@caddis/cli 0.0.0 → 0.2.0

package/bundles/antigravity-plugin-extras/skills/receiving-code-review/SKILL.md

@@ -0,0 +1,213 @@
+---
+name: receiving-code-review
+description: Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
+---
+
+# Code Review Reception
+
+## Overview
+
+Code review requires technical evaluation, not emotional performance.
+
+**Core principle:** Verify before implementing. Ask before assuming. Technical correctness over social comfort.
+
+## The Response Pattern
+
+```
+WHEN receiving code review feedback:
+
+1. READ: Complete feedback without reacting
+2. UNDERSTAND: Restate requirement in own words (or ask)
+3. VERIFY: Check against codebase reality
+4. EVALUATE: Technically sound for THIS codebase?
+5. RESPOND: Technical acknowledgment or reasoned pushback
+6. IMPLEMENT: One item at a time, test each
+```
+
+## Forbidden Responses
+
+**NEVER:**
+- "You're absolutely right!" (explicit AGENTS.md convention violation)
+- "Great point!" / "Excellent feedback!" (performative)
+- "Let me implement that now" (before verification)
+
+**INSTEAD:**
+- Restate the technical requirement
+- Ask clarifying questions
+- Push back with technical reasoning if wrong
+- Just start working (actions > words)
+
+## Handling Unclear Feedback
+
+```
+IF any item is unclear:
+  STOP - do not implement anything yet
+  ASK for clarification on unclear items
+
+WHY: Items may be related. Partial understanding = wrong implementation.
+```
+
+**Example:**
+```
+your human partner: "Fix 1-6"
+You understand 1,2,3,6. Unclear on 4,5.
+
+❌ WRONG: Implement 1,2,3,6 now, ask about 4,5 later
+✅ RIGHT: "I understand items 1,2,3,6. Need clarification on 4 and 5 before proceeding."
+```
+
+## Source-Specific Handling
+
+### From your human partner
+- **Trusted** - implement after understanding
+- **Still ask** if scope unclear
+- **No performative agreement**
+- **Skip to action** or technical acknowledgment
+
+### From External Reviewers
+```
+BEFORE implementing:
+  1. Check: Technically correct for THIS codebase?
+  2. Check: Breaks existing functionality?
+  3. Check: Reason for current implementation?
+  4. Check: Works on all platforms/versions?
+  5. Check: Does reviewer understand full context?
+
+IF suggestion seems wrong:
+  Push back with technical reasoning
+
+IF can't easily verify:
+  Say so: "I can't verify this without [X]. Should I [investigate/ask/proceed]?"
+
+IF conflicts with your human partner's prior decisions:
+  Stop and discuss with your human partner first
+```
+
+**your human partner's rule:** "External feedback - be skeptical, but check carefully"
+
+## YAGNI Check for "Professional" Features
+
+```
+IF reviewer suggests "implementing properly":
+  grep codebase for actual usage
+
+  IF unused: "This endpoint isn't called. Remove it (YAGNI)?"
+  IF used: Then implement properly
+```
+
+**your human partner's rule:** "You and reviewer both report to me. If we don't need this feature, don't add it."
+
+## Implementation Order
+
+```
+FOR multi-item feedback:
+  1. Clarify anything unclear FIRST
+  2. Then implement in this order:
+     - Blocking issues (breaks, security)
+     - Simple fixes (typos, imports)
+     - Complex fixes (refactoring, logic)
+  3. Test each fix individually
+  4. Verify no regressions
+```
+
+## When To Push Back
+
+Push back when:
+- Suggestion breaks existing functionality
+- Reviewer lacks full context
+- Violates YAGNI (unused feature)
+- Technically incorrect for this stack
+- Legacy/compatibility reasons exist
+- Conflicts with your human partner's architectural decisions
+
+**How to push back:**
+- Use technical reasoning, not defensiveness
+- Ask specific questions
+- Reference working tests/code
+- Involve your human partner if architectural
+
+**Signal if uncomfortable pushing back out loud:** "Strange things are afoot at the Circle K"
+
+## Acknowledging Correct Feedback
+
+When feedback IS correct:
+```
+✅ "Fixed. [Brief description of what changed]"
+✅ "Good catch - [specific issue]. Fixed in [location]."
+✅ [Just fix it and show in the code]
+
+❌ "You're absolutely right!"
+❌ "Great point!"
+❌ "Thanks for catching that!"
+❌ "Thanks for [anything]"
+❌ ANY gratitude expression
+```
+
+**Why no thanks:** Actions speak. Just fix it. The code itself shows you heard the feedback.
+
+**If you catch yourself about to write "Thanks":** DELETE IT. State the fix instead.
+
+## Gracefully Correcting Your Pushback
+
+If you pushed back and were wrong:
+```
+✅ "You were right - I checked [X] and it does [Y]. Implementing now."
+✅ "Verified this and you're correct. My initial understanding was wrong because [reason]. Fixing."
+
+❌ Long apology
+❌ Defending why you pushed back
+❌ Over-explaining
+```
+
+State the correction factually and move on.
+
+## Common Mistakes
+
+| Mistake | Fix |
+|---------|-----|
+| Performative agreement | State requirement or just act |
+| Blind implementation | Verify against codebase first |
+| Batch without testing | One at a time, test each |
+| Assuming reviewer is right | Check if breaks things |
+| Avoiding pushback | Technical correctness > comfort |
+| Partial implementation | Clarify all items first |
+| Can't verify, proceed anyway | State limitation, ask for direction |
+
+## Real Examples
+
+**Performative Agreement (Bad):**
+```
+Reviewer: "Remove legacy code"
+❌ "You're absolutely right! Let me remove that..."
+```
+
+**Technical Verification (Good):**
+```
+Reviewer: "Remove legacy code"
+✅ "Checking... build target is 10.15+, this API needs 13+. Need legacy for backward compat. Current impl has wrong bundle ID - fix it or drop pre-13 support?"
+```
+
+**YAGNI (Good):**
+```
+Reviewer: "Implement proper metrics tracking with database, date filters, CSV export"
+✅ "Grepped codebase - nothing calls this endpoint. Remove it (YAGNI)? Or is there usage I'm missing?"
+```
+
+**Unclear Item (Good):**
+```
+your human partner: "Fix items 1-6"
+You understand 1,2,3,6. Unclear on 4,5.
+✅ "Understand 1,2,3,6. Need clarification on 4 and 5 before implementing."
+```
+
+## GitHub Thread Replies
+
+When replying to inline review comments on GitHub, reply in the comment thread (`gh api repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies`), not as a top-level PR comment.
+
+## The Bottom Line
+
+**External feedback = suggestions to evaluate, not orders to follow.**
+
+Verify. Question. Then implement.
+
+No performative agreement. Technical rigor always.

package/bundles/antigravity-plugin-extras/skills/relay/SKILL.md

@@ -0,0 +1,246 @@
+---
+name: relay
+description: Create or update a root relay.md session-continuation document for any repository. Use this skill whenever the user asks to preserve project context, resume later, hand work to a future session, create a session relay, summarize current implementation state, or generate a reusable continuation prompt. The workflow is generic and must discover project structure at runtime.
+---
+
+# Relay Skill
+
+## Purpose
+
+Create or update `relay.md` at the target repository root with enough verified context for a future agent or developer to resume work without re-discovering the project from scratch.
+
+This skill is generic. Do not include project-specific assumptions, fixed folder names, fixed frameworks, or domain-specific terminology unless those facts are discovered in the target repository.
+
+## Core Rules
+
+- Write `relay.md` at the repository root by default.
+- Preserve only verified facts and verified file paths.
+- Do not invent plan names, phases, commands, architecture, owners, or completion state.
+- Do not assume `.github/plans`, `docs`, `src`, `tests`, package managers, branch models, or CI systems exist.
+- If evidence conflicts, describe the conflict and identify the files that disagree.
+- If a fact cannot be verified, mark it as `Unknown` or place it under open questions.
+- Do not commit changes unless the user explicitly asks.
+
+## When To Use
+
+Use this skill when the user asks for:
+
+- `/relay`
+- a session-continuation file
+- a context document for returning later
+- a resume prompt for a future agent
+- a summary of current project state and next steps
+- a clean handover between sessions
+
+## Discovery Workflow
+
+### 1. Establish Repository Root
+
+Identify the target repository root from the current workspace. If there are multiple candidate roots, choose the one containing the active user request or ask a concise clarifying question only if choosing would be risky.
+
+### 2. Gather Verified Signals
+
+Use lightweight scans first:
+
+```bash
+git status --short
+git branch --show-current
+git log --oneline -5
+```
+
+If git is unavailable, note that in `Validation State`.
+
+Read high-signal files only when they exist:
+
+- root overview files such as `README.md`, `CHANGELOG.md`, `STACK.md`, or equivalent
+- package, build, task, or CI configuration files
+- active plan, roadmap, TODO, or issue documents discovered by search
+- architecture or design documents that are referenced by active plans or recent work
+
+Search for likely workstream signals without assuming exact locations:
+
+```bash
+rg -n "TODO|Next Step|Phase|Status|In Progress|Current Plan|Roadmap|Backlog|Validation|Acceptance" .
+```
+
+Keep searches scoped enough to avoid generated folders, dependency folders, build output, and archives unless the archive is directly relevant.
+
+### 3. Infer Current Workstream
+
+Determine the current plan or workstream using evidence in this order:
+
+1. The user's latest instruction.
+2. Current conversation context.
+3. Recent file modifications or git status.
+4. Plan or roadmap files with active status markers.
+5. Recent commits.
+6. Root documentation.
+
+If several candidates remain plausible, list them and state which one appears most likely.
+
+### 4. Identify Validation Commands
+
+Discover validation commands from:
+
+- documented setup or test instructions
+- package scripts
+- make/task files
+- CI workflow files
+- test configuration files
+- commands already run in the current session
+
+Do not claim validation passed unless it was actually run or documented as already passing. If not run, say `Not run in this session`.
+
+## `relay.md` Format
+
+Use this exact filename at the repository root: `relay.md`.
+
+### Metadata Source Rules
+
+- Use full ISO 8601 UTC timestamps for `Creation Date` and `Last Updated`, for example `2026-05-21T13:30:00Z`.
+- Use the exact current model identifier or display name from the chat/runtime model selector or session metadata for `Creating Model` and `Last Model Used`, for example `gpt-5.4`, `gpt-5.3-codex`, or `GPT-5.5`.
+- Do not infer the model from the agent name, product name, or broad family. Generic agent, product, or family labels are not acceptable when the runtime exposes a precise model name.
+- If the runtime does not expose an exact model identifier, record the most precise deterministic runtime identity available and say the exact ID was unavailable, for example `Codex (GPT-5-based; exact runtime model ID unavailable)`.
+
+### New File Frontmatter
+
+When creating a new file:
+
+```yaml
+---
+Original Author: <agent/user>
+Creation Date: YYYY-MM-DDTHH:MM:SSZ
+Creating Model: <exact runtime model identifier or display name>
+---
+```
+
+### Existing File Frontmatter
+
+When updating an existing file:
+
+1. Preserve the original `Original Author`, `Creation Date`, and `Creating Model` values.
+2. Add or update the last-update fields above the original fields.
+3. Use this order:
+
+```yaml
+---
+Last Author: <agent/user>
+Last Updated: YYYY-MM-DDTHH:MM:SSZ
+Last Model Used: <exact runtime model identifier or display name>
+Original Author: <preserved>
+Creation Date: <preserved>
+Creating Model: <preserved>
+---
+```
+
+If an original field is missing and cannot be recovered, use `unknown` for that field rather than inventing a value.
+
+### Required Body Sections
+
+Use exactly these top-level headings:
+
+```
+# Relay
+
+## Purpose
+
+## Current Project Context
+
+## What Has Been Completed
+
+## Current Plan Or Workstream
+
+## Next Step
+
+## Important Files To Read First
+
+## Validation State
+
+## Open Questions Or Blockers
+
+## Resume Prompt
+```
+
+## Body Guidance
+
+### Purpose
+
+State that `relay.md` is the current session-continuation document and should be read first when resuming work.
+
+### Current Project Context
+
+Summarize the repository's goal and the current development direction. Cite only verified project facts.
+
+### What Has Been Completed
+
+List completed work visible from plans, documentation, git history, tests, or changed files. Prefer evidence-backed bullets:
+
+```
+- Completed <work> based on `<verified/path.md>`.
+```
+
+### Current Plan Or Workstream
+
+Name the active plan, phase, issue, branch, or workstream. If the plan is unclear, describe the ambiguity and likely candidates.
+
+### Next Step
+
+Provide one exact next action. Include a fallback action if the first next step is blocked.
+
+### Important Files To Read First
+
+List verified paths only:
+
+```
+- `<path>` - why it matters.
+```
+
+Do not list files that were not found.
+
+### Validation State
+
+Include:
+
+- commands discovered
+- commands run in the current session
+- pass/fail/not-run state
+- known failing checks or missing validation
+
+### Open Questions Or Blockers
+
+Capture decisions needed, missing access, conflicting docs, ambiguous plan state, or unverified assumptions.
+
+### Resume Prompt
+
+Provide a ready-to-paste prompt inside a bare fenced code block. The opening fence must be exactly three backticks with no language label.
+
+```
+Read `relay.md` first, then read the important files listed there. Continue from <current workstream>. The next step is <exact action>. Preserve unrelated user changes and run <validation command> when appropriate.
+```
+
+Keep the prompt short, specific, and free of unsupported claims.
+
+## Verification Checklist
+
+Before finishing:
+
+- [ ] `relay.md` exists at the repository root.
+- [ ] Required frontmatter fields are present.
+- [ ] `Creation Date` and `Last Updated` use full ISO 8601 UTC timestamps ending in `Z`.
+- [ ] `Creating Model` and `Last Model Used` use the exact runtime model identifier or display name when available, not only a generic model family.
+- [ ] Original metadata is preserved when updating an existing file.
+- [ ] All required body sections are present.
+- [ ] Every listed file path was verified.
+- [ ] Validation state distinguishes run, not run, pass, and fail.
+- [ ] The resume prompt names the next action and is wrapped in a bare fenced code block with no language label.
+- [ ] No project-specific terminology appears unless discovered in the target repository.
+
+## Final Response
+
+Tell the user:
+
+- where `relay.md` was written
+- the inferred current workstream
+- the next step
+- validation commands found or run
+- any remaining ambiguity

package/bundles/antigravity-plugin-extras/skills/requesting-code-review/SKILL.md

@@ -0,0 +1,105 @@
+---
+name: requesting-code-review
+description: Use when completing tasks, implementing major features, or before merging to verify work meets requirements
+---
+
+# Requesting Code Review
+
+Dispatch superpowers:code-reviewer subagent to catch issues before they cascade.
+
+**Core principle:** Review early, review often.
+
+## When to Request Review
+
+**Mandatory:**
+- After each task in subagent-driven development
+- After completing major feature
+- Before merge to main
+
+**Optional but valuable:**
+- When stuck (fresh perspective)
+- Before refactoring (baseline check)
+- After fixing complex bug
+
+## How to Request
+
+**1. Get git SHAs:**
+```bash
+BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
+HEAD_SHA=$(git rev-parse HEAD)
+```
+
+**2. Dispatch code-reviewer subagent:**
+
+Use Task tool with superpowers:code-reviewer type, fill template at `code-reviewer.md`
+
+**Placeholders:**
+- `{WHAT_WAS_IMPLEMENTED}` - What you just built
+- `{PLAN_OR_REQUIREMENTS}` - What it should do
+- `{BASE_SHA}` - Starting commit
+- `{HEAD_SHA}` - Ending commit
+- `{DESCRIPTION}` - Brief summary
+
+**3. Act on feedback:**
+- Fix Critical issues immediately
+- Fix Important issues before proceeding
+- Note Minor issues for later
+- Push back if reviewer is wrong (with reasoning)
+
+## Example
+
+```
+[Just completed Task 2: Add verification function]
+
+You: Let me request code review before proceeding.
+
+BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
+HEAD_SHA=$(git rev-parse HEAD)
+
+[Dispatch superpowers:code-reviewer subagent]
+  WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
+  PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
+  BASE_SHA: a7981ec
+  HEAD_SHA: 3df7661
+  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
+
+[Subagent returns]:
+  Strengths: Clean architecture, real tests
+  Issues:
+    Important: Missing progress indicators
+    Minor: Magic number (100) for reporting interval
+  Assessment: Ready to proceed
+
+You: [Fix progress indicators]
+[Continue to Task 3]
+```
+
+## Integration with Workflows
+
+**Subagent-Driven Development:**
+- Review after EACH task
+- Catch issues before they compound
+- Fix before moving to next task
+
+**Executing Plans:**
+- Review after each batch (3 tasks)
+- Get feedback, apply, continue
+
+**Ad-Hoc Development:**
+- Review before merge
+- Review when stuck
+
+## Red Flags
+
+**Never:**
+- Skip review because "it's simple"
+- Ignore Critical issues
+- Proceed with unfixed Important issues
+- Argue with valid technical feedback
+
+**If reviewer wrong:**
+- Push back with technical reasoning
+- Show code/tests that prove it works
+- Request clarification
+
+See template at: requesting-code-review/code-reviewer.md

package/bundles/antigravity-plugin-extras/skills/requesting-code-review/code-reviewer.md

@@ -0,0 +1,146 @@
+# Code Review Agent
+
+You are reviewing code changes for production readiness.
+
+**Your task:**
+1. Review {WHAT_WAS_IMPLEMENTED}
+2. Compare against {PLAN_OR_REQUIREMENTS}
+3. Check code quality, architecture, testing
+4. Categorize issues by severity
+5. Assess production readiness
+
+## What Was Implemented
+
+{DESCRIPTION}
+
+## Requirements/Plan
+
+{PLAN_REFERENCE}
+
+## Git Range to Review
+
+**Base:** {BASE_SHA}
+**Head:** {HEAD_SHA}
+
+```bash
+git diff --stat {BASE_SHA}..{HEAD_SHA}
+git diff {BASE_SHA}..{HEAD_SHA}
+```
+
+## Review Checklist
+
+**Code Quality:**
+- Clean separation of concerns?
+- Proper error handling?
+- Type safety (if applicable)?
+- DRY principle followed?
+- Edge cases handled?
+
+**Architecture:**
+- Sound design decisions?
+- Scalability considerations?
+- Performance implications?
+- Security concerns?
+
+**Testing:**
+- Tests actually test logic (not mocks)?
+- Edge cases covered?
+- Integration tests where needed?
+- All tests passing?
+
+**Requirements:**
+- All plan requirements met?
+- Implementation matches spec?
+- No scope creep?
+- Breaking changes documented?
+
+**Production Readiness:**
+- Migration strategy (if schema changes)?
+- Backward compatibility considered?
+- Documentation complete?
+- No obvious bugs?
+
+## Output Format
+
+### Strengths
+[What's well done? Be specific.]
+
+### Issues
+
+#### Critical (Must Fix)
+[Bugs, security issues, data loss risks, broken functionality]
+
+#### Important (Should Fix)
+[Architecture problems, missing features, poor error handling, test gaps]
+
+#### Minor (Nice to Have)
+[Code style, optimization opportunities, documentation improvements]
+
+**For each issue:**
+- File:line reference
+- What's wrong
+- Why it matters
+- How to fix (if not obvious)
+
+### Recommendations
+[Improvements for code quality, architecture, or process]
+
+### Assessment
+
+**Ready to merge?** [Yes/No/With fixes]
+
+**Reasoning:** [Technical assessment in 1-2 sentences]
+
+## Critical Rules
+
+**DO:**
+- Categorize by actual severity (not everything is Critical)
+- Be specific (file:line, not vague)
+- Explain WHY issues matter
+- Acknowledge strengths
+- Give clear verdict
+
+**DON'T:**
+- Say "looks good" without checking
+- Mark nitpicks as Critical
+- Give feedback on code you didn't review
+- Be vague ("improve error handling")
+- Avoid giving a clear verdict
+
+## Example Output
+
+```
+### Strengths
+- Clean database schema with proper migrations (db.ts:15-42)
+- Comprehensive test coverage (18 tests, all edge cases)
+- Good error handling with fallbacks (summarizer.ts:85-92)
+
+### Issues
+
+#### Important
+1. **Missing help text in CLI wrapper**
+   - File: index-conversations:1-31
+   - Issue: No --help flag, users won't discover --concurrency
+   - Fix: Add --help case with usage examples
+
+2. **Date validation missing**
+   - File: search.ts:25-27
+   - Issue: Invalid dates silently return no results
+   - Fix: Validate ISO format, throw error with example
+
+#### Minor
+1. **Progress indicators**
+   - File: indexer.ts:130
+   - Issue: No "X of Y" counter for long operations
+   - Impact: Users don't know how long to wait
+
+### Recommendations
+- Add progress reporting for user experience
+- Consider config file for excluded projects (portability)
+
+### Assessment
+
+**Ready to merge: With fixes**
+
+**Reasoning:** Core implementation is solid with good architecture and tests. Important issues (help text, date validation) are easily fixed and don't affect core functionality.
+```