opencodekit 0.15.21 → 0.16.0

package/dist/template/.opencode/memory/observations/2026-02-01-decision-subagents-load-minimal-skills-stay-lean.md

@@ -0,0 +1,29 @@
+---
+type: decision
+created: 2026-02-01T16:04:17.552Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["general", "subagent", "skills", "lean", "minimal", "delegation-packet", "verification"]
+---
+
+# 🎯 Subagents load minimal skills, stay lean
+
+🟢 **Confidence:** high
+
+General subagent (and other subagents) follow different skill philosophy than build leader:
+
+**Subagents stay LEAN:**
+- NO beads skill (read-only, don't modify state)
+- NO swarm-coordination (leader handles swarm)
+- NO prd/prd-task (leader responsibility)
+- NO brainstorming (execute, don't design)
+
+**Subagents load MINIMAL:**
+- ALWAYS: verification-before-completion
+- IF bug fix: systematic-debugging
+- IF test task: test-driven-development
+
+**Trust delegation packets:** If present, follow strictly without loading override skills.
+
+This keeps subagents fast, focused, and prevents skill bloat.

package/dist/template/.opencode/memory/observations/2026-02-01-decision-user-approved-permission-upgrades-in-ope.md

@@ -0,0 +1,15 @@
+---
+type: decision
+created: 2026-02-01T09:31:02.379Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["opencode.json", "permissions", "best-practices", "security", "bead-protocol"]
+files: [".opencode/opencode.json"]
+---
+
+# 🎯 User approved permission upgrades in opencode.json
+
+🟢 **Confidence:** high
+
+User asked to implement the recommended best-practice permission upgrades for .opencode/opencode.json (Tier 1 security improvements like tighter git, secret patterns, and publish protections). Proceed only after creating/claiming a bead as per protocol.

package/dist/template/.opencode/memory/observations/2026-02-01-discovery-verify-command-already-implemented.md

@@ -0,0 +1,28 @@
+---
+type: discovery
+created: 2026-02-01T15:16:50.162Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["verify", "command", "openspec", "completeness", "correctness", "coherence"]
+files: [".opencode/command/verify.md"]
+---
+
+# 💡 Verify command already implemented
+
+🟢 **Confidence:** high
+
+The `/verify` command already exists at `.opencode/command/verify.md` with full implementation:
+
+**Three dimensions:**
+1. Completeness - Are all required artifacts present? All tasks addressed?
+2. Correctness - Do automated gates pass? (build, test, lint, typecheck)
+3. Coherence - Do artifacts agree with each other? No contradictions?
+
+**Features:**
+- `--quick` - Skip coherence check, gates only
+- `--fix` - Auto-fix issues where possible
+- Multi-language support (Node, Rust, Python, Go)
+- Updates bead notes with verification results
+
+This was identified as "short-term" in OpenSpec research but is already done!

package/dist/template/.opencode/memory/observations/2026-02-01-feature-openspec-phase-b-complete-template-upgra.md

@@ -0,0 +1,43 @@
+---
+type: feature
+created: 2026-02-01T13:54:45.946Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["openspec", "templates", "context-injection", "workflow", "beads"]
+files: [".opencode/memory/_templates/proposal.md", ".opencode/memory/_templates/spec.md", ".opencode/memory/_templates/tasks.md", ".opencode/context/project.md", "opencode.json", ".opencode/opencode.json", ".opencode/memory/_templates/README.md", ".opencode/command/plan.md"]
+---
+
+# ✨ OpenSpec Phase B Complete: Template Upgrade + Context Injection
+
+🟢 **Confidence:** high
+
+## Phase B Complete
+
+Adapted OpenSpec patterns into the kit + beads system:
+
+### New Templates Created
+- `.opencode/memory/_templates/proposal.md` - Captures WHY (motivation, impact)
+- `.opencode/memory/_templates/spec.md` - WHEN/THEN behavioral requirements
+- `.opencode/memory/_templates/tasks.md` - Numbered implementation checklists
+
+### Context Injection Added
+- `.opencode/context/project.md` - Tech stack, constraints, integrations
+- Added to `opencode.json` instructions[] for auto-injection into all prompts
+
+### Key Adaptation Decisions
+1. **Kept our comprehensive style** - OpenSpec templates are minimal scaffolds (~10 lines), ours provide more structure
+2. **Used instructions[] not config.yaml** - OpenCode's native mechanism vs OpenSpec's custom parser
+3. **No CLI tooling** - We're AI-native, commands ARE the interface
+4. **Flat template structure** - No per-schema subdirectories (simpler)
+
+### OpenSpec Patterns NOT Adopted
+- Canonical spec maintenance (our beads are ephemeral)
+- Delta spec merging (no long-running specs)
+- Multiple schema workflows (keeping single flow for now)
+- Shell completions (not relevant for AI workflow)
+
+### Files Modified
+- `.opencode/opencode.json` - Added context/project.md to instructions[]
+- `.opencode/memory/_templates/README.md` - Documented all templates
+- `.opencode/command/plan.md` - Added templates reference section

package/dist/template/.opencode/memory/observations/2026-02-01-learning-build-agent-should-use-dynamic-lsp-not-f.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T10:01:36.015Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["build agent", "LSP", "dynamic tooling", "gpt-5.2-codex", "prompt update"]
+---
+
+# 📚 Build agent should use dynamic LSP, not forced 9 calls
+
+🟢 **Confidence:** high
+
+User reports that with gpt-5.2-codex, build agent prompt forces 9 LSP tool calls. User wants build agent prompt updated to use dynamic, best-practice LSP usage (only the needed operations).

package/dist/template/.opencode/memory/observations/2026-02-01-learning-kimi-k2-5-model-requires-temperature-1-0.md

@@ -0,0 +1,22 @@
+---
+type: learning
+created: 2026-02-01T04:58:58.391Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["kimi_k25", "temperature", "thinking mode", "opencode zen", "model configuration", "scout agent"]
+---
+
+# 📚 Kimi K2.5 model requires temperature 1.0
+
+🟢 **Confidence:** high
+
+The kimi_k25 (Kimi K2.5) model is a thinking mode model that requires temperature to be exactly 1.0. The parameter is immutable - you cannot set custom temperatures.
+
+Error message: "Parameter 'temperature' is immutable for kimi_k25 and must be 1.0 (thinking mode). Got 0.3."
+
+Solution options:
+1. Change scout.md temperature from 0.3 to 1.0 to use kimi-k2.5-free
+2. Use a different model like minimax-m2.1-free that supports custom temperatures
+
+Other thinking models in opencode.json also have "temperature": 1 in their configuration (e.g., big-pickle, glm-4.6, glm-4.7 with reasoning enabled).

package/dist/template/.opencode/memory/observations/2026-02-01-learning-opencode-context-injection-already-imple.md

@@ -0,0 +1,27 @@
+---
+type: learning
+created: 2026-02-01T15:16:13.160Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["opencode", "context-injection", "instructions", "agents-md", "config"]
+files: ["AGENTS.md", ".opencode/memory/user.md", "project/tech-stack.md", ".opencode/AGENTS.md"]
+---
+
+# 📚 OpenCode context injection already implemented
+
+🟢 **Confidence:** high
+
+OpenCode doesn't support `context` or `rules` fields from OpenSpec research.
+
+Instead, OpenCode uses:
+1. `instructions` array in opencode.json → files injected into prompts (we have: user.md, tech-stack.md)
+2. `AGENTS.md` files → rules and guidelines (project-level + global)
+3. `command` field in opencode.json → per-command customization
+
+Our current setup already follows best practices:
+- `.opencode/memory/user.md` + `project/tech-stack.md` via instructions[]
+- `.opencode/AGENTS.md` for global rules
+- `.opencode/command/*.md` for commands
+
+No additional context injection needed - we're already doing it right!

package/dist/template/.opencode/memory/observations/2026-02-01-learning-opencode-context-injection-uses-instruct.md

@@ -0,0 +1,35 @@
+---
+type: learning
+created: 2026-02-01T13:39:55.750Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["opencode", "openspec", "context injection", "instructions", "config", "prompt", "agent configuration"]
+files: [".opencode/memory/project/context.md"]
+---
+
+# 📚 OpenCode context injection uses 'instructions' not 'context'
+
+🟢 **Confidence:** high
+
+OpenCode config (opencode.json) doesn't have a `context` field like OpenSpec's config.yaml. Instead, it uses:
+
+1. **`instructions`** - Array of file paths that get injected into prompts
+   - Current: `[".opencode/memory/user.md", ".opencode/memory/project/*.md"]`
+   - These files are loaded and included in the system prompt
+
+2. **Per-agent `prompt`** - Custom prompt string per agent via `agent.<name>.prompt`
+
+3. **Per-command `template`** - Via `command.<name>.template`
+
+OpenSpec's approach:
+- `context:` - Global context injected into ALL artifacts
+- `rules:` - Per-artifact rules (e.g., `rules.proposal: ["Include rollback plan"]`)
+
+To adapt OpenSpec's context injection pattern to OpenCode:
+- Use `instructions` with well-structured markdown files
+- Create `.opencode/memory/project/context.md` for global project context
+- Use agent-specific `prompt` fields for per-agent rules
+- Or create command-specific files that commands load via skill pattern
+
+Key difference: OpenCode's approach is file-based, OpenSpec's is config-based inline text.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-update-build-agent-prompt-to-use-context.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T10:05:57.086Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["build agent", "prompt", "LSP", "contextual usage", "best practice"]
+---
+
+# 📚 Update build agent prompt to use contextual LSP
+
+🟢 **Confidence:** high
+
+User wants the build agent prompt updated to avoid forcing all 9 LSP calls. They want a brutal, best-practice policy: use LSP contextually (documentSymbol/hover first, add other ops only when needed).

package/dist/template/.opencode/memory/observations/2026-02-01-learning-upgrade-agents-md-using-opencode-expert-.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T10:26:42.193Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["AGENTS.md", "opencode-expert", "project rules", "opencode kit"]
+---
+
+# 📚 Upgrade AGENTS.md using opencode-expert reference
+
+🟢 **Confidence:** high
+
+User requested upgrading project rules in AGENTS.md for an OpenCode kit, referencing dmmulroy/.dotfiles opencode-expert.md.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-upgrade-agents-md-with-opencode-expert-g.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T10:27:47.569Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["AGENTS.md", "opencode-expert", "configuration", "best practices"]
+---
+
+# 📚 Upgrade AGENTS.md with OpenCode expert guidance
+
+🟢 **Confidence:** high
+
+User requested a focused upgrade to AGENTS.md using dmmulroy/.dotfiles opencode-expert.md as reference for OpenCode configuration best practices and links.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-upgrade-agents-md-with-opencode-expert-r.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T10:27:01.422Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["AGENTS.md", "opencode-expert", "project rules", "opencode kit"]
+---
+
+# 📚 Upgrade AGENTS.md with OpenCode expert rules
+
+🟢 **Confidence:** high
+
+User requested upgrading project AGENTS.md using dmmulroy/.dotfiles opencode-expert.md as reference to make the kit better for OpenCode users.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-user-prefers-copilot-gpt-5-2-codex-mediu.md

@@ -0,0 +1,14 @@
+---
+type: learning
+created: 2026-02-01T09:56:48.021Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["copilot", "gpt-5.2-codex", "medium", "speed", "model preference"]
+---
+
+# 📚 User prefers Copilot GPT-5.2-Codex medium for speed
+
+🟢 **Confidence:** high
+
+User reports that GitHub Copilot gpt-5.2-codex medium variant provides good speed and is preferred for their OpenCode setup.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-user-wants-general-agent-prompt-contextu.md

@@ -0,0 +1,15 @@
+---
+type: learning
+created: 2026-02-01T10:19:23.691Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["general agent", "LSP", "contextual usage", "prompt update"]
+files: [".opencode/agent/general.md"]
+---
+
+# 📚 User wants general agent prompt contextual LSP
+
+🟢 **Confidence:** high
+
+User asked to update .opencode/agent/general.md to use contextual LSP usage (avoid forced LSP calls), similar to build agent prompt.

package/dist/template/.opencode/memory/observations/2026-02-01-learning-user-wants-general-agent-prompt-reviewed.md

@@ -0,0 +1,15 @@
+---
+type: learning
+created: 2026-02-01T10:18:29.926Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["general agent", "prompt review", "LSP policy", "best practice", "opencode"]
+files: [".opencode/agent/general.md"]
+---
+
+# 📚 User wants general agent prompt reviewed and tightened
+
+🟢 **Confidence:** high
+
+User requested a review of .opencode/agent/general.md and wants a more brutal/best-practice upgrade similar to build agent prompt changes (e.g., LSP usage policy).

package/dist/template/.opencode/memory/project/command-rules.md

@@ -0,0 +1,122 @@
+---
+purpose: Per-command context and rules injected during command execution
+updated: 2026-02-01
+pattern: OpenSpec context/rules injection adapted for OpenCodeKit
+---
+
+# Command-Specific Rules
+
+Rules automatically injected based on active command context.
+
+## Planning Commands
+
+### /plan
+
+- Include rollback plan for risky changes
+- Break tasks into independently-testable units
+- Estimate complexity per task (S/M/L)
+- Identify dependencies between tasks explicitly
+
+### /design
+
+- Research existing patterns before proposing new ones
+- Include concrete file paths in all designs
+- Show interface contracts for public APIs
+- Specify error handling strategy
+
+### /research
+
+- Cite sources with URLs
+- Distinguish facts from inferences
+- Note confidence level (high/medium/low)
+- Identify gaps in available information
+
+## Implementation Commands
+
+### /start
+
+- Check for existing bead before creating new
+- Load relevant memory files first
+- Verify task context with `bd show <id>`
+
+### /resume
+
+- Re-read spec before continuing
+- Check what's already completed
+- Don't re-implement existing work
+
+### /ship
+
+- Run all verification gates before claiming done
+- Include test evidence in close reason
+- Never skip lint/typecheck even for "small" changes
+
+## Review Commands
+
+### /review
+
+- Focus on correctness over style
+- Identify security implications
+- Check for unhandled edge cases
+- Suggest simplifications where possible
+
+### /verify
+
+- Check completeness: all artifacts exist
+- Check correctness: implementation matches spec
+- Check coherence: no contradictions between artifacts
+
+### /ui-review
+
+- Check accessibility (WCAG compliance)
+- Verify responsive behavior
+- Identify inconsistent patterns
+
+## Handoff Commands
+
+### /handoff
+
+- Include current bead state
+- List completed vs remaining tasks
+- Note any blockers or decisions needed
+- Provide session context for continuity
+
+### /init
+
+- Don't overwrite existing memory files
+- Detect project type from existing files
+- Set up minimal viable structure first
+
+## Context Injection
+
+These rules are automatically considered when:
+
+1. User invokes a command explicitly (e.g., `/plan`)
+2. Agent recognizes a command-like workflow
+3. Subagent receives delegated work matching a command pattern
+
+---
+
+## Tech Stack Rules (Project-Specific)
+
+When working in this project, always:
+
+- **Runtime**: Use Bun (not Node.js)
+- **Language**: TypeScript with ESM imports
+- **Linting**: Run `npm run lint:fix` before commits
+- **Types**: Run `npm run typecheck` to validate
+- **Formatting**: Use Biome (configured in biome.json)
+
+## Git Rules
+
+- Never commit to main directly
+- Always ask before `git push`
+- Use conventional commit format: `type(scope): message`
+- Never force push unless explicitly requested
+
+## File Structure Rules
+
+- Commands go in `.opencode/command/`
+- Skills go in `.opencode/skill/`
+- Memory files go in `.opencode/memory/`
+- Plugin code goes in `.opencode/plugin/`

package/dist/template/.opencode/memory/project/tech-stack.md

@@ -0,0 +1,50 @@
+---
+purpose: Tech stack, constraints, and integrations for AI context injection
+updated: 2026-02-01
+---
+
+# Tech Stack
+
+This file is automatically injected into ALL AI prompts via `opencode.json` instructions[].
+
+## Framework & Language
+
+- **Framework:** [e.g., Next.js 15, React 19]
+- **Language:** TypeScript (strict mode)
+- **Runtime:** [e.g., Node.js 22, Bun 1.x]
+
+## Styling & UI
+
+- **CSS:** [e.g., Tailwind CSS v4]
+- **Components:** [e.g., shadcn/ui, Radix Primitives]
+- **Design System:** [e.g., Custom tokens in tailwind.config.ts]
+
+## Data & State
+
+- **Database:** [e.g., PostgreSQL via Supabase]
+- **ORM:** [e.g., Drizzle, Prisma]
+- **State Management:** [e.g., Zustand, React Query]
+- **API Style:** [e.g., REST, tRPC, GraphQL]
+
+## Testing
+
+- **Unit Tests:** [e.g., Vitest]
+- **E2E Tests:** [e.g., Playwright]
+- **Coverage Target:** [e.g., 80%]
+
+## Key Constraints
+
+- [Constraint 1: e.g., Must work offline]
+- [Constraint 2: e.g., WCAG 2.1 AA compliance required]
+- [Constraint 3: e.g., Bundle size < 500KB]
+
+## Active Integrations
+
+- [Service 1: e.g., Stripe for payments]
+- [Service 2: e.g., Resend for email]
+- [Service 3: e.g., Sentry for error tracking]
+
+---
+
+_Update this file when tech stack or constraints change._
+_AI will capture architecture, conventions, and gotchas via the `observation` tool as it works._