opencodekit 0.12.5 → 0.12.7

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

@@ -1,143 +0,0 @@
----
-description: Implement a bead - load context, make changes, verify
-argument-hint: "<bead-id>"
-agent: build
----
-
-# Implement: $ARGUMENTS
-
-You're implementing a tracked task. Stay focused, verify as you go, hand off if you hit limits.
-
-## First: Load Context
-
-```typescript
-skill({ name: "beads" });
-skill({ name: "test-driven-development" });
-skill({ name: "verification-before-completion" });
-```
-
-Get the task details and check for messages:
-
-```bash
-bd show $ARGUMENTS
-bd list --status=in_progress  # See what else is active
-```
-
-Check git state. If dirty, ask whether to stash, commit, or continue:
-
-```bash
-git status --porcelain
-git branch --show-current
-```
-
-Create a branch if not already on one for this task:
-
-```bash
-git checkout -b $ARGUMENTS
-```
-
-Mark the task in progress:
-
-```bash
-bd update $ARGUMENTS --status in_progress
-```
-
-## Load Artifacts
-
-Check what context exists:
-
-```bash
-ls .beads/artifacts/$ARGUMENTS/ 2>/dev/null || echo "No artifacts"
-```
-
-If `plan.md` exists, follow it step by step. If only `spec.md` exists, implement directly from requirements. If nothing exists, work from the bead description.
-
-Check for previous session work:
-
-```typescript
-list_sessions({ project: "current", limit: 3 });
-read_session({ session_reference: "last", project: "current" });
-```
-
-## Estimate Your Budget
-
-Look at the task complexity and set limits:
-
-- **Small** (~10 tool calls): Simple change, one file, clear path
-- **Medium** (~30 tool calls): Multiple files, some exploration needed
-- **Large** (~100 tool calls): Cross-cutting, needs research, checkpoint often
-- **XL**: Should be decomposed into smaller tasks first
-
-If you hit 80% of budget without finishing, create a handoff. Don't push past limits and produce garbage.
-
-## Do The Work
-
-Detect project type and know your verification commands:
-
-```bash
-ls package.json Cargo.toml pyproject.toml go.mod Makefile 2>/dev/null
-```
-
-Node/TypeScript: `npm test`, `npm run lint && npm run type-check`
-Rust: `cargo test`, `cargo clippy -- -D warnings`
-Python: `pytest`, `ruff check . && mypy .`
-Go: `go test ./...`, `golangci-lint run`
-
-**Rules while implementing:**
-
-1. Read before edit. Always.
-2. Run verification after each logical change
-3. If something fails 3 times, stop and try a different approach
-4. Checkpoint commit after significant progress: `git commit -m "WIP: $ARGUMENTS - [step]"`
-5. If blocked on external dependency, create a new bead for it and move on
-
-Track your progress. Every 10 tool calls, check: Am I on track? Should I checkpoint? Am I approaching budget?
-
-## Before Claiming Done
-
-Verify against success criteria in the spec:
-
-```bash
-cat .beads/artifacts/$ARGUMENTS/spec.md | grep -A 20 "Success Criteria"
-```
-
-Run each verification command. All must pass. No exceptions.
-
-Run the full test suite one more time:
-
-```bash
-# Whatever your project uses
-npm test && npm run type-check
-```
-
-## Complete
-
-If all gates pass:
-
-```bash
-git add -A
-git commit -m "$ARGUMENTS: [summary]"
-bd sync
-```
-
-Report what was done and suggest next step:
-
-```
-Done: $ARGUMENTS
-
-Changes: [files modified]
-Tests: Pass
-Next: /finish $ARGUMENTS
-```
-
-If gates fail, fix them. Don't proceed with broken code.
-
-## If You Can't Finish
-
-Hit budget limit or context getting too large? Create a handoff:
-
-```
-/handoff $ARGUMENTS "Stopped at [step]. Next: [what to do]"
-```
-
-Then start a fresh session. Don't grind past diminishing returns.

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

@@ -1,252 +0,0 @@
----
-description: Create and submit pull request with bead traceability
-argument-hint: "<bead-id> [--draft] [--wait]"
-agent: build
----
-
-# Pull Request
-
-**Load skills:**
-
-```typescript
-skill({ name: "beads" }); // Session protocol
-skill({ name: "verification-before-completion" });
-```
-
-## Options
-
-- `--draft`: Create as draft PR (for WIP or early feedback)
-- `--wait`: Wait for CI checks to pass after creation
-
-## Phase 1: Pre-PR Verification
-
-Before creating PR, run verification gates:
-
-```bash
-git status --porcelain  # Check for uncommitted changes
-```
-
-If uncommitted changes exist, ask: "Commit these changes first?"
-
-Run project gates:
-
-```bash
-npm run build 2>&1 | tail -5
-npm test 2>&1 | tail -10
-npm run lint 2>&1 | tail -5
-```
-
-```
-Pre-PR Gates:
-━━━━━━━━━━━━━
-
-Build: [✓/✗]
-Tests: [✓/✗]
-Lint:  [✓/✗]
-```
-
-**If any gate fails: STOP.**
-
-```
-Cannot create PR: [gate] failed.
-
-Fix errors first, then run /pr again.
-```
-
-## Phase 2: Check for Conflicts
-
-```bash
-git fetch origin main
-git merge-base --is-ancestor origin/main HEAD || git diff origin/main...HEAD --name-only
-```
-
-Check for merge conflicts:
-
-```bash
-git merge --no-commit --no-ff origin/main 2>&1 || true
-git merge --abort 2>/dev/null || true
-```
-
-If conflicts detected:
-
-```
-⚠️  Merge conflicts detected with main:
-- [file1]
-- [file2]
-
-Resolve conflicts before creating PR:
-  git fetch origin main
-  git rebase origin/main
-  # Fix conflicts, then /pr again
-```
-
-## Phase 3: Gather Context
-
-**Current state:**
-
-```bash
-git branch --show-current
-git diff main...HEAD --stat
-git log main...HEAD --oneline
-```
-
-**Load bead context (if provided):**
-
-```bash
-bd show $ARGUMENTS
-```
-
-**Load artifacts:**
-
-```bash
-ls .beads/artifacts/<bead-id>/ 2>/dev/null
-cat .beads/artifacts/<bead-id>/spec.md 2>/dev/null | head -30
-cat .beads/artifacts/<bead-id>/review.md 2>/dev/null | head -30
-```
-
-Extract from artifacts:
-
-- **Goal** from spec.md
-- **Changes Made** from review.md
-- **Estimation Accuracy** from review.md
-- **Success Criteria** verification
-
-## Phase 4: Push Branch
-
-```bash
-git push -u origin $(git branch --show-current)
-```
-
-## Phase 5: Create PR
-
-Generate PR content from context:
-
-```bash
-gh pr create --title "<title>" --body "$(cat <<'EOF'
-## Summary
-
-[1-2 sentence description of what this PR does and why]
-
-## Changes
-
-| File | Change |
-| ---- | ------ |
-| `src/foo.ts` | [description] |
-| `src/bar.ts` | [description] |
-
-## Testing
-
-**Automated:**
-- All tests pass ✓
-- Lint passes ✓
-- Type check passes ✓
-
-**Manual verification:**
-- [ ] [How to test manually]
-
-## Screenshots
-
-[If UI changes, include before/after screenshots]
-
-## Estimation
-
-| Metric | Value |
-| ------ | ----- |
-| Estimated | [S/M/L] (~N calls) |
-| Actual | N calls |
-| Accuracy | [+/-N%] |
-
-## Checklist
-
-- [x] Tests added/updated
-- [x] All gates pass
-- [ ] Docs updated (if applicable)
-- [ ] Breaking changes documented (if any)
-
-## Artifacts
-
-- [spec.md](.beads/artifacts/<bead-id>/spec.md)
-- [review.md](.beads/artifacts/<bead-id>/review.md)
-[- research.md, plan.md, adr.md if they exist]
-
-## Bead Reference
-
-Closes: <bead-id>
-EOF
-)"
-```
-
-**For draft PRs (--draft):**
-
-```bash
-gh pr create --draft --title "<title>" --body "..."
-```
-
-## Phase 6: Wait for CI (if --wait)
-
-```bash
-gh pr checks --watch
-```
-
-Report CI status:
-
-```
-CI Status:
-━━━━━━━━━━
-
-- build: [✓/✗/pending]
-- test: [✓/✗/pending]
-- lint: [✓/✗/pending]
-
-[If all pass] CI passed ✓
-[If any fail] CI failed: [which check]
-```
-
-## Phase 7: Update Bead & Sync
-
-```bash
-bd-msg --subj "PR created" --body "PR: <pr-url>\nStatus: [ready/draft]\nCI: [passing/pending]" --to "all" --importance normal
-bd sync
-```
-
-## Output
-
-```
-PR Created: <bead-id>
-━━━━━━━━━━━━━━━━━━━━
-
-URL: <pr-url>
-Status: [Ready for Review / Draft]
-Branch: <branch> → main
-
-Pre-PR Gates: All passed ✓
-Conflicts: None ✓
-[CI: Passed ✓ (if --wait)]
-
-Artifacts linked:
-- spec.md ✓
-- review.md ✓
-[- research.md, plan.md, adr.md]
-```
-
-**Next steps:**
-
-```
-━━━━━━━━━━━━━━━━━━━━
-
-Request review:
-  gh pr edit <pr-number> --add-reviewer <username>
-
-Check CI:
-  gh pr checks
-
-Merge when approved:
-  gh pr merge --squash
-```
-
-**If draft PR:**
-
-```
-Draft PR created. When ready:
-  gh pr ready
-```