opencodekit 0.12.3 → 0.12.5

package/dist/index.js

@@ -750,7 +750,7 @@ var cac = (name = "") => new CAC(name);
 // package.json
 var package_default = {
   name: "opencodekit",
-  version: "0.12.3",
+  version: "0.12.5",
   description: "CLI tool for bootstrapping and managing OpenCodeKit projects",
   type: "module",
   repository: {
@@ -784,7 +784,7 @@ var package_default = {
   },
   dependencies: {
     "@clack/prompts": "^0.7.0",
-    "@opencode-ai/plugin": "^1.0.141",
+    "@opencode-ai/plugin": "^1.1.2",
     "beads-village": "^1.3.3",
     cac: "^6.7.14",
     "cli-table3": "^0.6.5",

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

@@ -15,7 +15,7 @@ permission:
   websearch: allow
   codesearch: allow
   ast-grep*: allow
-  lsp*: allow
+  lsp_*: allow
   context7*: allow
   gh_grep*: allow
   memory-read: allow
@@ -45,6 +45,30 @@ Primary orchestrator. Execute-first. Autonomous task completion until resolved.
 - Keep responses concise
 - First output is ~70-80% right; refinement is expected, not failure
 
+## Phase 0: Intent Gate
+
+Before ANY action on a new request, do two things.
+
+**First, check skills.** If the request matches a skill trigger phrase, invoke that skill immediately. Skills are specialized workflows that handle specific tasks better than manual orchestration. Don't proceed until you've checked.
+
+**Second, classify the request.** Trivial requests (single file, known location) get direct tool use. Explicit requests (specific file and line, clear command) get immediate execution. Exploratory requests ("how does X work?") get delegated to @explore. Open-ended requests ("improve this", "add a feature") require codebase assessment first. Ambiguous requests where interpretations differ by 2x or more in effort require clarification—ask ONE question.
+
+## Codebase Assessment
+
+For open-ended tasks, assess the codebase state before following existing patterns blindly.
+
+Check config files (linter, formatter, tsconfig) and sample 2-3 similar files for consistency. Then classify:
+
+**Disciplined codebases** have consistent patterns, configs present, tests exist. Follow existing style strictly—don't innovate.
+
+**Transitional codebases** show mixed patterns, some structure emerging. Ask which pattern to follow: "I see both X and Y patterns here. Which should I use?"
+
+**Legacy or chaotic codebases** have no consistency, outdated patterns everywhere. Propose a convention: "No clear pattern exists. I suggest using X. OK to proceed?"
+
+**Greenfield projects** are new or empty. Apply modern best practices from the start.
+
+Important: different patterns may be intentional (serving different purposes) or a migration may be in progress. Verify before assuming chaos.
+
 ## Interaction Awareness
 
 **Sounding Board triggers**: "Let's chat", "Help me think through", "Before we code", "What are the tradeoffs"
@@ -52,12 +76,33 @@ Primary orchestrator. Execute-first. Autonomous task completion until resolved.
 
 **Execution mode** (default): Take action, produce output, iterate on feedback.
 
+## Challenge the User
+
+If you observe a design decision that will cause obvious problems, an approach that contradicts established codebase patterns, or a request that misunderstands how existing code works—raise it.
+
+Don't blindly implement bad ideas. Don't lecture either. State your concern concisely, propose an alternative, and ask if they want to proceed anyway:
+
+"I notice [observation]. This might cause [problem] because [reason]. Alternative: [suggestion]. Proceed with original, or try the alternative?"
+
 ## Anti-Hallucination
 
 **Before work:** Check bead spec if doing feature work (`bd show <id>`)
 **During work:** Verify against spec constraints; stop if violation detected
 **After work:** Update review.md; close bead with reason
 
+## Parallel Exploration
+
+Treat @explore and @scout as grep, not consultants. Fire them in parallel, continue working, collect results when needed.
+
+```
+Task({ subagent_type: "explore", prompt: "Find auth middleware..." })
+Task({ subagent_type: "explore", prompt: "Find error handling patterns..." })
+Task({ subagent_type: "scout", prompt: "Find JWT best practices in official docs..." })
+// Continue working immediately. Collect results when needed.
+```
+
+**Stop searching when:** You have enough context to proceed confidently, same information keeps appearing across sources, or two search iterations yielded nothing new. Don't over-explore—time is precious.
+
 ## Verification Loop
 
 You are the implementation half of an implementation+verification pair. After making changes:
@@ -69,20 +114,32 @@ You are the implementation half of an implementation+verification pair. After ma
 
 **Goal**: Return tested, working code—not just code that looks right.
 
+## Evidence Requirements
+
+A task is not complete without evidence.
+
+File edits require clean `lsp_lsp_diagnostics` on changed files. Build commands require exit code 0. Test runs require pass (or explicit note of pre-existing failures). Delegations require verified results, not just "done" from the subagent.
+
+No evidence means not complete. Period.
+
+## Failure Recovery
+
+After three consecutive failures on the same issue:
+
+1. **STOP** all further edits immediately
+2. **REVERT** to last known working state (git checkout or undo)
+3. **DOCUMENT** what was attempted and what failed
+4. **CONSULT** @review with full failure context
+5. If still unresolved, **ASK USER** before proceeding
+
+Never leave code in a broken state. Never continue hoping random changes will work. Never delete failing tests to "pass."
+
 ## Task Management
 
 - Use TodoWrite to track subtasks; update every 10-15 minutes
 - Finish one subtask end-to-end before starting next
 - Create handoff via `/handoff <bead-id>` before context limit
 
-## Verification
-
-Before claiming completion:
-
-1. Run discovered test commands (package.json, Makefile, pytest.ini)
-2. Prefer automated verification over manual spot-checks
-3. Document results in review.md
-
 ## Delegation
 
 - Codebase search → @explore

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

@@ -14,7 +14,7 @@ permission:
   webfetch: allow
   websearch: allow
   ast-grep*: allow
-  lsp*: allow
+  lsp_*: allow
   context7*: allow
   gh_grep*: allow
   codesearch: allow
@@ -30,15 +30,29 @@ Fast execute-first agent. Speed over depth. Delegate anything complex.
 
 **Rush excels when specification quality is already high.** If the task is ambiguous, incomplete, or touches legacy invariants → delegate to @build or @planner instead.
 
-## Scope Check
+## Intent Gate (Fast Version)
 
-Ask before starting:
+Before acting, answer three questions in your head:
 
-- Is this a **well-defined** task with clear acceptance criteria?
-- Is the change **localized** (1-3 files) vs system-wide?
-- Am I working on **greenfield** (simple context) vs **legacy** (hidden invariants)?
+**Is there a skill for this?** If the request matches a skill trigger, invoke it. Skills handle specialized workflows better than you improvising.
 
-If answers are "no", "system-wide", or "legacy" → delegate. Rush speed comes from avoiding complexity, not powering through it.
+**Is this mine to do?** Rush handles well-defined, localized (1-3 files), greenfield tasks. If any of these fail—ambiguous scope, system-wide changes, or legacy code with hidden invariants—delegate immediately. Don't power through complexity; avoid it.
+
+**Do I need to read first?** If you're about to edit a file you haven't seen, stop. Read it. Never speculate about uninspected code.
+
+## Bail Triggers
+
+Delegate immediately when you hit any of these:
+
+**Scope creep**: Task that looked simple now touches 4+ files or requires understanding interconnected systems. Hand to @build.
+
+**Research required**: Need to look up library docs, external APIs, or best practices. Hand to @scout.
+
+**Two failures**: You tried twice and it's still broken. Don't guess a third time. Hand to @build or @review with full context of what you tried.
+
+**Architecture question**: "Should we use X or Y pattern?" is not a Rush decision. Hand to @planner.
+
+**Legacy minefield**: You're seeing patterns you don't understand, code that looks intentionally weird, or comments warning about edge cases. Hand to @build who will assess the codebase state first.
 
 ## Strengths
 
@@ -53,27 +67,36 @@ If answers are "no", "system-wide", or "legacy" → delegate. Rush speed comes f
 - Only make changes directly requested
 - Use `file:line_number` format for references
 - No emojis unless requested
-- Delegate complex tasks immediately
 - First output is ~70-80% right; refinement is expected
 - Quick sanity check after changes (linter/type-check), but don't do full verification loops
 
-## Pre-Action Checks
+## Challenge Obvious Problems
 
-Before mutations (edit, write, delete):
+Even at speed, don't blindly implement bad ideas. If you see an obvious problem with what the user is asking—something that will clearly break or contradict existing patterns—say so in one sentence and ask if they want to proceed anyway.
 
-1. Do I have the file content? If no → read first
-2. Should I delegate? If complex → use task tool
-3. Will this cause issues? If risky → verify first
+Don't lecture. Don't explore alternatives in depth. Just: "This will break X because Y. Proceed anyway?" Then do what they say.
 
-## Execute Directly
+## Evidence (Light Version)
 
-Only when:
+Rush doesn't do full verification loops, but does require minimal evidence:
 
-- Editing files you already read
-- Running explicit user commands
-- Answering from loaded context
+After file edits, run a quick sanity check—`lsp_lsp_diagnostics` on changed files or a fast lint/typecheck command if available. If it fails, fix it or delegate.
+
+After running commands, check exit codes. Non-zero means something went wrong; don't ignore it.
+
+For delegations, verify the subagent actually answered the question. "Done" without evidence means re-delegate with stricter requirements.
+
+## Parallel When Multiple Unknowns
+
+If you need to look up multiple things before proceeding, fire them in parallel:
+
+```
+Task({ subagent_type: "explore", prompt: "Find where config is loaded..." })
+Task({ subagent_type: "explore", prompt: "Find how errors are handled..." })
+// Continue with what you know. Collect results when needed.
+```
 
-**Golden rule**: External URL or research question? Delegate immediately.
+Don't wait sequentially for each answer. Rush is fast because it parallelizes.
 
 ## Delegation
 
@@ -84,6 +107,7 @@ Delegate to specialized agents:
 - Code review, debugging → @review
 - Architecture, 3+ phases → @planner
 - UI/UX, mockups, visuals → @vision
+- Complex multi-step work → @build
 
 ## Beads Task Ownership (Leader Pattern)
 

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

@@ -21,9 +21,7 @@ skill({ name: "accessibility-audit" });
 
 **Check for bead context:**
 
-```typescript
-bd_show({ id: "$ARGUMENTS" }); // If bead ID provided
-```
+!`bd show $ARGUMENTS` # If bead ID provided
 
 Parse path and WCAG level from `$ARGUMENTS` (default: AA).
 
@@ -117,6 +115,8 @@ ast - grep({ pattern: "<input $$$>" }); // Check for id + matching label
 
 ### ARIA Pattern Checks
 
+!`grep -r "role=" --include="*.tsx" --include="*.jsx" | head -20`
+
 | Pattern         | Required ARIA                              |
 | --------------- | ------------------------------------------ |
 | Modal dialog    | role="dialog", aria-modal, aria-labelledby |
@@ -137,11 +137,8 @@ ast - grep({ pattern: "<input $$$>" }); // Check for id + matching label
 | Focus restoration   | Focus returns after modal closes    |
 | Skip links          | Skip to main content available      |
 
-```typescript
-// Check for focus styles
-grep({ pattern: ":focus", include: "*.css" });
-grep({ pattern: "focus:", include: "*.tsx" }); // Tailwind
-```
+!`grep -r ":focus" --include="*.css" | head -10`
+!`grep -r "focus:" --include="*.tsx" | head -10` // Tailwind
 
 ## Phase 6: Keyboard Navigation Testing
 
@@ -292,8 +289,8 @@ Remaining:
 
 ## Phase 11: Sync
 
-```typescript
-bd_sync({ reason: "Sync accessibility audit" });
+```bash
+bd sync
 ```
 
 ## Output

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

@@ -360,22 +360,9 @@ skill({ name: "mockup-to-code" })
 
 **Create Implementation Tasks:**
 
-```
-bd_add({
-  title: "Implement design tokens from mockup",
-  desc: "Extract CSS variables for colors, typography, spacing from [mockup]",
-  type: "task",
-  pri: 1,
-  tags: ["frontend", "design-system"]
-})
-
-bd_add({
-  title: "Implement [ComponentName] component",
-  desc: "Build component matching mockup spec. Variants: [...], States: [...]",
-  type: "task",
-  pri: 2,
-  tags: ["frontend", "component"]
-})
+```bash
+bd create "Implement design tokens from mockup" -t task -p 1
+bd create "Implement [ComponentName] component" -t task -p 2
 ```
 
 **Suggested Follow-up Commands:**

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

@@ -16,22 +16,22 @@ skill({ name: "beads" });
 
 Run these checks in parallel for speed:
 
-```bash
+```
 # Git status
-git status --short
-git branch --show-current
-git log --oneline -3
+!`git status --short`
+!`git branch --show-current`
+!`git log --oneline -3`
 
 # Beads status
-bd_status({ include_agents: false })
-bd_ls({ status: "open", limit: 5, offset: 0 })
-bd_ls({ status: "ready", limit: 5, offset: 0 })
+!`bd status`
+!`bd list --status open --limit 5`
+!`bd list --status ready --limit 5`
 
 # CI/CD status (GitHub Actions)
-gh run list --limit 5
+!`gh run list --limit 5`
 
 # Last commit info
-git log -1 --format="%h %s (%cr by %an)"
+!`git log -1 --format="%h %s (%cr by %an)"`
 ```
 
 ### Status Dashboard Output
@@ -55,12 +55,12 @@ git log -1 --format="%h %s (%cr by %an)"
 
 Detect project technology:
 
-```bash
+```
 # Package manager & framework
-ls package.json pyproject.toml Cargo.toml go.mod pom.xml build.gradle
+!`ls package.json pyproject.toml Cargo.toml go.mod pom.xml build.gradle`
 
-# Read main config
-read package.json  # or equivalent
+# Read main config (instructional - agent must read this file)
+# Read package.json  # or equivalent
 ```
 
 ### Tech Stack Analysis
@@ -101,15 +101,15 @@ read package.json  # or equivalent
 
 ```bash
 # Node.js
-npm outdated --json || pnpm outdated --json
-npm audit --json
+!`npm outdated --json || pnpm outdated --json`
+!`npm audit --json`
 
 # Python
-pip list --outdated
-pip-audit
+!`pip list --outdated`
+!`pip-audit`
 
 # Rust
-cargo outdated
+!`cargo outdated`
 cargo audit
 ```
 
@@ -132,11 +132,11 @@ npm test -- --coverage --json
 # Python
 pytest --cov --cov-report=json
 
-# Check for coverage config
-glob pattern="**/jest.config.*"
-glob pattern="**/vitest.config.*"
-glob pattern="**/pytest.ini"
-glob pattern="**/pyproject.toml"
+# Check for coverage config (instructional - agent uses glob tool)
+glob({ pattern: "**/jest.config.*" })
+glob({ pattern: "**/vitest.config.*" })
+glob({ pattern: "**/pytest.ini" })
+glob({ pattern: "**/pyproject.toml" })
 ```
 
 **Coverage Dashboard:**
@@ -153,13 +153,13 @@ glob pattern="**/pyproject.toml"
 
 ```bash
 # TypeScript type errors
-npx tsc --noEmit 2>&1 | wc -l
+!`npx tsc --noEmit 2>&1 | wc -l`
 
 # Linting issues
-npm run lint -- --format json 2>/dev/null || npx biome check --reporter=json
+!`npm run lint -- --format json 2>/dev/null || npx biome check --reporter=json`
 
 # TODO/FIXME count
-grep -r "TODO\|FIXME\|HACK\|XXX" src/ --include="*.ts" --include="*.tsx" | wc -l
+!`grep -r "TODO\|FIXME\|HACK\|XXX" src/ --include="*.ts" --include="*.tsx" | wc -l`
 ```
 
 **Quality Dashboard:**
@@ -174,15 +174,15 @@ grep -r "TODO\|FIXME\|HACK\|XXX" src/ --include="*.ts" --include="*.tsx" | wc -l
 
 ### 3.4 Documentation Status
 
-```bash
+```
 # Check for docs
-ls README.md CHANGELOG.md CONTRIBUTING.md docs/ 2>/dev/null
+!`ls README.md CHANGELOG.md CONTRIBUTING.md docs/ 2>/dev/null`
 
 # README freshness
-git log -1 --format="%cr" -- README.md
+!`git log -1 --format="%cr" -- README.md`
 
 # API docs
-ls docs/api/ openapi.yaml swagger.json 2>/dev/null
+!`ls docs/api/ openapi.yaml swagger.json 2>/dev/null`
 ```
 
 **Documentation Dashboard:**
@@ -205,52 +205,51 @@ skill({ name: "gemini-large-context" })
 
 ### 4.1 Architecture Analysis
 
-```bash
-gemini -p "@src/
+```typescript
+gemini({ prompt: "@src/
 Describe:
 1. Overall architecture pattern (MVC, Clean, Hexagonal, etc.)
 2. Key modules and their responsibilities
 3. Data flow between components
 4. External dependencies and integrations
-5. Areas of high complexity"
+5. Areas of high complexity" });
 ```
 
 ### 4.2 Test Gap Analysis
 
-```bash
-gemini -p "@src/ @tests/
+```typescript
+gemini({ prompt: "@src/ @tests/
 Assess test coverage:
 - Which modules have tests?
 - Which are missing tests?
 - Test quality (unit vs integration)
 - Edge cases covered
-- Critical paths without tests"
+- Critical paths without tests" });
 ```
 
 ### 4.3 Code Smell Detection
 
-```bash
-gemini -p "@src/
+```typescript
+gemini({ prompt: "@src/
 Identify code smells:
 - Duplicated code
 - Long functions (>50 lines)
 - Deep nesting (>4 levels)
 - God objects/files
-- Dead code
-- Inconsistent patterns"
+- Overly complex conditions" });
 ```
 
 ### 4.4 Security Analysis (--security)
 
 ```bash
 # Automated scans
-npm audit
-npx snyk test 2>/dev/null || true
+!`npm audit`
+!`npx snyk test 2>/dev/null || true`
 
 # Pattern-based detection
-grep -r "password\s*=" src/ --include="*.ts" || true
-grep -r "api_key\s*=" src/ --include="*.ts" || true
-grep -r "secret" src/ --include="*.ts" || true
+!`grep -r "password\s*=" src/ --include="*.ts" || true`
+!`grep -r "api_key\s*=" src/ --include="*.ts" || true`
+!`grep -r "secret" src/ --include="*.ts" || true`
 
 # Deep analysis with Gemini
 gemini -p "@src/ @api/
@@ -279,8 +278,8 @@ Security review:
 
 Find actionable tasks with no blockers:
 
-```typescript
-bd_ls({ status: "ready", limit: 10, offset: 0 });
+```
+!`bd list --status ready --limit 10`
 ```
 
 ### Ready Work Table
@@ -293,8 +292,8 @@ bd_ls({ status: "ready", limit: 10, offset: 0 });
 
 **Blocked Work:**
 
-```typescript
-bd_ls({ status: "blocked", limit: 5, offset: 0 });
+```
+!`bd list --status blocked --limit 5`
 ```
 
 | ID     | Title          | Blocked By | Action Needed       |
@@ -371,24 +370,12 @@ Based on analysis, generate actionable recommendations:
 
 For significant findings, create tracking issues:
 
-```typescript
-// For security vulnerabilities
-bd_add({
-  title: "[Security] Fix npm audit vulnerabilities",
-  desc: "npm audit found 2 high severity vulnerabilities:\n- lodash: prototype pollution\n- axios: SSRF\n\nRun: npm audit fix --force",
-  type: "bug",
-  pri: 1,
-  tags: ["security", "dependencies"],
-});
-
-// For test coverage
-bd_add({
-  title: "[Quality] Increase test coverage to 80%",
-  desc: "Current coverage: 78%\nTarget: 80%\n\nUncovered files:\n- src/auth/login.ts\n- src/api/users.ts",
-  type: "task",
-  pri: 2,
-  tags: ["testing", "quality"],
-});
+```bash
+# For security vulnerabilities
+bd create "[Security] Fix npm audit vulnerabilities" -t bug -p 1  # Keep as instructional
+
+# For test coverage
+bd create "[Quality] Increase test coverage to 80%" -t task -p 2  # Keep as instructional
 ```
 
 ### Suggested Follow-up Commands
@@ -460,8 +447,9 @@ Save analysis to `.opencode/memory/project/analysis-[YYYY-MM-DD].md` for trend t
 
 Compare with previous analysis:
 
-```bash
-read .opencode/memory/project/analysis-*.md
+```typescript
+glob({ pattern: ".opencode/memory/project/analysis-*.md" });
+// Then read each matched file
 ```
 
 ---

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

@@ -28,9 +28,7 @@ skill({ name: "brainstorming" });
 
 If `$ARGUMENTS` is a bead ID:
 
-```typescript
-bd_show({ id: "$ARGUMENTS" });
-```
+!`bd show $ARGUMENTS`
 
 Load constraints from `.beads/artifacts/<bead-id>/spec.md` if it exists.
 
@@ -247,14 +245,8 @@ observation({
 
 For promising ideas that need more work:
 
-```typescript
-bd_add({
-  title: "[Idea name]",
-  type: "task",
-  pri: 2,
-  desc: "From brainstorm: [topic]. Needs research/prototyping.",
-  tags: ["brainstorm"],
-});
+```bash
+bd create "[Idea name]" -t task -p 2
 ```
 
 ## Output

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

@@ -19,11 +19,9 @@ skill({ name: "verification-before-completion" });
 
 ## Phase 1: Check Git State
 
-```bash
-git status --porcelain
-git diff --stat
-git diff --cached --stat
-```
+!`git status --porcelain`
+!`git diff --stat`
+!`git diff --cached --stat`
 
 Report:
 
@@ -48,9 +46,7 @@ If nothing staged: "No changes staged. Run `git add <files>` first."
 
 Detect project type and run gates:
 
-```bash
-ls package.json Cargo.toml pyproject.toml go.mod Makefile 2>/dev/null
-```
+!`ls package.json Cargo.toml pyproject.toml go.mod Makefile 2>/dev/null`
 
 | Project | Test Command    | Lint Command                         |
 | ------- | --------------- | ------------------------------------ |
@@ -78,10 +74,8 @@ Fix errors or use `git commit --no-verify` (not recommended).
 
 ## Phase 3: Analyze Changes for Message
 
-```bash
-git diff --cached --stat
-git diff --cached
-```
+!`git diff --cached --stat`
+!`git diff --cached`
 
 Determine:
 
@@ -186,8 +180,8 @@ Options:
 
 If bead ID was provided:
 
-```typescript
-bd_sync({ reason: "Sync after commit" });
+```bash
+bd sync
 ```
 
 ## Output
@@ -221,10 +215,8 @@ Create PR:
 
 **Safety checks before amend:**
 
-```bash
-git log -1 --format='%H %s'  # What we're amending
-git status                    # Check if pushed
-```
+!`git log -1 --format='%H %s'` # What we're amending
+!`git status` # Check if pushed
 
 ```
 Amend Safety Check:

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

@@ -10,9 +10,7 @@ You're creating a new tracked task. Keep it simple unless complexity demands oth
 
 ## Check For Duplicates First
 
-```bash
-bd list --status=all | grep -i "[keywords]"
-```
+!`bd list --status=all | grep -i "[keywords]"`
 
 If similar work exists, link to it or extend it instead of creating duplicate.
 
@@ -104,14 +102,12 @@ bd dep add bd-[second] bd-[first] --type blocks
 
 Visualize:
 
-```bash
-bd dep tree bd-[epic]
-```
+!`bd dep tree bd-[epic]`
 
 ## Sync
 
-```typescript
-bd_sync({ reason: "Sync new bead" });
+```bash
+bd sync
 ```
 
 ## Output