opencodekit 0.16.4 → 0.16.6

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

@@ -97,7 +97,7 @@ If memory search fails (Ollama not running), continue without it.
 
 Read all available context:
 
-!`cat .beads/artifacts/$ARGUMENTS/spec.md 2>/dev/null`
+!`cat .beads/artifacts/$ARGUMENTS/prd.md 2>/dev/null`
 !`cat .beads/artifacts/$ARGUMENTS/plan.md 2>/dev/null`
 !`cat .beads/artifacts/$ARGUMENTS/research.md 2>/dev/null`
 
@@ -108,8 +108,9 @@ Check if there was an active swarm for this task:
 ```typescript
 // Check for active swarm state
 const teamName = "$ARGUMENTS-swarm";
-const status = await swarm_monitor({
-  operation: "status",
+const status = await swarm({
+  operation: "monitor",
+  action: "status",
   team_name: teamName,
 });
 
@@ -118,8 +119,9 @@ if (stats.summary?.total_workers > 0) {
   console.log(`✓ Found active swarm with ${stats.summary.total_workers} workers`);
 
   // Show current progress
-  const ui = await swarm_monitor({
-    operation: "render_block",
+  const ui = await swarm({
+    operation: "monitor",
+    action: "render_block",
     team_name: teamName,
   });
   console.log(ui);
@@ -128,7 +130,7 @@ if (stats.summary?.total_workers > 0) {
 }
 
 // Sync beads to OpenCode todos for subagent visibility
-beads_sync({ operation: "push" });
+swarm({ operation: "sync", action: "push" });
 ```
 
 ## Check For Stale Context

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

@@ -141,7 +141,7 @@ If review finds issues, fix them, re-run verification gates, then re-run review.
 ## Verify Success Criteria
 
 ```bash
-cat .beads/artifacts/$ARGUMENTS/spec.md
+cat .beads/artifacts/$ARGUMENTS/prd.md
 ```
 
 Ensure all criteria are met before closing.

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

@@ -8,6 +8,8 @@ agent: build
 
 You're claiming a task and preparing to work on it. This is the entry point before implementation.
 
+> **Lifecycle context:** Ideation → Design → Specification → Task Conversion → Planning → **Implementation** → Verification
+>
 > **CCPM Philosophy:** One issue ≠ one task. One issue = multiple parallel work streams.
 > Agents are "context firewalls" - they do heavy work and return concise summaries.
 
@@ -23,6 +25,7 @@ You're claiming a task and preparing to work on it. This is the entry point befo
 ## Load Skills
 
 ```typescript
+skill({ name: "development-lifecycle" }); // Phase guidance
 skill({ name: "beads" });
 skill({ name: "beads-bridge" }); // For cross-session todo coordination
 skill({ name: "prd" }); // PRD creation workflow
@@ -35,7 +38,7 @@ skill({ name: "memory-system" });
 First-time setup per repo (prevents stale JSONL issues):
 
 ```bash
-bd hooks install 2>/dev/null || echo "Hooks already installed"
+br hooks install 2>/dev/null || echo "Hooks already installed"
 ```
 
 ## Current State
@@ -87,7 +90,7 @@ Make beads tasks visible to subagents via todoread:
 
 ```typescript
 // Push beads state to OpenCode todos
-beads_sync({ operation: "push" });
+swarm({ operation: "sync", action: "push" });
 ```
 
 This enables subagents to see task context via `todoread()` without beads access.
@@ -224,7 +227,6 @@ Task({
 
 Look for:
 
-- `spec.md` - Requirements and constraints
 - `prd.md` - PRD created via `prd` skill (defines WHAT to build)
 - `prd.json` - Executable tasks from `prd-task` skill
 - `progress.txt` - PRD execution progress (append-only)
@@ -305,13 +307,14 @@ const beadInfo = br show $ARGUMENTS --json;
 const taskTitle = beadInfo.title;
 const taskDescription = beadInfo.description;
 
-// Read spec/plan if exists for file context
-const specContent = read(".beads/artifacts/$ARGUMENTS/spec.md");
+// Read prd/plan if exists for file context
+const prdContent = read(".beads/artifacts/$ARGUMENTS/prd.md");
 const planContent = read(".beads/artifacts/$ARGUMENTS/plan.md");
 
 // Analyze THIS SPECIFIC task for parallel execution
-const analysis = swarm_plan({
-  operation: "analyze",
+const analysis = swarm({
+  operation: "plan",
+  action: "analyze",
   task: taskTitle,                    // User's actual task
   context: taskDescription,           // User's requirements
   files: "[files from spec/plan]",    // Actual affected files
@@ -340,7 +343,8 @@ The analysis returns **task-specific** streams:
 ```typescript
 // Iterate over streams from analysis - these are DYNAMIC based on task
 for (const stream of analysis.streams) {
-  swarm_delegate({
+  swarm({
+    operation: "delegate",
     bead_id: "$ARGUMENTS",
     title: stream.purpose, // From analysis, not hardcoded
     expected_outcome: `Complete ${stream.purpose} for task requirements`,
@@ -360,8 +364,9 @@ for (const stream of analysis.streams) {
 // Launch workers based on ACTUAL analysis results
 for (const stream of analysis.streams) {
   // Initialize monitoring for this stream
-  swarm_monitor({
-    operation: "progress_update",
+  swarm({
+    operation: "monitor",
+    action: "progress_update",
     team_name: "$ARGUMENTS-swarm",
     worker_id: stream.id,
     phase: "starting",
@@ -403,8 +408,9 @@ for (const stream of analysis.streams) {
 
 ```typescript
 // Render progress visualization
-swarm_monitor({
-  operation: "render_block",
+swarm({
+  operation: "monitor",
+  action: "render_block",
   team_name: "$ARGUMENTS-swarm",
 });
 ```
@@ -424,8 +430,9 @@ swarm_monitor({
 Before proceeding, verify parallelization makes sense:
 
 ```typescript
-swarm_plan({
-  operation: "check",
+swarm({
+  operation: "plan",
+  action: "check",
   task: taskTitle,
   files: analysis.streams.length,
   recommended_agents: analysis.recommended_agents,
@@ -495,14 +502,14 @@ Based on task type and what exists:
 
 ### For Tasks/Subtasks (leaf work)
 
-| Artifacts Found       | Next Step                                 |
-| --------------------- | ----------------------------------------- |
-| Nothing               | `/research $ARGUMENTS` or create PRD      |
-| Only spec.md          | `/plan $ARGUMENTS` or create PRD          |
-| prd.md (no prd.json)  | Run `prd-task` skill to convert to tasks  |
-| prd.json exists       | `/ship $ARGUMENTS` (PRD-driven execution) |
-| spec.md + research.md | `/plan $ARGUMENTS`                        |
-| plan.md exists        | `/ship $ARGUMENTS`                        |
+| Artifacts Found      | Next Step                                 |
+| -------------------- | ----------------------------------------- |
+| Nothing              | Ask user for task description             |
+| Only prd.md          | `/plan $ARGUMENTS` or use `prd-task`      |
+| prd.md (no prd.json) | Run `prd-task` skill to convert to tasks  |
+| prd.json exists      | `/ship $ARGUMENTS` (PRD-driven execution) |
+| prd.md + research.md | `/plan $ARGUMENTS`                        |
+| plan.md exists       | `/ship $ARGUMENTS`                        |
 
 ### PRD vs Plan Decision
 
@@ -530,10 +537,9 @@ Hierarchy:
 └── Children: [count or "none"]
 
 Artifacts:
-• spec.md: [exists/missing]
+• prd.md: [exists/missing]
 • research.md: [exists/missing]
 • plan.md: [exists/missing]
-• prd.md: [exists/missing]
 • prd.json: [exists/missing] ([N] tasks, [M] complete)
 
 [If PRD exists:]
@@ -607,7 +613,6 @@ Task({
 | Need                 | Command                          |
 | -------------------- | -------------------------------- |
 | Skip to implement    | `/ship $ARGUMENTS`               |
-| Create PRD first     | `/create $ARGUMENTS --prd`       |
 | Research first       | `/research $ARGUMENTS`           |
 | Plan implementation  | `/plan $ARGUMENTS`               |
 | Convert PRD to tasks | Use `prd-task` skill             |

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

@@ -22,9 +22,9 @@ Run all status checks simultaneously:
 
 ```
 # Beads CLI commands
-!`br status`
-!`br list --status in_progress --limit 10`
-!`br list --status ready --limit 10`
+!`br stats`
+!`br list --status in_progress`
+!`br ready`
 
 # Git state
 !`git status --porcelain`
@@ -33,10 +33,6 @@ Run all status checks simultaneously:
 ```
 
 ```typescript
-// Custom tools (message inbox, locks)
-bd - inbox({ n: 5, unread: true, to: "all" });
-bd - release(); // Lists active locks when called with no args
-
 // Built-in tools
 list_sessions({ project: "current", since: "today", limit: 5 });
 ```
@@ -114,11 +110,11 @@ TASK OVERVIEW
 
 IN PROGRESS
 ━━━━━━━━━━━
-ID       │ Priority │ Title                    │ Agent    │ Age
+ID       │ Priority │ Title                    │ Assignee │ Age
 ─────────┼──────────┼──────────────────────────┼──────────┼────────
-bd-abc12 │ P0       │ Fix auth regression      │ build    │ 2h
-bd-def34 │ P1       │ Add user dashboard       │ build    │ 1d
-bd-ghi56 │ P2       │ Refactor logging         │ build    │ 3h
+bd-abc12 │ P0       │ Fix auth regression      │ user     │ 2h
+bd-def34 │ P1       │ Add user dashboard       │ user     │ 1d
+bd-ghi56 │ P2       │ Refactor logging         │ user     │ 3h
 
 
 READY TO START
@@ -130,35 +126,6 @@ bd-xyz22 │ P2       │ Update API docs          │ -
 bd-xyz33 │ P2       │ Add analytics            │ bd-abc12
 
 
-MESSAGES
-━━━━━━━━
-[If unread messages exist:]
-📬 3 unread messages
-
-From        │ Subject                          │ Time
-────────────┼──────────────────────────────────┼────────
-build-1     │ Need API spec for dashboard      │ 2h ago
-review      │ Tests failing on staging         │ 4h ago
-build-2     │ Migration complete               │ 1d ago
-
-[If no messages:]
-📭 No unread messages
-
-
-FILE LOCKS
-━━━━━━━━━━
-[If locks exist:]
-🔒 2 active locks
-
-Path                           │ Owner     │ Expires
-───────────────────────────────┼───────────┼─────────
-src/auth/service.ts            │ build     │ 8m
-src/components/Dashboard.tsx   │ build     │ 15m
-
-[If no locks:]
-🔓 No active file locks
-
-
 GIT STATUS
 ━━━━━━━━━━
 Branch: feature/auth-refactor
@@ -255,7 +222,7 @@ Fri ██████████ 10
 
 ```typescript
 // Check memory system status
-memory_maintain({ operation: "status", older_than_days: 90, dry_run: false });
+memory_admin({ operation: "status" });
 ```
 
 Display memory stats in dashboard:
@@ -389,7 +356,7 @@ Handle gracefully:
 ```
 [If beads unavailable:]
 ⚠️ Beads database not initialized
-   Run: bd status to check connection
+   Run: br init
 
 [If git not available:]
 ⚠️ Not a git repository

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

@@ -48,7 +48,7 @@ ls .beads/artifacts/$ARGUMENTS/
 Read all artifacts:
 
 ```bash
-cat .beads/artifacts/$ARGUMENTS/spec.md 2>/dev/null
+cat .beads/artifacts/$ARGUMENTS/prd.md 2>/dev/null
 cat .beads/artifacts/$ARGUMENTS/plan.md 2>/dev/null
 cat .beads/artifacts/$ARGUMENTS/research.md 2>/dev/null
 cat .beads/artifacts/$ARGUMENTS/design.md 2>/dev/null
@@ -62,14 +62,14 @@ cat .beads/artifacts/$ARGUMENTS/design.md 2>/dev/null
 
 | Artifact      | Required | Status |
 | ------------- | -------- | ------ |
-| `spec.md`     | Yes      | [ ]    |
+| `prd.md`      | Yes      | [ ]    |
 | `plan.md`     | Yes      | [ ]    |
 | `research.md` | No       | [ ]    |
 | `design.md`   | No       | [ ]    |
 
-**Are all tasks in the spec addressed?**
+**Are all tasks in the PRD addressed?**
 
-Extract tasks/criteria from spec.md and verify each is implemented:
+Extract tasks/criteria from prd.md and verify each is implemented:
 
 ```markdown
 ## Completeness Report
@@ -149,12 +149,12 @@ golangci-lint run 2>&1 | tail -10
 
 Cross-reference artifacts for contradictions:
 
-| Check                        | Status | Issue                                |
-| ---------------------------- | ------ | ------------------------------------ |
-| spec.md ↔ plan.md            | ✓      | Plan addresses all spec requirements |
-| plan.md ↔ implementation     | ✓      | Code follows plan structure          |
-| research.md ↔ implementation | ⚠      | Didn't use recommended approach      |
-| design.md ↔ implementation   | ✓      | Follows design patterns              |
+| Check                        | Status | Issue                               |
+| ---------------------------- | ------ | ----------------------------------- |
+| prd.md ↔ plan.md             | ✓      | Plan addresses all PRD requirements |
+| plan.md ↔ implementation     | ✓      | Code follows plan structure         |
+| research.md ↔ implementation | ⚠      | Didn't use recommended approach     |
+| design.md ↔ implementation   | ✓      | Follows design patterns             |
 
 **Common coherence issues:**
 
@@ -234,7 +234,7 @@ if (missingTests) {
 Record verification results in bead:
 
 ```bash
-bd note $ARGUMENTS "Verification: [PASS|PARTIAL|FAIL] - [summary]"
+br comments add $ARGUMENTS "Verification: [PASS|PARTIAL|FAIL] - [summary]"
 ```
 
 ---

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

@@ -1,59 +1,89 @@
 ---
-purpose: Persistent project knowledge that survives across sessions
-updated: 2024-12-21
+purpose: PARA-organized memory system with SQLite backing
+updated: 2026-02-04
 ---
 
 # Project Memory
 
-This directory stores persistent project knowledge that agents use across sessions.
+Multi-layer memory system combining PARA organization with SQLite + FTS5 search.
 
-## Standard Files
+## Directory Structure
 
-| File              | Purpose                                 | Update When             |
-| ----------------- | --------------------------------------- | ----------------------- |
-| `commands.md`     | Build, test, lint, deploy commands      | Discover new command    |
-| `conventions.md`  | Code patterns, commit style, PR process | Learn team pattern      |
-| `gotchas.md`      | Footguns, edge cases, warnings          | Hit unexpected behavior |
-| `architecture.md` | Key modules, directory structure        | Map new area            |
+```
+memory/
+├── project/           # Tacit knowledge (always-injected context)
+│   ├── user.md        # User preferences, identity
+│   ├── tech-stack.md  # Framework, dependencies, constraints
+│   └── gotchas.md     # Footguns, edge cases, warnings
+├── knowledge/         # PARA-organized reference (curated)
+│   ├── projects/      # Active work with deadlines
+│   ├── areas/         # Ongoing responsibilities
+│   ├── resources/     # Reference material
+│   └── archives/      # Completed/inactive items
+├── daily/             # Chronological session logs
+├── research/          # Deep-dive analysis documents
+├── handoffs/          # Session handoff context
+└── _templates/        # File templates
+```
 
-## File Format
+## Memory Layers (3-Layer Architecture)
 
-Each file uses YAML frontmatter:
+| Layer               | Location      | Purpose                 | Access                             |
+| ------------------- | ------------- | ----------------------- | ---------------------------------- |
+| **Knowledge Graph** | SQLite + FTS5 | Searchable observations | `memory-search()`, `observation()` |
+| **Daily Notes**     | `daily/`      | Chronological narrative | Manual review                      |
+| **Tacit Knowledge** | `project/`    | Always-present context  | Auto-injected                      |
 
-```yaml
----
-purpose: How this memory should influence agent behavior
-updated: YYYY-MM-DD
----
-```
+## SQLite Memory Tools
 
-## How Agents Use This
+| Tool                | Purpose                                       |
+| ------------------- | --------------------------------------------- |
+| `observation()`     | Write structured observations to SQLite       |
+| `memory-search()`   | FTS5 full-text search (returns compact index) |
+| `memory-get()`      | Fetch full observation details by ID          |
+| `memory-timeline()` | Get chronological context around anchor       |
+| `memory-update()`   | Update markdown files in memory               |
 
-- **Session start**: Agents read relevant memory files for context
-- **During work**: Agents update files when learning new information
-- **Session end**: Critical learnings persisted here survive context reset
+## PARA Categories
 
-## Integration
+- **Projects**: Active work with deadlines → `knowledge/projects/`
+- **Areas**: Ongoing responsibilities → `knowledge/areas/`
+- **Resources**: Reference material → `knowledge/resources/`
+- **Archives**: Completed/inactive → `knowledge/archives/`
 
-### With Commands
+## Memory Tiers (Decay-based)
 
-- `/implement` - Reads conventions for code style
-- `/setup-project` - Populates these files initially
-- `/review-codebase` - Checks against conventions
+| Tier     | Access Pattern | Location                   |
+| -------- | -------------- | -------------------------- |
+| **Hot**  | Daily/Weekly   | Active SQLite + `project/` |
+| **Warm** | Monthly        | `knowledge/` directories   |
+| **Cold** | Rarely         | `knowledge/archives/`      |
 
-### With Beads
+## Workflow
 
-```bash
-bd new feature "Add auth" --context .opencode/memory/project/
-```
+### Session Start
+
+1. `memory-search()` - Find relevant context
+2. Read `project/` files (auto-injected)
+3. Check `daily/` for recent sessions if needed
+
+### During Work
+
+1. Use `observation()` for decisions, patterns, gotchas
+2. Update `project/gotchas.md` for footguns
+3. Add to `knowledge/` for curated reference
+
+### Session End
+
+1. Summary appended to `daily/YYYY-MM-DD.md`
+2. Sync beads: `br sync --flush-only`
 
 ## Philosophy
 
-**Don't rely on implicit learning.** When agents discover:
+**Three-layer memory beats single-layer:**
 
-- Non-obvious behavior → Update `gotchas.md`
-- New commands → Update `commands.md`
-- Code patterns → Update `conventions.md`
-- Architecture insights → Update `architecture.md`
+- SQLite for searchability (Knowledge Graph)
+- Daily notes for context (Chronological)
+- Project files for presence (Tacit Knowledge)
 
-Explicit memory beats hoping the agent remembers.
+Each layer serves a different retrieval pattern.

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

@@ -1,12 +1,37 @@
 # Beads PRD Template
 
-**Bead:** bd-[id]
-**Created:** [date]
-**Status:** Draft
+**Bead:** bd-[id]  
+**Created:** [date]  
+**Status:** Draft | In Review | Approved
 
-## Goal
+## Bead Metadata
 
-What exactly are we building and why does it exist?
+```yaml
+depends_on: [] # Bead IDs that must complete before this one
+parallel: true # Can run concurrently with other parallel beads
+conflicts_with: [] # Bead IDs that modify same files (cannot parallelize)
+blocks: [] # Bead IDs waiting on this one
+estimated_hours: 2 # Time estimate for planning
+```
+
+---
+
+## Problem Statement
+
+### What problem are we solving?
+
+[Clear description of the problem. Include user impact and business impact.]
+
+### Why now?
+
+[What triggered this work? Cost of inaction?]
+
+### Who is affected?
+
+- **Primary users:** [Description]
+- **Secondary users:** [Description]
+
+---
 
 ## Scope
 
@@ -17,20 +42,55 @@ What exactly are we building and why does it exist?
 ### Out-of-Scope
 
 - [List what's explicitly off-limits]
+- [Deferred to future iterations]
+
+---
+
+## Proposed Solution
+
+### Overview
+
+[One paragraph describing what this feature does when complete.]
 
-## User Flow (if user-facing)
+### User Flow (if user-facing)
 
 1. [Step 1]
 2. [Step 2]
 3. [Step 3]
 
+---
+
+## Requirements
+
+### Functional Requirements
+
+#### [Requirement Name]
+
+Brief description of what must be true.
+
+**Scenarios:**
+
+- **WHEN** [precondition or trigger] **THEN** [expected outcome]
+- **WHEN** [edge case condition] **THEN** [expected behavior]
+
+### Non-Functional Requirements
+
+- **Performance:** [constraint if applicable]
+- **Security:** [constraint if applicable]
+- **Accessibility:** [WCAG level if applicable]
+- **Compatibility:** [constraint if applicable]
+
+---
+
 ## Success Criteria
 
-- [ ] [Specific, measurable criteria 1]
+- [ ] [Specific, measurable criterion 1]
   - Verify: `[command or manual check]`
-- [ ] [Specific, measurable criteria 2]
+- [ ] [Specific, measurable criterion 2]
   - Verify: `[command or manual check]`
 
+---
+
 ## Technical Context
 
 ### Existing Patterns
@@ -41,26 +101,44 @@ What exactly are we building and why does it exist?
 
 - `src/relevant/file.ts` - Why relevant
 
-## Risks
+### Affected Files
 
-- [Risk 1 + mitigation]
+Files this bead will modify (for conflict detection):
 
-## Notes
+```yaml
+files:
+  - src/path/to/file.ts # Why
+  - src/path/to/other.ts # Why
+```
 
-[Additional context or constraints]
+---
+
+## Risks & Mitigations
+
+| Risk   | Likelihood   | Impact       | Mitigation      |
+| ------ | ------------ | ------------ | --------------- |
+| Risk 1 | High/Med/Low | High/Med/Low | How to mitigate |
+
+---
+
+## Open Questions
+
+| Question   | Owner | Due Date | Status        |
+| ---------- | ----- | -------- | ------------- |
+| Question 1 | Name  | Date     | Open/Resolved |
 
 ---
 
 ## Tasks
 
-Write tasks in a machine-convertible format for `prd-task`.
+Write tasks in a machine-convertible format for `prd-task` skill.
 
-Rules:
+**Rules:**
 
-- Each task is a `### <Title> [category]` heading.
-- Provide one sentence describing the end state.
-- Include `**Verification:**` with bullet steps proving it works.
-- Include `**Metadata:**` with dependency and parallelization info.
+- Each task is a `### <Title> [category]` heading
+- Provide one sentence describing the end state
+- Include `**Metadata:**` with dependency info
+- Include `**Verification:**` with bullet steps proving it works
 
 ### <Task Title> [category]
 
@@ -106,3 +184,9 @@ files: []
 | `parallel`       | Can run concurrently with other parallel tasks    | `true` / `false`                           |
 | `conflicts_with` | Cannot run in parallel (same files)               | `["Update config"]`                        |
 | `files`          | Files this task modifies (for conflict detection) | `["src/db/schema.ts", "src/db/client.ts"]` |
+
+---
+
+## Notes
+
+[Additional context, constraints, or decisions]

package/dist/template/.opencode/memory/project/gotchas.md

@@ -0,0 +1,31 @@
+---
+purpose: Footguns, edge cases, and warnings discovered during development
+updated: 2026-02-04
+---
+
+# Gotchas
+
+Track unexpected behaviors, edge cases, and warnings here. Update when you hit something surprising.
+
+## OpenCode Config
+
+- **`compaction` key invalid**: Not in official schema at opencode.ai/config.json. Remove if present.
+- **`experimental` key invalid**: Not in schema. Remove if present.
+- **`tools` key invalid**: Not in schema. Remove if present.
+- **`formatter` valid but undocumented**: Works but missing from schema (schema incomplete).
+
+## Memory System
+
+- Subagents (explore, scout, review) should NOT write to memory - only leader agents
+- Use `observation: false` and `memory-update: false` in agent configs to enforce
+
+## Build System
+
+- `dist/` is generated - never edit directly
+- Build copies `.opencode/` to `dist/template/` via rsync
+- Run `npm run build` to regenerate
+
+## Beads
+
+- Only leader agents (build, plan) should modify beads state
+- Subagents read with `br show <id>`, report findings back