opencodekit 0.0.1

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

@@ -0,0 +1,233 @@
+---
+description: Finish a bead - hard gates, commit, close
+argument-hint: "<bead-id>"
+agent: build
+---
+
+# Finish
+
+## Phase 1: Load Bead
+
+```bash
+bd show $ARGUMENTS --json
+```
+
+Verify status is `in-progress` or `open`.
+
+## Phase 2: Detect Project Type
+
+Check which project files exist to determine verification commands:
+
+```bash
+ls package.json Cargo.toml pyproject.toml setup.py Makefile go.mod 2>/dev/null || true
+```
+
+**Node.js/TypeScript** (`package.json` exists):
+
+- Build: `npm run build` or `bun run build`
+- Test: `npm test` or `bun test`
+- Lint: `npm run lint` or `bun run lint`
+- Type check: `npm run type-check` or `bun run type-check`
+
+**Rust** (`Cargo.toml` exists):
+
+- Build: `cargo build`
+- Test: `cargo test`
+- Lint: `cargo clippy -- -D warnings`
+
+**Python** (`pyproject.toml` or `setup.py` exists):
+
+- Test: `pytest`
+- Lint: `ruff check .` or `flake8`
+- Type check: `mypy .`
+
+**Go** (`go.mod` exists):
+
+- Build: `go build ./...`
+- Test: `go test ./...`
+- Lint: `golangci-lint run`
+
+**Make-based** (`Makefile` exists, no other markers):
+
+- Build: `make build`
+- Test: `make test`
+- Lint: `make lint`
+
+**No recognized files:** Skip automated gates, proceed to Phase 4.
+
+Check if each command actually exists before running (e.g., verify script exists in `package.json`).
+
+## Phase 3: Hard Gates (MUST ALL PASS)
+
+Run detected verification commands. Skip any that don't exist for the project.
+
+Report:
+
+```
+Finish Gates: <bead-id>
+━━━━━━━━━━━━━━━━━━━━━━
+Project: [detected type]
+
+Build:      [✓/✗/skipped]
+Tests:      [✓/✗/skipped]
+Lint:       [✓/✗/skipped]
+Type check: [✓/✗/skipped]
+```
+
+**If ANY gate fails: STOP.**
+
+```
+Cannot finish: [gate name] failed.
+
+Fix errors and run /finish again.
+```
+
+Do not proceed. Do not offer workarounds.
+
+## Phase 4: Verify Success Criteria
+
+Read spec:
+
+```bash
+cat .beads/artifacts/<bead-id>/spec.md
+```
+
+Check each success criterion:
+
+```
+Success Criteria:
+- [x] [Criterion 1] - verified by [how]
+- [x] [Criterion 2] - verified by [how]
+- [ ] [Criterion 3] - NOT MET: [reason]
+```
+
+**If any criterion not met: STOP.**
+
+```
+Cannot finish: Success criteria not met.
+
+Missing:
+- [Criterion] - [what's needed]
+```
+
+## Phase 5: Create Review
+
+Write `.beads/artifacts/<bead-id>/review.md`:
+
+```markdown
+# Review: [Title]
+
+**Bead:** <bead-id>
+**Completed:** <date>
+
+## Changes Made
+
+| File         | Change        |
+| ------------ | ------------- |
+| `src/foo.ts` | [description] |
+| `src/bar.ts` | [description] |
+
+## What Worked
+
+- [Thing that went well]
+
+## What Was Skipped
+
+- [Thing intentionally not done and why]
+
+## Inconsistencies Found
+
+- [Any issues discovered but not fixed]
+
+## Test Coverage
+
+- [New tests added]
+- [Existing tests modified]
+
+## Success Criteria
+
+- [x] [Criterion 1]
+- [x] [Criterion 2]
+```
+
+## Phase 6: Final Commit
+
+```bash
+git add -A
+git status
+```
+
+Commit with bead reference:
+
+```bash
+git commit -m "<bead-id>: [summary of changes]
+
+- [bullet 1]
+- [bullet 2]
+
+Closes: <bead-id>"
+```
+
+## Phase 7: Close Bead
+
+```bash
+bd close $ARGUMENTS --reason "Implemented: [1-liner summary]"
+```
+
+## Phase 8: Database Health Check
+
+Check issue count:
+
+```bash
+bd list --status all 2>/dev/null | wc -l
+```
+
+**If >200 issues:** Warn about performance.
+
+**If >500 issues:** Strongly recommend cleanup.
+
+## Output
+
+```
+Bead Closed: <bead-id>
+━━━━━━━━━━━━━━━━━━━━━
+
+Gates: All passed ✓
+Criteria: All met ✓
+Commit: [commit hash]
+
+Artifacts:
+- .beads/artifacts/<bead-id>/spec.md
+- .beads/artifacts/<bead-id>/research.md
+- .beads/artifacts/<bead-id>/plan.md
+- .beads/artifacts/<bead-id>/review.md
+
+Branch: <bead-id>
+```
+
+**If issue count >200:**
+
+```
+⚠️  Database has [count] issues. Consider running:
+    bd cleanup --older-than 7d && bd sync
+```
+
+**Session recommendation:**
+
+```
+━━━━━━━━━━━━━━━━━━━━━
+Task complete. For best performance:
+→ Start a fresh agent session for next task
+→ Previous work available via read_session("last")
+
+Next: Create PR or merge to main
+```
+
+**If work was interrupted or partially complete:**
+
+```
+⚠️  Work incomplete? Create handoff:
+    /handoff <bead-id> "Resume: [what's left]"
+
+Next session: /resume <bead-id>
+```

package/dist/template/.opencode/command/fix-ci.md

@@ -0,0 +1,20 @@
+---
+description: Analyze Github Actions logs and fix issues
+argument-hint: "[github-actions-url]"
+---
+
+## Github Actions URL
+
+<url>$ARGUMENTS</url>
+
+## Workflow
+
+- Use `build` agent to read the GitHub Actions logs, analyze and find the root causes of the issues.
+- For complex CI/CD problems (≥3 phases), delegate to `planner` agent to create a detailed implementation plan.
+- Use `build` agent to implement the fixes step by step.
+- Use `review` agent to run tests, ensure quality and security, then report back.
+- If there are issues or failed tests, `build` agent will fix them and repeat the process until all tests pass.
+
+## Notes
+
+- If `gh` command is not available, instruct the user to install and authorize GitHub CLI first.

package/dist/template/.opencode/command/fix-types.md

@@ -0,0 +1,10 @@
+---
+description: Fix type errors
+---
+
+Run `bun run typecheck` and fix all type errors.
+
+## Rules
+
+- Fix all of type errors and repeat the process until there are no more type errors.
+- Do not use `any` just to pass the type check.

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

@@ -0,0 +1,22 @@
+---
+description: Analyze and fix UI issues
+argument-hint: "[issue]"
+agent: build
+---
+
+# Fix UI: $ARGUMENTS
+
+use_skill("frontend-aesthetics")
+
+1. **Analyze:**
+   - If screenshots/videos provided, describe issue in detail
+   - For large UI analysis, use Gemini CLI: `gemini` then `@[image] Analyze issue`
+2. **Research:** Check design guidelines, component patterns
+   - Apply `frontend-aesthetics` criteria (typography, color, motion, backgrounds)
+3. **Fix:** Implement step by step
+   - Avoid generic AI aesthetics (Inter font, purple gradients, flat backgrounds)
+   - Use distinctive typography, cohesive themes, meaningful motion
+4. **Verify:** Screenshot/test the fix
+5. **Review:** Run tests, ensure quality
+
+If bead exists, update `.beads/artifacts/<bead-id>/review.md` and run `/finish`.

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

@@ -0,0 +1,22 @@
+---
+description: Debug and fix issues
+argument-hint: "[issue]"
+agent: build
+---
+
+# Fix: $ARGUMENTS
+
+**Simple (1-3 lines, obvious cause):** Fix directly, commit.
+
+**Complex (unclear cause, multiple files):**
+
+use_skill("systematic-debugging")
+
+Follow four phases:
+
+1. Root cause investigation (NO fixes yet)
+2. Pattern analysis
+3. Hypothesis testing
+4. Implementation with TDD
+
+If bead exists, work within `.beads/artifacts/<bead-id>/spec.md` constraints.

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

@@ -0,0 +1,146 @@
+---
+description: Create handoff for next session - save state with repo provenance
+argument-hint: "<bead-id> [instructions]"
+agent: build
+---
+
+# Handoff
+
+## Phase 1: Gather State
+
+```bash
+# Bead info
+bd show $ARGUMENTS --json
+
+# Git state
+git remote get-url origin 2>/dev/null
+git branch --show-current
+git rev-parse HEAD
+git status --porcelain
+
+# Uncommitted changes
+git diff --stat
+```
+
+## Phase 2: Commit WIP (if needed)
+
+If uncommitted changes exist:
+
+```bash
+git add -A
+git commit -m "WIP: <bead-id> - [current step]"
+```
+
+## Phase 3: Create Handoff
+
+Write `.beads/artifacts/<bead-id>/handoffs/<timestamp>.md`:
+
+```markdown
+# Handoff: <bead-id>
+
+**Created:** <ISO timestamp>
+**Agent:** build
+
+## Provenance
+
+| Key    | Value            |
+| ------ | ---------------- |
+| Repo   | [git remote URL] |
+| Branch | [branch name]    |
+| Commit | [commit hash]    |
+| Clean  | [yes/no]         |
+
+## Session Context
+
+**Current Session:** [session ID from OpenCode]
+**Token Usage:** [if available]
+
+Next session can load context with:
+```
+
+read_session("last", project="current")
+
+```
+
+## Bead State
+
+| Key      | Value      |
+| -------- | ---------- |
+| ID       | <bead-id>  |
+| Title    | [title]    |
+| Status   | [status]   |
+| Priority | [priority] |
+
+## Progress
+
+### Completed
+
+- [x] [Step/task completed]
+- [x] [Step/task completed]
+
+### In Progress
+
+- [ ] [Current step] - [where stopped]
+
+### Remaining
+
+- [ ] [Step not started]
+- [ ] [Step not started]
+
+## Context
+
+### Key Files
+
+- `src/foo.ts:42` - [why relevant]
+- `src/bar.ts` - [why relevant]
+
+### Decisions Made
+
+- [Decision 1] - [reason]
+- [Decision 2] - [reason]
+
+### Blockers/Issues
+
+- [Issue 1] - [status]
+
+## Resume Instructions
+
+[Specific instructions for next session]
+
+1. [First thing to do]
+2. [Second thing to do]
+
+**Recommended:** Start next session with `/resume <bead-id>` to auto-load this handoff + previous session context.
+
+## Artifacts
+
+- spec.md: [exists/missing]
+- research.md: [exists/missing]
+- plan.md: [exists/missing]
+```
+
+## Phase 4: Update Bead
+
+```bash
+bd edit <bead-id> --note "Handoff created. Resume with /resume <bead-id>"
+```
+
+## Output
+
+```
+Handoff Created: <bead-id>
+━━━━━━━━━━━━━━━━━━━━━━━━
+
+Commit: [hash]
+Branch: [branch]
+
+Saved: .beads/artifacts/<bead-id>/handoffs/<timestamp>.md
+
+Resume: /resume <bead-id>
+
+Next session will auto-load:
+- This handoff
+- Previous session context (read_session)
+- Git state
+- Bead artifacts
+```

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

@@ -0,0 +1,167 @@
+---
+description: Implement a bead - setup workspace, execute changes, verify
+argument-hint: "<bead-id>"
+agent: build
+---
+
+# Implement
+
+## Phase 1: Setup Workspace
+
+```bash
+bd show $ARGUMENTS --json
+```
+
+Check git state:
+
+```bash
+git status --porcelain
+git branch --show-current
+```
+
+If uncommitted changes exist, ask: "Stash, commit, or continue?"
+
+Create branch if not on bead branch:
+
+```bash
+git checkout -b <bead-id>
+```
+
+## Phase 2: Load Context
+
+**Check for previous session work:**
+
+```bash
+list_sessions(project="current", limit=3)
+```
+
+If recent session exists:
+
+```bash
+read_session("last", project="current")
+```
+
+Review what was already attempted/completed.
+
+Check what artifacts exist:
+
+```bash
+ls .beads/artifacts/<bead-id>/ 2>/dev/null || echo "No artifacts yet"
+```
+
+**If `plan.md` exists:** Follow the plan step-by-step (Phase 4).
+
+**If `research.md` exists but no plan:** Ask user "Create plan first? Or implement directly?"
+
+**If only `spec.md` exists (Quick Mode):** Read spec and implement directly based on requirements. No plan needed for simple tasks.
+
+**If no artifacts:** Read bead description and implement based on that.
+
+Check for handoffs:
+
+```bash
+ls .beads/artifacts/<bead-id>/handoffs/ 2>/dev/null
+```
+
+If handoff exists, load latest and continue from checkpoint.
+
+## Phase 3: Detect Project Type
+
+Check which project files exist:
+
+```bash
+ls package.json Cargo.toml pyproject.toml setup.py Makefile go.mod 2>/dev/null || true
+```
+
+**Node.js/TypeScript** (`package.json`): `npm test`, `npm run lint`, `npm run type-check`
+
+**Rust** (`Cargo.toml`): `cargo test`, `cargo clippy -- -D warnings`
+
+**Python** (`pyproject.toml` or `setup.py`): `pytest`, `ruff check .`, `mypy .`
+
+**Go** (`go.mod`): `go test ./...`, `golangci-lint run`
+
+**Make-based** (`Makefile`): `make test`, `make lint`
+
+**No recognized files:** Skip automated verification.
+
+Report:
+
+```
+Implementing: <bead-id>
+━━━━━━━━━━━━━━━━━━━━━━
+Project: [detected type]
+Mode: [Quick/Planned]
+```
+
+## Phase 4: Implementation
+
+### With Plan (Planned Mode)
+
+For each unchecked step in plan.md:
+
+1. Make changes to listed files
+2. Run verification (test/lint/type-check)
+3. Mark step complete: `- [x]`
+4. Commit if significant
+
+### Without Plan (Quick Mode)
+
+1. Read spec requirements
+2. Identify files to change
+3. Make minimal, focused changes
+4. Run verification after each logical change
+5. Keep changes atomic and reviewable
+
+**Gate rules:**
+
+- Type check fails → Fix before proceeding
+- Tests fail → Fix before proceeding
+- Lint fails → Fix if auto-fixable, else note
+
+## Phase 5: Progress Report
+
+After each change:
+
+```
+Progress: <bead-id>
+━━━━━━━━━━━━━━━━━━
+
+Changes:
+- src/foo.ts:15 - [what changed]
+
+Verification: Test ✓ | Lint ✓ | Types ✓
+
+Continue? (yes/pause/stop)
+```
+
+If "pause" or "stop": Run `/handoff <bead-id>`.
+
+## Phase 6: Complete
+
+When done:
+
+```
+Implementation Complete: <bead-id>
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Final verification running...
+```
+
+Run full verification suite.
+
+If all pass:
+
+```
+All gates passed ✓
+
+Next: /finish <bead-id>
+```
+
+If any fail:
+
+```
+Gate failed: [which one]
+
+Fix issues before running /finish.
+```