Architectural decision records
+│   └── database-choice.md       # Example: Why PostgreSQL
+│
+└── plans/                       # Strategic planning documents
+    └── q4-roadmap.md            # Example: Quarterly objectives
+```
+
+**Subdirectories:** Use to organize knowledge by category and prevent flat directory bloat.
+
+## Usage
+
+### For Agents
+
+**At Session Start:**
+
+1. Read `memory.md` for current project context
+2. Check `todo.md` for active tasks
+3. Review `blockers.md` for known issues
+
+**During Session:**
+
+- Consult `development-guidelines.md` for coding standards
+- Reference `architecture-decisions.md` for design rationale
+- Reference `design-guidelines.md` for design standards
+- Update progress in `todo.md`
+- Save research to `research/YYYY-MM-DD-topic.md` (auto-created by /research command)
+- Document decisions in `decisions/choice-name.md`
+- Create specs using templates from `_templates/spec.md`
+
+**At Session End:**
+
+- Update `memory.md` with new learnings
+- Mark completed tasks in `todo.md`
+- Document new blockers or resolve existing ones
+
+### For Humans
+
+**Quick Status Check:**
+
+```bash
+# See current state
+cat memory/memory.md
+
+# Check active tasks
+cat memory/todo.md
+
+# Review blockers
+cat memory/blockers.md
+```
+
+**Update Memory:**
+Edit files directly or use memory-update tool - agents will read on next session.
+
+**Examples:**
+
+```bash
+# Read research notes
+memory-read research/opencode-sessions
+
+# Create new research note
+memory-update research/new-topic content="# Research Notes\n..."
+
+# Add decision record
+memory-update decisions/database-choice content="# Why PostgreSQL\n..."
+
+# Tools auto-create subdirectories and strip .md extension
+```
+
+## Memory Lifecycle
+
+### Compaction (When memory.md > 5000 words)
+
+1. Distill to critical facts only
+2. Archive detailed history to dated file: `memory-archive-YYYY-MM-DD.md`
+3. Keep current state lean and focused
+
+### Rotation
+
+- Archive completed tasks monthly
+- Move resolved blockers to history section
+- Keep active memory under 5000 words
+
+## Integration Points
+
+- **Plan Agent:** Reads memory.md before creating plans
+- **Build Agent:** Updates memory.md after major completions
+- **All Agents:** Consult development-guidelines.md for standards
+- **Design Agent:** Consults design-guidelines.md for design standards
+
+## Best Practices
+
+1. **Be Specific:** "Uses React 18 Server Components" vs "Uses React"
+2. **Date Decisions:** Track when and why choices were made
+3. **Keep Current:** Update after significant progress, not every trivial change
+4. **Prune Regularly:** Remove obsolete information
+5. **Link Context:** Reference related files/specs when relevant
+
+## Future Enhancements
+
+- Automatic memory compaction triggers
+- Memory-read and memory-update tools
+- Integration with task ledgers
+- Progress monitoring and re-planning triggers

package/dist/template/.opencode/memory/_templates/handoff.md

@@ -0,0 +1,33 @@
+# Handoff: [Phase Name]
+
+**Date:** YYYY-MM-DD
+**From:** [Current phase/agent]
+**To:** [Next phase/agent]
+**Task:** [Task ID if applicable]
+
+## Summary
+
+[1-2 sentences: What was accomplished in this phase]
+
+## Relevant Files
+
+- `@path/to/file1` - [Why needed]
+- `@path/to/file2` - [Why needed]
+
+## Key Decisions
+
+- [Decision 1]: [Rationale]
+- [Decision 2]: [Rationale]
+
+## Constraints
+
+- [Constraint that must be followed]
+- [Limitation to be aware of]
+
+## Next Instructions
+
+[Clear prompt for the next agent - what exactly to do next]
+
+## Open Questions
+
+- [Unresolved question for next phase]

package/dist/template/.opencode/memory/_templates/research.md

@@ -0,0 +1,29 @@
+# Research: [Topic]
+
+**Date:** YYYY-MM-DD
+**Context:** [Why this research was needed]
+
+## Question
+
+[The specific question or problem being researched]
+
+## Findings
+
+### [Finding 1]
+
+- [Key insight]
+- Source: [URL or document]
+
+### [Finding 2]
+
+- [Key insight]
+- Source: [URL or document]
+
+## Decision
+
+[Clear recommendation based on findings]
+
+## Next Steps
+
+1. [Action item]
+2. [Action item]

package/dist/template/.opencode/memory/_templates/task-prd.md

@@ -0,0 +1,43 @@
+# Task PRD Template
+
+**Task ID:** [auto-generated]
+**Created:** [date]
+**Status:** To Do
+
+## Goal
+
+What exactly are we building and why does it exist in the product?
+
+## Scope
+
+### In-Scope:
+
+- [List what's allowed]
+
+### Out-of-Scope:
+
+- [List what's explicitly off-limits]
+
+## User Flow
+
+The literal step-by-step of what the user sees/does:
+
+1. [Step 1]
+2. [Step 2]
+3. [Step 3]
+
+## Success Criteria
+
+The exact conditions under which I consider this done:
+
+- [ ] [Specific, measurable criteria 1]
+- [ ] [Specific, measurable criteria 2]
+- [ ] [Specific, measurable criteria 3]
+
+## Dependencies
+
+- [List any prerequisites or blocking tasks]
+
+## Notes
+
+[Additional context or constraints]

package/dist/template/.opencode/memory/_templates/task-review.md

@@ -0,0 +1,73 @@
+# Task Review Template
+
+**Task ID:** [auto-generated]
+**Completed:** [date]
+**Status:** Done
+
+## What Changed
+
+### Files Modified:
+
+- `src/[file1.js]` - [brief description of changes]
+- `src/[file2.js]` - [brief description of changes]
+- `tests/[test.js]` - [brief description of changes]
+
+### Logic Added:
+
+- [New functionality implemented]
+- [Key algorithms or business logic]
+- [Data flow changes]
+
+### Files Created:
+
+- [List any new files created]
+
+## What Skipped
+
+### Intentionally Not Done:
+
+- [Feature X - reason: out of scope for this task]
+- [Optimization Y - reason: will be separate task]
+- [Test case Z - reason: requires additional setup]
+
+### Known Limitations:
+
+- [Limitation 1 - temporary workaround]
+- [Limitation 2 - technical debt introduced]
+- [Limitation 3 - performance considerations]
+
+## Inconsistencies with Architecture
+
+### Deviations from Spec:
+
+- [What was supposed to happen vs what actually happened]
+- [Why the deviation was necessary]
+- [Impact on overall architecture]
+
+### Unexpected Challenges:
+
+- [Problem 1 encountered and how solved]
+- [Problem 2 encountered and how solved]
+- [Problem 3 encountered and how solved]
+
+## Validation Results
+
+### Success Criteria Met:
+
+- [x] [Criteria 1 from PRD - how verified]
+- [x] [Criteria 2 from PRD - how verified]
+- [x] [Criteria 3 from PRD - how verified]
+
+### Test Results:
+
+- [Test suite results summary]
+- [Performance benchmarks]
+- [Security validations]
+
+## Next Micro-Task
+
+[Immediate next step or follow-up task needed]
+
+## Lessons Learned
+
+[What worked well, what didn't, what to improve for future tasks]