npm - opencodekit - Versions diffs - 0.15.21 → 0.16.0 - Mend

opencodekit 0.15.21 → 0.16.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (116) hide show

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

@@ -1,373 +0,0 @@
----
-description: Brainstorm and explore ideas with structured ideation
-argument-hint: "<topic or bead-id> [--quick]"
-agent: plan
-subtask: true
----
-# Brainstorm: $ARGUMENTS
-## Load Beads Skill
-```typescript
-skill({ name: "beads" });
-```
-## Options
-- `--quick`: 15-minute time box (default: 30 minutes)
-## Phase 1: Load Context
-**Load skill:**
-```typescript
-skill({ name: "brainstorming" });
-```
-**Check for bead context:**
-If `$ARGUMENTS` is a bead ID:
-!`bd show $ARGUMENTS`
-Load constraints from `.beads/artifacts/<bead-id>/spec.md` if it exists.
-**Check for prior thinking (Semantic Search):**
-```typescript
-// Search for related ideas and past brainstorms
-memory -
-  search({
-    query: "[topic keywords]",
-    mode: "semantic",
-    limit: 5,
-  });
-// Find related observations
-memory -
-  search({
-    query: "[topic]",
-    mode: "semantic",
-    type: "observation",
-    limit: 3,
-  });
-```
-Review findings for:
-- Previous brainstorms on similar topics
-- Related decisions and patterns
-- Ideas that were considered before
-If memory search fails (Ollama not running), continue without it.
-## Phase 2: Set Boundaries
-Before brainstorming, establish:
-```
-Brainstorm Session: $ARGUMENTS
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Topic: [what we're exploring]
-Goal: [what decision/outcome we need]
-Constraints: [hard limits from spec or user]
-Time box: [15/30 minutes]
-Out of scope:
-- [what we're NOT considering]
-```
-## Phase 3: Diverge (Generate Ideas)
-**Goal:** Quantity over quality. No evaluation yet.
-Generate 5-10 ideas rapidly:
-```
-Ideas:
-━━━━━━
-1. [Idea name]
-   Brief: [1-2 sentences]
-2. [Idea name]
-   Brief: [1-2 sentences]
-3. [Idea name]
-   Brief: [1-2 sentences]
-... continue to 5-10 ideas
-```
-**Techniques:**
-- **Inversion:** What's the opposite approach?
-- **Analogy:** How do others solve similar problems?
-- **Constraint removal:** What if [constraint] didn't exist?
-- **Combination:** Can we merge two partial solutions?
-- **Extreme:** What's the simplest? Most complex?
-## Phase 4: Explore Codebase
-Validate feasibility against existing code:
-```typescript
-// Find related patterns
-grep({ pattern: "[related concept]", include: "*.ts" });
-ast - grep({ pattern: "[code pattern]" });
-// Understand existing architecture
-lsp_lsp_document_symbols({ filePath: "<relevant file>" });
-```
-For each promising idea, note:
-- Existing code that supports it
-- Existing code that conflicts
-- New code required
-## Phase 5: Converge (Evaluate Ideas)
-Rate each idea on 4 dimensions:
-| Idea | Feasibility | Impact | Effort | Risk  | Score  |
-| ---- | ----------- | ------ | ------ | ----- | ------ |
-| 1    | H/M/L       | H/M/L  | S/M/L  | H/M/L | [1-10] |
-| 2    | H/M/L       | H/M/L  | S/M/L  | H/M/L | [1-10] |
-| ...  |             |        |        |       |        |
-**Scoring guide:**
-- **Feasibility:** Can we actually build this? (H=easy, L=very hard)
-- **Impact:** How much value does this deliver? (H=high value)
-- **Effort:** How much work? (S=small, L=large)
-- **Risk:** What could go wrong? (H=high risk)
-**Score formula:** (Feasibility × Impact) / (Effort × Risk)
-## Phase 6: Deep Dive Top 3
-For the top 3 scoring ideas:
-### Idea [N]: [Name]
-**Approach:**
-[2-3 sentence description]
-**How it works:**
-1. [Step 1]
-2. [Step 2]
-3. [Step 3]
-**Pros:**
-- [Advantage 1]
-- [Advantage 2]
-**Cons:**
-- [Disadvantage 1]
-- [Disadvantage 2]
-**Code sketch:**
-```typescript
-// Quick pseudocode or structure
-```
-**Open questions:**
-- [Uncertainty 1]
-- [Uncertainty 2]
-## Phase 7: Prototype (Optional)
-For the most promising idea, create a quick spike:
-```
-Prototype Goal:
-━━━━━━━━━━━━━━━
-Question to answer: [what are we validating?]
-Time limit: 15 minutes
-Success criteria: [how we know it works]
-```
-Create throwaway code to validate:
-```bash
-# Create spike branch
-git checkout -b spike/brainstorm-$ARGUMENTS
-```
-Build minimal proof of concept. Delete or keep based on learnings.
-## Phase 8: Capture Decision
-Save brainstorm results:
-**If bead exists:**
-Write to `.beads/artifacts/<bead-id>/brainstorm.md`:
-```markdown
-# Brainstorm: [Topic]
-**Date:** [date]
-**Duration:** [N] minutes
-**Bead:** <bead-id>
-## Goal
-[What we were exploring]
-## Ideas Considered
-| Idea | Feasibility | Impact | Effort | Risk | Score |
-| ---- | ----------- | ------ | ------ | ---- | ----- |
-| [1]  | H           | H      | M      | L    | 8     |
-| [2]  | M           | H      | S      | M    | 6     |
-| [3]  | L           | M      | L      | H    | 2     |
-## Recommendation
-**Chosen approach:** [Idea N]
-**Rationale:** [Why this approach]
-## Next Steps
-- [ ] [Action 1]
-- [ ] [Action 2]
-```
-**Create observation for reusable insights:**
-```typescript
-observation({
-  type: "discovery",
-  title: "Brainstorm: [topic]",
-  content: `
-## Key Insight
-[What we learned]
-## Approach Chosen
-[Brief description]
-## Why Others Rejected
-[Brief notes on alternatives]
-  `,
-  concepts: "[topic keywords]",
-  bead_id: "<bead-id>",
-});
-```
-## Phase 9: Create Follow-up Beads
-For promising ideas that need more work:
-```bash
-bd create "[Idea name]" -t task -p 2
-```
-## Output
-```markdown
-Brainstorm Complete: $ARGUMENTS
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Duration: [N] minutes
-Ideas generated: [N]
-Ideas evaluated: [N]
-Top 3:
-1. [Idea 1] - Score: [N]
-2. [Idea 2] - Score: [N]
-3. [Idea 3] - Score: [N]
-Recommendation: [Chosen approach]
-Confidence: [High/Medium/Low]
-Artifacts:
-- .beads/artifacts/<bead-id>/brainstorm.md (if bead)
-- Observation created ✓
-Follow-up beads: [N] created
-```
-**Use question tool for next steps:**
-```typescript
-question({
-  questions: [
-    {
-      header: "Next Step",
-      question: "What should we do next with $ARGUMENTS?",
-      options: [
-        {
-          label: "Research approach (Recommended)",
-          description: "Validate with /research",
-        },
-        { label: "Create implementation plan", description: "Plan with /plan" },
-        {
-          label: "Explore more",
-          description: "Continue brainstorming other aspects",
-        },
-        { label: "Done for now", description: "Save findings, revisit later" },
-      ],
-    },
-  ],
-});
-```
-Brainstorm Complete: $ARGUMENTS
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-Duration: [N] minutes
-Ideas generated: [N]
-Ideas evaluated: [N]
-Top 3:
-1. [Idea 1] - Score: [N]
-2. [Idea 2] - Score: [N]
-3. [Idea 3] - Score: [N]
-Recommendation: [Chosen approach]
-Confidence: [High/Medium/Low]
-Artifacts:
-- .beads/artifacts/<bead-id>/brainstorm.md (if bead)
-- Observation created ✓
-Follow-up beads: [N] created
-```
-**Next steps:**
-```
-If ready to proceed:
-/research <bead-id> # Validate approach
-/plan <bead-id> # Create implementation plan
-If need more exploration:
-/brainstorm <new-aspect> # Continue ideation
-```
-## Anti-Patterns
-- ❌ **Evaluating during divergence** - Generate first, judge later
-- ❌ **Falling in love with first idea** - Explore alternatives
-- ❌ **Infinite brainstorming** - Time box and decide
-- ❌ **No decision** - Brainstorming must produce a recommendation
-- ❌ **No capture** - Undocumented ideas are lost ideas
-```

package/dist/template/.opencode/command/cloudflare.md DELETED Viewed

@@ -1,70 +0,0 @@
----
-description: Load Cloudflare skill and get contextual guidance for your task
----
-Load the Cloudflare platform skill and help with any Cloudflare development task.
-## Workflow
-### Step 1: Check for --update-skill flag
-If $ARGUMENTS contains `--update-skill`:
-1. Determine install location by checking which exists:
-   - Local: `.opencode/skill/cloudflare/`
-   - Global: `~/.config/opencode/skill/cloudflare/`
-2. Run the appropriate install command:
-   ```bash
-   # For local installation
-   curl -fsSL https://raw.githubusercontent.com/dmmulroy/cloudflare-skill/main/install.sh | bash
-   # For global installation
-   curl -fsSL https://raw.githubusercontent.com/dmmulroy/cloudflare-skill/main/install.sh | bash -s -- --global
-   ```
-3. Output success message and stop (do not continue to other steps).
-### Step 2: Load cloudflare skill
-```
-skill({ name: 'cloudflare' })
-```
-### Step 3: Identify task type from user request
-Analyze $ARGUMENTS to determine:
-- **Product(s) needed** (Workers, D1, R2, Durable Objects, etc.)
-- **Task type** (new project setup, feature implementation, debugging, config)
-Use decision trees in SKILL.md to select correct product.
-### Step 4: Read relevant reference files
-Based on task type, read from `references/<product>/`:
-| Task | Files to Read |
-|------|---------------|
-| New project | `README.md` + `configuration.md` |
-| Implement feature | `README.md` + `api.md` + `patterns.md` |
-| Debug/troubleshoot | `gotchas.md` |
-| All-in-one (monolithic) | `SKILL.md` |
-### Step 5: Execute task
-Apply Cloudflare-specific patterns and APIs from references to complete the user's request.
-### Step 6: Summarize
-```
-=== Cloudflare Task Complete ===
-Product(s): <products used>
-Files referenced: <reference files consulted>
-<brief summary of what was done>
-```
-<user-request>
-$ARGUMENTS
-</user-request>

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

@@ -1,245 +0,0 @@
----
-description: Commit with verification and optional bead traceability
-argument-hint: "[bead-id] [--amend]"
-agent: build
----
-# Commit
-**Load skills:**
-```typescript
-skill({ name: "beads" }); // Session protocol
-skill({ name: "verification-before-completion" });
-```
-## Options
-- `--amend`: Amend the last commit (only if not pushed and you created it)
-## Phase 1: Check Git State
-!`git status --porcelain`
-!`git diff --stat`
-!`git diff --cached --stat`
-Report:
-```
-Git State:
-━━━━━━━━━━
-Staged:
-- [file1] (modified)
-- [file2] (new)
-Unstaged:
-- [file3] (modified)
-Untracked:
-- [file4]
-```
-If nothing staged: "No changes staged. Run `git add <files>` first."
-## Phase 2: Run Verification Gates
-Detect project type and run gates:
-!`ls package.json Cargo.toml pyproject.toml go.mod Makefile 2>/dev/null`
-| Project | Test Command    | Lint Command                         |
-| ------- | --------------- | ------------------------------------ |
-| Node.js | `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`                  |
-```
-Verification:
-━━━━━━━━━━━━━
-Tests: [✓/✗/skipped]
-Lint:  [✓/✗/skipped]
-Types: [✓/✗/skipped]
-```
-**If any gate fails:**
-```
-Cannot commit: [gate] failed.
-Fix errors or use `git commit --no-verify` (not recommended).
-```
-## Phase 3: Analyze Changes for Message
-!`git diff --cached --stat`
-!`git diff --cached`
-Determine:
-- **Type**: What kind of change is this?
-- **Scope**: Which module/component changed?
-- **Summary**: What does this change do?
-### Commit Type Guide
-| Type       | When to Use                             | Example                            |
-| ---------- | --------------------------------------- | ---------------------------------- |
-| `feat`     | New feature for user                    | `feat(auth): add OAuth login`      |
-| `fix`      | Bug fix                                 | `fix(api): handle null response`   |
-| `refactor` | Code change (no new feature or fix)     | `refactor(utils): simplify parser` |
-| `docs`     | Documentation only                      | `docs: update API reference`       |
-| `test`     | Adding or updating tests                | `test(auth): add login tests`      |
-| `chore`    | Maintenance, deps, tooling              | `chore: update dependencies`       |
-| `style`    | Formatting, whitespace (no code change) | `style: fix indentation`           |
-| `perf`     | Performance improvement                 | `perf(db): add query caching`      |
-| `ci`       | CI/CD changes                           | `ci: add deploy workflow`          |
-### Scope Detection
-Auto-detect scope from changed files:
-| Changed Files           | Suggested Scope |
-| ----------------------- | --------------- |
-| `src/auth/*`            | auth            |
-| `src/api/*`             | api             |
-| `src/components/*`      | ui              |
-| `tests/*`               | test            |
-| `docs/*`                | docs            |
-| Multiple unrelated dirs | (omit scope)    |
-## Phase 4: Generate Commit Message
-Propose message based on analysis:
-```
-Proposed Commit:
-━━━━━━━━━━━━━━━━
-<type>(<scope>): <summary>
-[body - what and why, not how]
-[footer - bead reference, breaking changes]
-```
-**Example with bead:**
-```
-feat(auth): add token refresh mechanism
-Implement automatic token refresh when access token expires.
-Tokens are stored in secure session storage.
-bd-a1b2c3: OAuth implementation
-```
-**Example with breaking change:**
-```
-feat(api)!: change response format
-BREAKING CHANGE: API responses now use camelCase instead of snake_case.
-Migration guide: https://...
-```
-Ask user:
-```
-Use this message? (yes/edit/cancel)
-```
-## Phase 5: Execute Commit
-```bash
-git commit -m "<message>"
-```
-**If pre-commit hook fails:**
-```
-Pre-commit hook failed:
-━━━━━━━━━━━━━━━━━━━━━━━
-[hook output]
-Options:
-1. Fix issues and retry: /commit [bead-id]
-2. Skip hook (not recommended): git commit --no-verify -m "..."
-```
-**Do NOT use --amend** unless:
-1. User explicitly requested `--amend`
-2. You created the HEAD commit in this session
-3. Commit has NOT been pushed to remote
-## Phase 6: Sync (for multi-agent)
-If bead ID was provided:
-```bash
-bd sync
-```
-## Output
-```
-Committed: [short-hash]
-━━━━━━━━━━━━━━━━━━━━━━━
-Message: <type>(<scope>): <summary>
-Files: [N] changed
-Bead: <bead-id> (if provided)
-Verification: All gates passed ✓
-```
-**Next steps:**
-```
-Continue working:
-  [make more changes]
-  /commit [bead-id]
-Ready to finish:
-  /finish <bead-id>
-Create PR:
-  /pr <bead-id>
-```
-## Amend Workflow (--amend)
-**Safety checks before amend:**
-!`git log -1 --format='%H %s'` # What we're amending
-!`git status` # Check if pushed
-```
-Amend Safety Check:
-━━━━━━━━━━━━━━━━━━━
-HEAD commit: [hash] [message]
-Pushed to remote: [yes/no]
-Created by you: [yes/no]
-```
-**If pushed or not created by you: STOP.**
-```
-Cannot amend: Commit already pushed or not created by you.
-Use a new commit instead:
-  git add <files>
-  /commit [bead-id]
-```
-**If safe to amend:**
-```bash
-git add <files>
-git commit --amend -m "<updated message>"
-```