opencodekit 0.16.2 → 0.16.4

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

@@ -141,11 +141,11 @@ Limit options to 3-5. Recommend best option first.
 
 ### The Three Blockers
 
-These are hard gates that must be passed before proceeding. First, DO NOT start major work without running `bd show <id>` to understand the task context. Understanding the task context enables everything that follows, so skipping this blocks your ability to work effectively. Second, DO NOT generate ANY URL yourself. If you need an external link, either the user provides it or you use @scout to fetch verified information. Guessing URLs leads to hallucinated documentation and broken references. Third, DO NOT claim completion without running `bd close <id>` to mark the task as done. Claiming work is finished without closing the task breaks the tracking system and loses context.
+These are hard gates that must be passed before proceeding. First, DO NOT start major work without running `br show <id>` to understand the task context. Understanding the task context enables everything that follows, so skipping this blocks your ability to work effectively. Second, DO NOT generate ANY URL yourself. If you need an external link, either the user provides it or you use @scout to fetch verified information. Guessing URLs leads to hallucinated documentation and broken references. Third, DO NOT claim completion without running `br close <id>` to mark the task as done. Claiming work is finished without closing the task breaks the tracking system and loses context.
 
 ### Verification chain
 
-Think of these checkpoints as a chain where each step enables the next. Running `bd show <id>` gives you task context, which enables you to proceed with confidence. Verifying links through fetch before using them enables you to trust your sources. Running `bd close <id>` marks you as complete and finalizes the state.
+Think of these checkpoints as a chain where each step enables the next. Running `br show <id>` gives you task context, which enables you to proceed with confidence. Verifying links through fetch before using them enables you to trust your sources. Running `br close <id>` marks you as complete and finalizes the state.
 
 ### No guessing protocol
 
@@ -331,15 +331,15 @@ Beads is a git-backed task tracking system. Tasks have IDs, statuses, and depend
 
 ### Leader protocol for build and plan agents
 
-Only build and plan agents own the beads database. Subagents work read-only and report findings back to their leader. The leader follows this chain: run `bd ready` to find unblocked work, run `bd update <id> --status in_progress` to claim the task, do the editing work, run `bd close <id> --reason "..."` to mark it complete, run `bd sync` to push changes to git, and then restart the session. Skipping any step breaks the tracking flow.
+Only build and plan agents own the beads database. Subagents work read-only and report findings back to their leader. The leader follows this chain: run `br ready` to find unblocked work, run `br update <id> --status in_progress` to claim the task, do the editing work, run `br close <id> --reason "..."` to mark it complete, run `br sync --flush-only` to export changes to JSONL (then git commit/push manually), and then restart the session. Skipping any step breaks the tracking flow.
 
 ### Subagent protocol
 
-Subagents must not modify beads state. When a subagent needs task information, read it with `bd show <id>`. Report findings back to the leader agent rather than making decisions yourself. Let the leader agent update task status. This keeps the tracking system clean and ensures only one agent controls each task's state.
+Subagents must not modify beads state. When a subagent needs task information, read it with `br show <id>`. Report findings back to the leader agent rather than making decisions yourself. Let the leader agent update task status. This keeps the tracking system clean and ensures only one agent controls each task's state.
 
 ### Checkpoints before claiming done
 
-Before you claim work is complete, verify these things have happened. You ran `bd update <id> --status in_progress` when you started. You completed the actual editing work. You ran `bd close <id> --reason "..."` with a meaningful reason explaining what you did. You ran `bd sync` to push the changes. If any of these are missing, the work is not done.
+Before you claim work is complete, verify these things have happened. You ran `br update <id> --status in_progress` when you started. You completed the actual editing work. You ran `br close <id> --reason "..."` with a meaningful reason explaining what you did. You ran `br sync --flush-only` to export changes to JSONL (then git commit/push). If any of these are missing, the work is not done.
 
 ### Atomic Version
 
@@ -474,8 +474,8 @@ Before you claim completion, verify these things:
 
    If review suggests simplification, implement it before proceeding.
 
-3. You ran `bd close <id>` with a meaningful reason
-4. You ran `bd sync` to push changes
+3. You ran `br close <id>` with a meaningful reason
+4. You ran `br sync --flush-only` to export changes
 5. There are no pending LSP nudges
 6. You saved observations for any important decisions or patterns
 

package/dist/template/.opencode/agent/build.md

@@ -2,7 +2,6 @@
 description: Leader agent for plan execution and parallel task coordination via Task tool.
 mode: primary
 temperature: 0.2
-steps: 50
 permission:
   bash:
     "*": allow
@@ -335,7 +334,7 @@ PARALLEL FLOW:
   3. Task({ subagent_type: "...", prompt: "..." }) → Spawn workers
   4. Wait for results (automatic)
   5. Synthesize and verify
-  6. bd close <bead>
+  6. br close <bead>
 
 SINGLE FLOW:
   Read → Edit → Verify → Repeat → Close

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

@@ -2,7 +2,6 @@
 description: Primary planning agent for architecture and multi-phase execution; produces actionable plans with gated steps.
 mode: primary
 temperature: 0.2
-steps: 50
 permission:
   write:
     "*": ask

package/dist/template/.opencode/agent/scout.md

@@ -130,15 +130,61 @@ To construct a permalink: use `grepsearch` to find code, then build the URL from
 | Priority | Tool          | Use Case                                  | Speed   |
 | -------- | ------------- | ----------------------------------------- | ------- |
 | 1        | memory-search | Past research findings                    | Instant |
-| 2        | context7      | Official library docs                     | Fast    |
-| 3        | codesearch    | Exa Code API for SDK/library patterns     | Fast    |
-| 4        | grepsearch    | Cross-repo GitHub code search (1M+ repos) | Medium  |
-| 5        | webfetch      | Specific doc URLs, READMEs, changelogs    | Medium  |
-| 6        | opensrc + LSP | Clone & analyze source code               | Slow    |
-| 7        | websearch     | Tutorials, blog posts, recent news        | Slow    |
+| 2        | v1-run        | npm package health, vulns, comparisons    | Fast    |
+| 3        | context7      | Official library docs                     | Fast    |
+| 4        | codesearch    | Exa Code API for SDK/library patterns     | Fast    |
+| 5        | grepsearch    | Cross-repo GitHub code search (1M+ repos) | Medium  |
+| 6        | webfetch      | Specific doc URLs, READMEs, changelogs    | Medium  |
+| 7        | opensrc + LSP | Clone & analyze source code               | Slow    |
+| 8        | websearch     | Tutorials, blog posts, recent news        | Slow    |
 
 **Rule:** Exhaust faster tools before slower ones. Run tools in parallel when independent.
 
+## v1-run MCP (npm Package Intelligence)
+
+Use for npm package evaluation before adding dependencies. Load the skill first:
+
+```typescript
+skill({ name: "v1-run" });
+```
+
+### Primary Tool: get_package_health
+
+```typescript
+// Comprehensive health check (use this first)
+skill_mcp({ skill_name: "v1-run", tool_name: "get_package_health", arguments: '{"name": "zod"}' });
+```
+
+Returns: version, vulnerabilities, health score (0-100), downloads, TypeScript support, maintenance status, AI recommendation.
+
+### Compare Packages
+
+```typescript
+// Side-by-side comparison (2-5 packages)
+skill_mcp({
+  skill_name: "v1-run",
+  tool_name: "compare_packages",
+  arguments: '{"packages": ["zod", "yup", "joi"]}',
+});
+```
+
+### Other Tools
+
+| Tool                    | Use Case                              |
+| ----------------------- | ------------------------------------- |
+| `check_vulnerabilities` | Security audit for specific version   |
+| `check_deprecated`      | Check if package is deprecated        |
+| `find_alternatives`     | Discover better options for a package |
+| `check_types`           | Verify TypeScript support             |
+| `get_package_version`   | Get latest version only               |
+
+**When to use v1-run:**
+
+- Choosing between npm packages → `compare_packages`
+- Before adding a dependency → `get_package_health`
+- Security audit → `check_vulnerabilities`
+- Package seems abandoned → `find_alternatives`
+
 ## context7 Tools
 
 Use to access up-to-date library documentation (37.6k+ libraries).

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

@@ -45,7 +45,7 @@ Review findings for:
 ## Load Bead Context
 
 ```bash
-bd show $ARGUMENTS
+br show $ARGUMENTS
 ```
 
 Check what artifacts already exist:
@@ -308,4 +308,4 @@ Next: /research $ARGUMENTS (optional)
 | ------------------ | ---------------------- |
 | Research first     | `/research $ARGUMENTS` |
 | Plan after spec    | `/plan $ARGUMENTS`     |
-| Create bead itself | `bd create "Title"`    |
+| Create bead itself | `br create "Title"`    |

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

@@ -605,7 +605,7 @@ observation({
 For component/page designs:
 
 ```bash
-bd create "Implement [component/page] design" -t task -p 2
+br create "Implement [component/page] design" -t task -p 2
 ```
 
 ### Bead Integration

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

@@ -44,7 +44,7 @@ Don't grind past diminishing returns. A clean handoff beats degraded output.
 
 Get current task status:
 
-!`bd show $ARGUMENTS`
+!`br show $ARGUMENTS`
 
 Get git state:
 
@@ -178,7 +178,7 @@ Start next session with: `/resume $ARGUMENTS`
 ## Sync State
 
 ```bash
-bd sync
+br sync --flush-only
 ```
 
 This commits the handoff and pushes to remote.

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

@@ -28,7 +28,7 @@ skill({ name: "memory-system" });
 ```
 
 ```bash
-bd show $ARGUMENTS
+br show $ARGUMENTS
 ```
 
 Check for existing artifacts:
@@ -288,47 +288,47 @@ With user approval or `--create-beads` flag:
 PARENT=$ARGUMENTS
 
 # Task 1 (no blockers - starts immediately)
-bd create "[Task 1 title]" -t task -p 2
+br create "[Task 1 title]" -t task -p 2
 # Capture: bd-xxx1
 
 # Link to parent
-bd dep add bd-xxx1 $PARENT
+br dep add bd-xxx1 $PARENT
 
 # Task 2 (blocked by Task 1)
-bd create "[Task 2 title]" -t task -p 2
+br create "[Task 2 title]" -t task -p 2
 # Capture: bd-xxx2
 
-bd dep add bd-xxx2 $PARENT
-bd dep add bd-xxx2 bd-xxx1 --type blocks
+br dep add bd-xxx2 $PARENT
+br dep add bd-xxx2 bd-xxx1 --type blocks
 
 # Task 3 (blocked by Task 2)
-bd create "[Task 3 title]" -t task -p 2
+br create "[Task 3 title]" -t task -p 2
 # Capture: bd-xxx3
 
-bd dep add bd-xxx3 $PARENT
-bd dep add bd-xxx3 bd-xxx2 --type blocks
+br dep add bd-xxx3 $PARENT
+br dep add bd-xxx3 bd-xxx2 --type blocks
 ```
 
 ### Create Subtasks (for complex tasks)
 
 ```bash
 # For Task 2, create subtasks:
-bd create "[Subtask 2.1 title]" -t subtask -p 2
+br create "[Subtask 2.1 title]" -t subtask -p 2
 # Capture: bd-xxx2.1
 
-bd dep add bd-xxx2.1 bd-xxx2
+br dep add bd-xxx2.1 bd-xxx2
 
-bd create "[Subtask 2.2 title]" -t subtask -p 2
+br create "[Subtask 2.2 title]" -t subtask -p 2
 # Capture: bd-xxx2.2
 
-bd dep add bd-xxx2.2 bd-xxx2
-bd dep add bd-xxx2.2 bd-xxx2.1 --type blocks  # Sequential dependency
+br dep add bd-xxx2.2 bd-xxx2
+br dep add bd-xxx2.2 bd-xxx2.1 --type blocks  # Sequential dependency
 ```
 
 ### Verify Hierarchy
 
 ```bash
-bd dep tree $ARGUMENTS
+br dep tree $ARGUMENTS
 ```
 
 ---
@@ -442,7 +442,7 @@ After creating hierarchy, execute READY tasks in parallel:
 
 ```bash
 # Check what's ready to start
-bd ready --json
+br ready --json
 ```
 
 ```typescript
@@ -473,7 +473,7 @@ for (const taskId of backgroundTaskIds) {
 }
 
 // Check newly unblocked tasks
-bd ready  // → Next wave of tasks now READY
+br ready  // → Next wave of tasks now READY
 
 // Cleanup
 background_cancel({ all: true })
@@ -484,7 +484,7 @@ background_cancel({ all: true })
 ## Phase 8: Sync and Report
 
 ```bash
-bd sync
+br sync --flush-only
 ```
 
 ### Output (without child beads)
@@ -552,4 +552,4 @@ Next: /start bd-xxx1
 | Research before plan | `/research <bead-id>`    |
 | Start first task     | `/start <first-task-id>` |
 | Ship the work        | `/ship <bead-id>`        |
-| View hierarchy       | `bd dep tree <bead-id>`  |
+| View hierarchy       | `br dep tree <bead-id>`  |

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

@@ -108,7 +108,7 @@ Resolve conflicts before creating PR:
 **Load bead context (if provided):**
 
 ```
-!`bd show $ARGUMENTS`
+!`br show $ARGUMENTS`
 ```
 
 **Load artifacts:**
@@ -257,7 +257,7 @@ CI Status:
 ## Phase 7: Update Bead & Sync
 
 ```bash
-bd sync
+br sync --flush-only
 ```
 
 ## Output

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

@@ -23,6 +23,9 @@ if (thorough) {
   skill({ name: "deep-research" });
 }
 
+// For npm package evaluation
+skill({ name: "v1-run" });
+
 // For source code analysis
 skill({ name: "source-code-research" });
 
@@ -111,7 +114,7 @@ Return: Documentation, code examples, best practices`,
 
 ### Load Bead Details
 
-!`bd show $ARGUMENTS`
+!`br show $ARGUMENTS`
 !`cat .beads/artifacts/$ARGUMENTS/spec.md`
 
 Extract questions that need answering from spec.
@@ -149,10 +152,11 @@ If memory search fails (Ollama not running), continue to external sources.
 
 1. **Codebase patterns** (highest trust) - Delegate to @explore for LSP analysis
 2. **Official docs** (high trust) - What does the library documentation say?
-3. **Context7** (high trust) - API usage and examples
-4. **Source code** (high trust) - Library implementation (use `source-code-research` skill)
-5. **GitHub examples** (medium trust) - Real-world patterns via codesearch/grepsearch
-6. **Web search** (lower trust) - Only if tiers 1-5 don't answer
+3. **v1-run** (high trust) - npm package health, vulnerabilities, comparisons
+4. **Context7** (high trust) - API usage and examples
+5. **Source code** (high trust) - Library implementation (use `source-code-research` skill)
+6. **GitHub examples** (medium trust) - Real-world patterns via codesearch/grepsearch
+7. **Web search** (lower trust) - Only if tiers 1-6 don't answer
 
 ## Research
 

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

@@ -18,9 +18,9 @@ skill({ name: "memory-system" });
 
 ## Verify The Task Exists
 
-!`bd show $ARGUMENTS`
+!`br show $ARGUMENTS`
 
-If not found, check `bd list --status=all`. Maybe it was closed, or you have the wrong ID.
+If not found, check `br list --status=all`. Maybe it was closed, or you have the wrong ID.
 
 ## Check Git State
 
@@ -168,7 +168,7 @@ Next: [from handoff resume instructions]
 Mark in progress if not already:
 
 ```bash
-bd update $ARGUMENTS --status in_progress
+br update $ARGUMENTS --status in_progress
 ```
 
 Then continue with implementation:

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

@@ -35,7 +35,7 @@ Parse `$ARGUMENTS` to determine what to review:
 | Input                    | Scope                  | How to Get Code                             |
 | ------------------------ | ---------------------- | ------------------------------------------- |
 | File/directory path      | That path only         | `read` or `glob` + `read`                   |
-| Bead ID (e.g., `bd-123`) | Implementation vs spec | `bd show` then `git diff` from spec         |
+| Bead ID (e.g., `br-123`) | Implementation vs spec | `br show` then `git diff` from spec         |
 | PR number (e.g., `#45`)  | PR changes             | `gh pr diff 45`                             |
 | `all` or empty           | Recent changes         | `git diff main...HEAD` or `git diff HEAD~5` |
 
@@ -123,7 +123,7 @@ Review each category with specific focus:
 For each Critical or Important finding:
 
 ```bash
-bd create "[Review] <brief issue description>" -t bug -p 1
+br create "[Review] <brief issue description>" -t bug -p 1
 ```
 
 Skip creating beads for Minor issues (just report them).

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

@@ -43,8 +43,8 @@ Apply past learnings to avoid known issues.
 ## Verify Task & Claim
 
 ```bash
-bd show $ARGUMENTS
-bd update $ARGUMENTS --status in_progress
+br show $ARGUMENTS
+br update $ARGUMENTS --status in_progress
 ```
 
 ## Pre-Flight Verification
@@ -166,8 +166,8 @@ question({
 If confirmed:
 
 ```bash
-bd close $ARGUMENTS --reason "Shipped: verification + review passed"
-bd sync
+br close $ARGUMENTS --reason "Shipped: verification + review passed"
+br sync --flush-only
 ```
 
 ## Record Learnings (On Completion)

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

@@ -47,7 +47,7 @@ bd hooks install 2>/dev/null || echo "Hooks already installed"
 
 ### Active Tasks
 
-!`bd list --status=in_progress`
+!`br list --status=in_progress`
 
 If you have uncommitted changes, ask the user:
 
@@ -59,7 +59,7 @@ If you already have tasks in_progress, warn the user before claiming another.
 
 ## Task Details
 
-!`bd show $ARGUMENTS`
+!`br show $ARGUMENTS`
 
 Identify the task type from the bead:
 
@@ -72,13 +72,13 @@ Identify the task type from the bead:
 Check for parent/child relationships:
 
 ```bash
-bd dep tree $ARGUMENTS 2>/dev/null || echo "No dependencies"
+br dep tree $ARGUMENTS 2>/dev/null || echo "No dependencies"
 ```
 
 ## Claim The Task
 
 ```bash
-bd update $ARGUMENTS --status in_progress
+br update $ARGUMENTS --status in_progress
 ```
 
 ## Sync Beads State to OpenCode Todos
@@ -103,7 +103,7 @@ Extract task info and parent branch for a readable branch name:
 PARENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
 
 # Get task title and type from bead
-BEAD_INFO=$(bd show $ARGUMENTS --json 2>/dev/null)
+BEAD_INFO=$(br show $ARGUMENTS --json 2>/dev/null)
 BEAD_TITLE=$(echo "$BEAD_INFO" | jq -r '.title // ""' | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-40)
 BEAD_TYPE=$(echo "$BEAD_INFO" | jq -r '.type // "task"')
 
@@ -150,7 +150,7 @@ skill({ name: "using-git-worktrees" });
 PARENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
 
 # Get task title for readable worktree name
-BEAD_INFO=$(bd show $ARGUMENTS --json 2>/dev/null)
+BEAD_INFO=$(br show $ARGUMENTS --json 2>/dev/null)
 BEAD_TITLE=$(echo "$BEAD_INFO" | jq -r '.title // ""' | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-40)
 BEAD_TYPE=$(echo "$BEAD_INFO" | jq -r '.type // "task"')
 
@@ -301,7 +301,7 @@ Use swarm planning to analyze the specific task:
 
 ```typescript
 // Get task details from bead
-const beadInfo = bd show $ARGUMENTS --json;
+const beadInfo = br show $ARGUMENTS --json;
 const taskTitle = beadInfo.title;
 const taskDescription = beadInfo.description;
 

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

@@ -22,9 +22,9 @@ Run all status checks simultaneously:
 
 ```
 # Beads CLI commands
-!`bd status`
-!`bd list --status in_progress --limit 10`
-!`bd list --status ready --limit 10`
+!`br status`
+!`br list --status in_progress --limit 10`
+!`br list --status ready --limit 10`
 
 # Git state
 !`git status --porcelain`

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

@@ -284,10 +284,10 @@ If `--bead=<id>` provided:
 
 ```bash
 # Create issues for critical findings
-bd create "[UI] Fix invisible focus states" -t bug -p 1
+br create "[UI] Fix invisible focus states" -t bug -p 1
 
 # Then link to parent bead
-bd dep add <task-id> <bead-id>
+br dep add <task-id> <bead-id>
 ```
 
 ---

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

@@ -41,7 +41,7 @@ memory_search({ query: "$ARGUMENTS verification issues patterns", limit: 3 });
 ## Phase 2: Gather Artifacts
 
 ```bash
-bd show $ARGUMENTS
+br show $ARGUMENTS
 ls .beads/artifacts/$ARGUMENTS/
 ```