@hienlh/ppm 0.9.81 → 0.9.83

package/.opencode/skills/fix/references/diagnosis-protocol.md

@@ -1,133 +0,0 @@
-# Diagnosis Protocol
-
-Structured root cause analysis methodology. Replaces ad-hoc guessing with evidence-based investigation.
-
-## Core Principle
-
-**NEVER guess root causes.** Form hypotheses through structured reasoning and test them against evidence.
-
-## Pre-Diagnosis: Capture State (MANDATORY)
-
-Before any investigation, capture the current broken state as baseline:
-
-```
-1. Record exact error messages (copy-paste, not paraphrase)
-2. Record failing test output (full command + output)
-3. Record relevant stack traces
-4. Record relevant log snippets with timestamps
-5. Record git status / recent changes: git log --oneline -10
-```
-
-This baseline is required for Step 5 (Verify) — you MUST compare before/after.
-
-## Diagnosis Chain (Follow in Order)
-
-### Phase 1: Observe — What is actually happening?
-
-Read, don't assume. Use `ck:debug` (systematic-debugging Phase 1).
-
-- What is the exact error message?
-- Where does it occur? (file, line, function)
-- When did it start? (check `git log`, `git bisect`)
-- Can it be reproduced consistently?
-- What is the expected vs actual behavior?
-
-### Phase 2: Hypothesize — Why might this happen?
-
-Activate `ck:sequential-thinking` skill. Form hypotheses through structured reasoning.
-
-**Structured hypothesis formation:**
-```
-For each hypothesis:
-  1. State the hypothesis clearly
-  2. What evidence would CONFIRM it?
-  3. What evidence would REFUTE it?
-  4. How to test it quickly?
-```
-
-**Common hypothesis categories:**
-- Recent code change introduced regression (`git log`, `git diff`)
-- Data/state mismatch (wrong input, stale cache, race condition)
-- Environment difference (deps version, config, platform)
-- Missing validation (null check, type guard, boundary)
-- Incorrect assumption (API contract, data shape, ordering)
-
-### Phase 3: Test — Verify hypotheses against evidence
-
-Spawn parallel `Explore` subagents to test each hypothesis simultaneously:
-
-```
-// Launch in SINGLE message — max 3 parallel agents
-Task("Explore", "Test hypothesis A: [specific search/check]", "Verify H-A")
-Task("Explore", "Test hypothesis B: [specific search/check]", "Verify H-B")
-Task("Explore", "Test hypothesis C: [specific search/check]", "Verify H-C")
-```
-
-**For each hypothesis result:**
-- CONFIRMED: Evidence supports this as root cause → proceed to root cause tracing
-- REFUTED: Evidence contradicts → discard, note why
-- INCONCLUSIVE: Need more data → refine hypothesis or gather more evidence
-
-### Phase 4: Trace — Follow the root cause chain
-
-Use `ck:debug` (root-cause-tracing technique). Trace backward:
-
-```
-Symptom (where error appears)
-  ↑ Immediate cause (what triggered the error)
-    ↑ Contributing factor (what set up the bad state)
-      ↑ ROOT CAUSE (the original trigger that must be fixed)
-```
-
-**Rule:** NEVER fix where the error appears. Trace back to the source.
-
-### Phase 5: Escalate — When hypotheses fail
-
-If 2+ hypotheses are REFUTED:
-1. Auto-activate `ck:problem-solving` skill
-2. Apply Inversion Exercise: "What would CAUSE this bug intentionally?"
-3. Apply Scale Game: "Does this fail with 1 item? 100? 10000?"
-4. Consider environmental factors (timing, concurrency, platform)
-
-If 3+ fix attempts fail after diagnosis:
-1. STOP immediately
-2. Question the architecture — is the design fundamentally flawed?
-3. Discuss with user before attempting more
-
-## Diagnosis Report Format
-
-```markdown
-## Diagnosis Report
-
-**Issue:** [one-line description]
-**Pre-fix state captured:** Yes/No
-
-### Root Cause
-[Clear explanation of the root cause, traced back to origin]
-
-### Evidence Chain
-1. [Observation] → led to hypothesis [X]
-2. [Test result] → confirmed/refuted [X]
-3. [Trace] → root cause at [file:line]
-
-### Affected Scope
-- Files: [list]
-- Functions: [list]
-- Dependencies: [list]
-
-### Recommended Fix
-[What to change and why — addressing root cause, not symptoms]
-
-### Prevention Needed
-[What guards/tests to add to prevent recurrence]
-```
-
-## Quick Mode Diagnosis
-
-For trivial issues (type errors, lint, syntax), abbreviated diagnosis:
-
-1. Read error message
-2. Locate affected file(s) via scout results
-3. Identify root cause (usually obvious for simple issues)
-4. Skip parallel hypothesis testing
-5. Still capture pre-fix state for verification

package/.opencode/skills/fix/references/mode-selection.md

@@ -1,46 +0,0 @@
-# Mode Selection
-
-Use `AskUserQuestion` at start of fixing workflow.
-
-## AskUserQuestion Format
-
-```json
-{
-  "questions": [{
-    "question": "How should I handle the fix workflow?",
-    "header": "Fix Mode",
-    "options": [
-      {
-        "label": "Autonomous (Recommended)",
-        "description": "Auto-approve if quality high, only ask when stuck"
-      },
-      {
-        "label": "Human-in-the-loop",
-        "description": "Pause for approval at each major step"
-      },
-      {
-        "label": "Quick fix",
-        "description": "Fast debug-fix-review cycle for simple issues"
-      }
-    ],
-    "multiSelect": false
-  }]
-}
-```
-
-## Mode Recommendations
-
-| Issue Type | Recommended Mode |
-|------------|------------------|
-| Type errors, lint errors | Quick |
-| Single file bugs | Quick or Autonomous |
-| Multi-file, unclear root cause | Autonomous |
-| Production/critical code | Human-in-the-loop |
-| System-wide/architecture | Human-in-the-loop |
-| Security vulnerabilities | Human-in-the-loop |
-
-## Skip Mode Selection When
-
-- Issue is clearly trivial (type error keyword detected) → default Quick
-- User explicitly specified mode in prompt
-- Previous context already established mode

package/.opencode/skills/fix/references/parallel-exploration.md

@@ -1,77 +0,0 @@
-# Parallel Exploration
-
-Patterns for launching multiple subagents in parallel to scout codebase and verify implementation.
-
-## Parallel Exploration (Scouting)
-
-Launch multiple `Explore` subagents simultaneously when needing to find:
-- Related files across different areas
-- Similar implementations/patterns
-- Dependencies and usage
-
-**Pattern:**
-```
-Task(subagent_type="Explore", prompt="Find [X] in [area1]", description="Scout area1")
-Task(subagent_type="Explore", prompt="Find [Y] in [area2]", description="Scout area2")
-Task(subagent_type="Explore", prompt="Find [Z] in [area3]", description="Scout area3")
-```
-
-**Example - Multi-area scouting:**
-```
-// Launch in SINGLE message with multiple Task calls:
-Task("Explore", "Find auth-related files in src/", "Scout auth")
-Task("Explore", "Find API routes handling users", "Scout API")
-Task("Explore", "Find test files for auth module", "Scout tests")
-```
-
-## Parallel Verification (Bash)
-
-Launch multiple `Bash` subagents to verify implementation from different angles.
-
-**Pattern:**
-```
-Task(subagent_type="Bash", prompt="Run [command1]", description="Verify X")
-Task(subagent_type="Bash", prompt="Run [command2]", description="Verify Y")
-```
-
-**Example - Multi-verification:**
-```
-// Launch in SINGLE message:
-Task("Bash", "Run typecheck: bun run typecheck", "Verify types")
-Task("Bash", "Run lint: bun run lint", "Verify lint")
-Task("Bash", "Run build: bun run build", "Verify build")
-```
-
-## When to Use Parallel
-
-| Scenario | Parallel Strategy |
-|----------|-------------------|
-| Root cause unclear, multiple suspects | 2-3 Explore agents on different areas |
-| Multi-module fix | Explore each module in parallel |
-| After implementation | Bash agents for typecheck + lint + build |
-| Before commit | Bash agents for test + build + lint |
-
-## Combining Explore + Bash
-
-**Step 1:** Parallel Explore to scout
-**Step 2:** Sequential implementation
-**Step 3:** Parallel Bash to verify
-
-```
-// Scout phase - parallel
-Task("Explore", "Find payment handlers", "Scout payments")
-Task("Explore", "Find order processors", "Scout orders")
-
-// Wait for results, implement fix
-
-// Verify phase - parallel
-Task("Bash", "Run tests: bun test", "Run tests")
-Task("Bash", "Run typecheck", "Check types")
-Task("Bash", "Run build", "Verify build")
-```
-
-## Resource Limits
-
-- Max 3 parallel agents recommended (system resources)
-- Each subagent has 200K token context limit
-- Keep prompts concise to avoid context bloat

package/.opencode/skills/fix/references/prevention-gate.md

@@ -1,87 +0,0 @@
-# Prevention Gate
-
-After fixing a bug, prevent the same class of issues from recurring. This step is MANDATORY.
-
-## Core Principle
-
-A fix without prevention is incomplete. The same bug pattern WILL recur if you only patch the symptom.
-
-## Prevention Requirements (Check All That Apply)
-
-### 1. Regression Test (ALWAYS required)
-
-Every fix MUST have a test that:
-- **Fails** without the fix applied (proves the test catches the bug)
-- **Passes** with the fix applied (proves the fix works)
-
-```
-If no test framework exists:
-  → Add inline verification or assertion at minimum
-  → Note in report: "No test framework — added runtime assertion"
-```
-
-### 2. Defense-in-Depth Validation (When applicable)
-
-Apply layered validation from `ck:debug` defense-in-depth technique:
-
-| Layer | Apply When | Example |
-|-------|-----------|---------|
-| **Entry point validation** | Fix involves user/external input | Reject invalid input at API boundary |
-| **Business logic validation** | Fix involves data processing | Assert data makes sense for operation |
-| **Environment guards** | Fix involves env-sensitive operations | Prevent dangerous ops in wrong context |
-| **Debug instrumentation** | Fix was hard to diagnose | Add logging/context capture for forensics |
-
-**Rule:** Not every fix needs all 4 layers. Apply what's relevant. But ALWAYS consider each.
-
-### 3. Type Safety (When applicable)
-
-| Scenario | Prevention |
-|----------|-----------|
-| Null/undefined caused the bug | Add strict null checks, use `??` or `?.` |
-| Wrong type passed | Add type guard or runtime validation |
-| Missing property | Add required field to interface/type |
-| Implicit any | Add explicit types |
-
-### 4. Error Handling (When applicable)
-
-| Scenario | Prevention |
-|----------|-----------|
-| Unhandled promise rejection | Add `.catch()` or try/catch |
-| Missing error boundary | Add error boundary component |
-| Silent failure | Add explicit error logging |
-| No fallback for external dependency | Add timeout + fallback |
-
-## Verification Checklist (Before Completing Step 5)
-
-```
-□ Pre-fix state captured? (error messages, test output)
-□ Fix applied to ROOT CAUSE (not symptom)?
-□ Fresh verification run? (exact same commands as pre-fix)
-□ Before/after comparison documented?
-□ Regression test added? (fails without fix, passes with fix)
-□ Defense-in-depth layers considered? (applied where relevant)
-□ No new warnings/errors introduced?
-□ Parallel verification passed? (typecheck + lint + build + test)
-```
-
-## Output Format
-
-```
-Prevention measures applied:
-- Regression test: [test file:line] — covers [specific scenario]
-- Guard added: [file:line] — [description of guard]
-- Type safety: [file:line] — [what was strengthened]
-- Error handling: [file:line] — [what was added]
-
-Before/After comparison:
-- Before: [exact error/failure]
-- After: [exact success output]
-```
-
-## Quick Mode Prevention
-
-For trivial issues (type errors, lint), abbreviated prevention:
-- Regression test: optional (type system IS the test)
-- Parallel verification: typecheck + lint only
-- Defense-in-depth: skip (not applicable for type fixes)
-- Still require before/after comparison of typecheck output

package/.opencode/skills/fix/references/review-cycle.md

@@ -1,77 +0,0 @@
-# Review Cycle
-
-Mode-aware review handling for code-reviewer results.
-
-## Autonomous Mode
-
-```
-cycle = 0
-LOOP:
-  1. Run code-reviewer → score, critical_count, warnings, suggestions
-
-  2. IF score >= 9.5 AND critical_count == 0:
-     → Output: "✓ Review [score]/10 - Auto-approved"
-     → PROCEED to next step
-
-  3. ELSE IF critical_count > 0 AND cycle < 3:
-     → Output: "⚙ Auto-fixing [N] critical issues (cycle [cycle+1]/3)"
-     → Fix critical issues
-     → Re-run tests
-     → cycle++, GOTO LOOP
-
-  4. ELSE IF cycle >= 3:
-     → ESCALATE to user via AskUserQuestion
-     → Display findings
-     → Options: "Fix manually" / "Approve anyway" / "Abort"
-
-  5. ELSE (score < 9.5, no critical):
-     → Output: "✓ Review [score]/10 - Approved with [N] warnings"
-     → PROCEED (warnings logged, not blocking)
-```
-
-## Human-in-the-Loop Mode
-
-```
-ALWAYS:
-  1. Run code-reviewer → score, critical_count, warnings, suggestions
-
-  2. Display findings:
-     ┌─────────────────────────────────────┐
-     │ Review: [score]/10                  │
-     ├─────────────────────────────────────┤
-     │ Critical ([N]): [list]              │
-     │ Warnings ([N]): [list]              │
-     │ Suggestions ([N]): [list]           │
-     └─────────────────────────────────────┘
-
-  3. Use AskUserQuestion:
-     IF critical_count > 0:
-       - "Fix critical issues"
-       - "Fix all issues"
-       - "Approve anyway"
-       - "Abort"
-     ELSE:
-       - "Approve"
-       - "Fix warnings/suggestions"
-       - "Abort"
-
-  4. Handle response:
-     - Fix → implement, re-test, re-review (max 3 cycles)
-     - Approve → proceed
-     - Abort → stop workflow
-```
-
-## Quick Mode Review
-
-Uses same logic as Autonomous but:
-- Lower threshold: score >= 8.5 acceptable
-- Only 1 auto-fix cycle before escalate
-- Focus on: correctness, security, no regressions
-
-## Critical Issues (Always Block)
-
-- Security vulnerabilities (XSS, SQL injection, OWASP)
-- Performance bottlenecks (O(n²) when O(n) possible)
-- Architectural violations
-- Data loss risks
-- Breaking changes without migration

package/.opencode/skills/fix/references/skill-activation-matrix.md

@@ -1,65 +0,0 @@
-# Skill Activation Matrix
-
-When to activate each skill during fixing workflows.
-
-## Always Activate
-
-| Skill | Reason |
-|-------|--------|
-| `debugging` | Core to all fix workflows - find root cause first |
-
-## Conditional Activation
-
-| Skill | Activate When |
-|-------|---------------|
-| `problem-solving` | Stuck on approach, multiple failed attempts |
-| `sequential-thinking` | Complex logic chain, multi-step reasoning needed |
-| `brainstorming` | Multiple valid approaches, architecture decision |
-| `context-engineering` | Fixing AI/LLM/agent code, context window issues |
-| `ai-multimodal` | UI issues, screenshots provided, visual bugs |
-
-## Subagent Usage
-
-| Subagent | Activate When |
-|----------|---------------|
-| `debugger` | Root cause unclear, need deep investigation |
-| `Explore` (parallel) | Scout multiple areas simultaneously |
-| `Bash` (parallel) | Verify implementation (typecheck, lint, build) |
-| `researcher` | External docs needed, latest best practices |
-| `planner` | Complex fix needs breakdown, multiple phases |
-| `tester` | After implementation, verify fix works |
-| `code-reviewer` | After fix, verify quality and security |
-| `git-manager` | After approval, commit changes |
-| `docs-manager` | API/behavior changes need doc updates |
-| `project-manager` | Major fix impacts roadmap/plan status |
-
-## Parallel Patterns
-
-See `references/parallel-exploration.md` for detailed patterns.
-
-| When | Parallel Strategy |
-|------|-------------------|
-| Root cause unclear | 2-3 `Explore` agents on different areas |
-| Multi-module fix | `Explore` each module in parallel |
-| After implementation | `Bash` agents: typecheck + lint + build |
-| Before commit | `Bash` agents: test + build + lint |
-
-## Workflow → Skills Map
-
-| Workflow | Skills Activated |
-|----------|------------------|
-| Quick | `debugging`, `code-reviewer`, parallel `Bash` verification |
-| Standard | Above + `problem-solving`, `sequential-thinking`, `tester`, parallel `Explore` |
-| Deep | All above + `brainstorming`, `context-engineering`, `researcher`, `planner` |
-| Parallel | Per-issue workflow + coordination via parallel agents |
-
-## Detection Triggers
-
-| Keyword/Pattern | Skill to Consider |
-|-----------------|-------------------|
-| "AI", "LLM", "agent", "context" | `context-engineering` |
-| "stuck", "tried everything" | `problem-solving` |
-| "complex", "multi-step" | `sequential-thinking` |
-| "which approach", "options" | `brainstorming` |
-| "latest docs", "best practice" | `researcher` subagent |
-| Screenshot attached | `ai-multimodal` |

package/.opencode/skills/fix/references/task-orchestration.md

@@ -1,110 +0,0 @@
-# Task Orchestration
-
-Native Claude Task tools for tracking and coordinating fix workflows.
-
-**Skill:** Activate `ck:project-management` for advanced task orchestration — provides hydration (plan checkboxes → Tasks), sync-back (Tasks → plan checkboxes), cross-session resume, and progress tracking patterns.
-
-**Tool Availability:** `TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList` are **CLI-only** — disabled in VSCode extension (`isTTY` check). If these tools error, use `TodoWrite` for progress tracking instead. Fix workflow remains fully functional — Tasks add visibility and coordination, not core functionality.
-
-## When to Use Tasks
-
-| Complexity | Use Tasks? | Reason |
-|-----------|-----------|--------|
-| Simple/Quick | No | < 3 steps, overhead exceeds benefit |
-| Moderate (Standard) | Yes | 6 steps, multi-subagent coordination |
-| Complex (Deep) | Yes | 9 steps, dependency chains, parallel agents |
-| Parallel | Yes | Multiple independent issue trees |
-
-## Task Tools
-
-- `TaskCreate(subject, description, activeForm, metadata)` - Create task
-- `TaskUpdate(taskId, status, addBlockedBy, addBlocks)` - Update status/deps
-- `TaskGet(taskId)` - Get full task details
-- `TaskList()` - List all tasks with status
-
-**Lifecycle:** `pending` → `in_progress` → `completed`
-
-## Standard Workflow Tasks (6 phases)
-
-Create all tasks upfront, then work through them:
-
-```
-T1 = TaskCreate(subject="Scout codebase",       activeForm="Scouting codebase",     metadata={step: 1, phase: "investigate"})
-T2 = TaskCreate(subject="Diagnose root cause",   activeForm="Diagnosing root cause", metadata={step: 2, phase: "investigate"})
-T3 = TaskCreate(subject="Implement fix",         activeForm="Implementing fix",      metadata={step: 3, phase: "implement"},  addBlockedBy=[T1, T2])
-T4 = TaskCreate(subject="Verify + prevent",      activeForm="Verifying fix",         metadata={step: 4, phase: "verify"},     addBlockedBy=[T3])
-T5 = TaskCreate(subject="Code review",           activeForm="Reviewing code",        metadata={step: 5, phase: "verify"},     addBlockedBy=[T4])
-T6 = TaskCreate(subject="Finalize",              activeForm="Finalizing",            metadata={step: 6, phase: "finalize"},   addBlockedBy=[T5])
-```
-
-Update as work progresses:
-```
-TaskUpdate(taskId=T1, status="in_progress")
-// ... scout codebase ...
-TaskUpdate(taskId=T1, status="completed")
-// T3 auto-unblocks when T1 + T2 complete
-```
-
-## Deep Workflow Tasks (9 phases)
-
-Steps 1+2+3 run in parallel (scout + diagnose + research).
-
-```
-T1 = TaskCreate(subject="Scout codebase",           metadata={step: 1, phase: "investigate"})
-T2 = TaskCreate(subject="Diagnose root cause",       metadata={step: 2, phase: "investigate"})
-T3 = TaskCreate(subject="Research solutions",         metadata={step: 3, phase: "investigate"})
-T4 = TaskCreate(subject="Brainstorm approaches",      metadata={step: 4, phase: "design"},     addBlockedBy=[T1, T2, T3])
-T5 = TaskCreate(subject="Create implementation plan", metadata={step: 5, phase: "design"},     addBlockedBy=[T4])
-T6 = TaskCreate(subject="Implement fix",              metadata={step: 6, phase: "implement"},  addBlockedBy=[T5])
-T7 = TaskCreate(subject="Verify + prevent",           metadata={step: 7, phase: "verify"},     addBlockedBy=[T6])
-T8 = TaskCreate(subject="Code review",                metadata={step: 8, phase: "verify"},     addBlockedBy=[T7])
-T9 = TaskCreate(subject="Finalize & docs",            metadata={step: 9, phase: "finalize"},   addBlockedBy=[T8])
-```
-
-**Note:** Steps 1, 2, and 3 run in parallel (scout + diagnose + research simultaneously).
-
-## Parallel Issue Coordination
-
-For 2+ independent issues, create separate task trees per issue:
-
-```
-// Issue A tree
-TaskCreate(subject="[Issue A] Scout",      metadata={issue: "A", step: 1})
-TaskCreate(subject="[Issue A] Diagnose",   metadata={issue: "A", step: 2})
-TaskCreate(subject="[Issue A] Fix",        metadata={issue: "A", step: 3}, addBlockedBy=[A-step1, A-step2])
-TaskCreate(subject="[Issue A] Verify",     metadata={issue: "A", step: 4}, addBlockedBy=[A-step3])
-
-// Issue B tree
-TaskCreate(subject="[Issue B] Scout",      metadata={issue: "B", step: 1})
-TaskCreate(subject="[Issue B] Diagnose",   metadata={issue: "B", step: 2})
-TaskCreate(subject="[Issue B] Fix",        metadata={issue: "B", step: 3}, addBlockedBy=[B-step1, B-step2])
-TaskCreate(subject="[Issue B] Verify",     metadata={issue: "B", step: 4}, addBlockedBy=[B-step3])
-
-// Final shared task
-TaskCreate(subject="Integration verify",   addBlockedBy=[A-step4, B-step4])
-```
-
-Spawn `fullstack-developer` subagents per issue tree. Each agent:
-1. Claims tasks via `TaskUpdate(status="in_progress")`
-2. Completes tasks via `TaskUpdate(status="completed")`
-3. Blocked tasks auto-unblock when dependencies resolve
-
-## Subagent Task Assignment
-
-Assign tasks to subagents via `owner` field:
-
-```
-TaskUpdate(taskId=taskA, owner="agent-scout")
-TaskUpdate(taskId=taskB, owner="agent-diagnose")
-```
-
-Check available work: `TaskList()` → filter by `status=pending`, `blockedBy=[]`, `owner=null`
-
-## Rules
-
-- Create tasks BEFORE starting work (upfront planning)
-- Only 1 task `in_progress` per agent at a time
-- Mark complete IMMEDIATELY after finishing (don't batch)
-- Use `metadata` for filtering: `{step, phase, issue, severity}`
-- If task fails → keep `in_progress`, create subtask for blocker
-- Skip Tasks entirely for Quick workflow (< 3 steps)

package/.opencode/skills/fix/references/workflow-ci.md

@@ -1,28 +0,0 @@
-# CI/CD Fix Workflow
-
-For GitHub Actions failures and CI/CD pipeline issues.
-
-## Prerequisites
-- `gh` CLI installed and authorized
-- GitHub Actions URL or run ID
-
-## Workflow
-
-1. **Fetch logs** with `debugger` agent:
-   ```bash
-   gh run view <run-id> --log-failed
-   gh run view <run-id> --log
-   ```
-
-2. **Analyze** root cause from logs
-
-3. **Implement fix** based on analysis
-
-4. **Test locally** with `tester` agent before pushing
-
-5. **Iterate** if tests fail, repeat from step 3
-
-## Notes
-- If `gh` unavailable, instruct user to install: `gh auth login`
-- Check both failed step and preceding steps for context
-- Common issues: env vars, dependencies, permissions, timeouts