agentsys 5.0.3 → 5.2.0

package/adapters/opencode/commands/audit-project.md

@@ -1,268 +0,0 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
----
-description: Multi-agent code review with iterative improvement
-agent: general
----
-
-> **OpenCode Note**: Invoke agents using `@agent-name` syntax.
-> Available agents: task-discoverer, exploration-agent, planning-agent,
-> implementation-agent, deslop-agent, delivery-validator, sync-docs-agent, consult-agent
-> Example: `@exploration-agent analyze the codebase`
-
-
-# /audit-project - Multi-Agent Code Review
-
-Comprehensive code review using specialized AI agents with iterative improvement.
-
-## Quick Reference
-
-| Phase | Description | Details |
-|-------|-------------|---------|
-| 1 | Context & Agent Selection | This file |
-| 2 | Multi-Agent Review | See `audit-project-agents.md` |
-| 3-4 | Tech Debt & Fixes | This file |
-| 5-6 | Verification & Iteration | This file |
-| 7 | Completion Report | This file |
-| 8 | GitHub Issues | See `audit-project-github.md` |
-
-## Arguments
-
-Parse from $ARGUMENTS:
-- **Scope**: Path to review (default: `.`) or `--recent` (last 5 commits only)
-- **--domain AGENT**: Review with specific agent only (e.g., `--domain security`)
-- **--quick**: Single pass, no iteration (fast feedback)
-- **--create-tech-debt**: Force create/update TECHNICAL_DEBT.md
-- **--resume**: Resume from existing review queue file
-
-### Resume Mode
-
-If `--resume` is provided, reuse the most recent review queue in the platform state dir.
-Otherwise create a new queue file. See `audit-project-agents.md` for queue handling.
-
-## Phase 1: Context Gathering
-
-### Platform Detection
-
-*(Bash command with Node.js require - adapt for OpenCode)*
-
-### Project Analysis
-
-```bash
-FILE_COUNT=$(git ls-files | wc -l)
-TEST_FILES=$(git ls-files | grep -E '(test|spec)\.' | wc -l)
-HAS_TESTS=$( [ "$TEST_FILES" -gt 0 ] && echo "true" || echo "false" )
-HAS_DB=$(grep -rq -E "(Sequelize|Prisma|TypeORM)" . 2>/dev/null && echo "true" || echo "false")
-HAS_API=$(grep -rq -E "(express|fastify|@nestjs)" . 2>/dev/null && echo "true" || echo "false")
-HAS_FRONTEND=$( [ "$(git ls-files | grep -E '\.(tsx|jsx|vue|svelte)$' | wc -l)" -gt 0 ] && echo "true" || echo "false" )
-HAS_BACKEND=$(grep -rq -E "(express|fastify|@nestjs|koa|hapi)" . 2>/dev/null && echo "true" || echo "false")
-if [ -d ".github/workflows" ] || [ -f ".gitlab-ci.yml" ] || [ -f ".circleci/config.yml" ] || \
-  [ -f "Jenkinsfile" ] || [ -f ".travis.yml" ] || [ -f "azure-pipelines.yml" ] || \
-  [ -f "bitbucket-pipelines.yml" ]; then
-  HAS_CICD="true"
-else
-  HAS_CICD="false"
-fi
-```
-
-### Agent Selection
-
-**Always Active:**
-- `code-quality-reviewer`: Code quality, error handling, maintainability
-- `security-expert`: Security vulnerabilities, auth, input validation
-- `performance-engineer`: Performance bottlenecks, algorithms, memory
-- `test-quality-guardian`: Test coverage and quality (reports missing tests)
-
-**Conditional:**
-- `architecture-reviewer`: Design patterns (if `FILE_COUNT > 50`)
-- `database-specialist`: Query optimization (if `HAS_DB=true`)
-- `api-designer`: REST best practices (if `HAS_API=true`)
-- `frontend-specialist`: Component design (if `HAS_FRONTEND=true`)
-- `backend-specialist`: Service and domain logic (if `HAS_BACKEND=true`)
-- `devops-reviewer`: CI/CD config (if `HAS_CICD=true`)
-
-## Phase 2: Multi-Agent Review
-
-See `audit-project-agents.md` for detailed agent coordination.
-
-**Review queue:** Write findings to a temporary queue file in the platform state dir and keep it updated until all issues are resolved. Remove the file when the queue is empty.
-
-### Finding Format (Required)
-
-Every finding MUST include:
-- **File:Line**: Exact location (e.g., `src/auth/session.ts:42`)
-- **Severity**: critical | high | medium | low
-- **Category**: From agent domain
-- **Description**: What's wrong and why
-- **Code Quote**: 1-3 lines showing issue
-- **Suggested Fix**: Specific remediation
-- **Effort**: small | medium | large
-
-### Example Finding
-
-```markdown
-### Finding: Unsafe SQL Query
-**Agent**: security-expert
-**File**: src/api/users.ts:87
-**Severity**: critical
-**Code**:
-```typescript
-const query = `SELECT * FROM users WHERE id = ${userId}`;
-```
-**Fix**: Use parameterized queries.
-**Effort**: small
-```
-
-## Phase 3: Tech Debt Documentation
-
-If TECHNICAL_DEBT.md exists or `--create-tech-debt`:
-
-```markdown
-# Technical Debt
-
-Last updated: $(date -I)
-
-## Summary
-**Total Issues**: X | Critical: Y | High: Z | Medium: A | Low: B
-
-## Critical Issues
-[Grouped by severity with file:line, description, fix, effort]
-
-## Progress Tracking
-- [ ] Issue 1
-- [ ] Issue 2
-```
-
-## Phase 4: Automated Fixes
-
-### Fix Strategy
-
-1. **Auto-fixable** (lint, formatting): Apply directly
-2. **Manual fix** (code logic): Implement suggested fix
-3. **Design decision required**: Flag as blocked and report to user
-4. **False positive**: Mark and remove from review queue
-
-### Fix Order
-
-1. Critical severity first
-2. Then high → medium → low
-3. Then by effort (small → large)
-4. Then batch by file
-
-## Phase 5: Verification
-
-```bash
-# Run tests
-[ -n "$TEST_CMD" ] && $TEST_CMD
-TEST_STATUS=$?
-
-# Run linter
-[ -n "$LINT_CMD" ] && $LINT_CMD
-LINT_STATUS=$?
-
-# Run build
-[ -n "$BUILD_CMD" ] && $BUILD_CMD
-BUILD_STATUS=$?
-
-# Overall status
-VERIFICATION_PASSED=$([ $TEST_STATUS -eq 0 ] && [ $LINT_STATUS -eq 0 ] && [ $BUILD_STATUS -eq 0 ] && echo "true" || echo "false")
-```
-
-### Handle Failures
-
-If verification fails:
-1. Review recent changes (`git diff`)
-2. Identify breaking fix
-3. Rollback: `git restore <file>`
-4. Document as "fix caused regression"
-
-## Phase 6: Iteration
-
-*(JavaScript reference - not executable in OpenCode)*
-
-### Quick Mode
-
-If `--quick` flag: Single pass, findings only, no fixes.
-
-## Phase 6.5: Decision Gate (User)
-
-After each iteration (or after re-review if issues remain), report the queue state and ask the user what to do next.
-
-- Use AskUserQuestion tool for user input
-
-
-## Phase 7: Completion Report
-
-```markdown
-# Project Review Complete
-
-**Scope**: ${SCOPE} | **Framework**: ${FRAMEWORK}
-**Iterations**: ${iteration} | **Duration**: ${duration}
-
-## Summary
-**Issues Found**: ${initialCount}
-**Issues Fixed**: ${fixedCount}
-**Remaining**: ${remainingCount}
-
-## By Severity
-- Critical: ${criticalFound} → ${criticalRemaining}
-- High: ${highFound} → ${highRemaining}
-- Medium: ${mediumFound} → ${mediumRemaining}
-- Low: ${lowFound} → ${lowRemaining}
-
-## Verification
-- Tests: [OK]/[FAIL]
-- Linter: [OK]/[FAIL]
-- Build: [OK]/[FAIL]
-
-## Files Changed
-${FILE_COUNT} files modified
-
-## Remaining Issues
-[List of issues needing attention]
-```
-
-## Phase 8: GitHub Issue Creation
-
-See `audit-project-github.md` for:
-- Creating GitHub issues for deferred items
-- Security issue handling (no public issues)
-- TECHNICAL_DEBT.md cleanup
-
-## Error Handling
-
-### No Framework Detected
-```
-Framework detection failed, using generic patterns.
-```
-
-### No Tests Available
-```
-No test suite detected. Skipping test-quality-guardian.
-```
-
-### All Agents Failed
-```
-ERROR: All review agents failed.
-Try: --recent or specific path for smaller scope.
-```
-
-## Usage Examples
-
-```bash
-/audit-project                    # Full review
-/audit-project --recent           # Last 5 commits only
-/audit-project src/api            # Specific path
-/audit-project --domain security  # Security audit only
-/audit-project --quick            # Fast feedback, no fixes
-/audit-project --create-tech-debt # Force tech debt file
-```
-
-## Success Criteria
-
-- [OK] All agents completed review
-- [OK] Evidence-based findings (file:line provided)
-- [OK] Critical issues fixed or documented
-- [OK] Verification passes
-- [OK] TECHNICAL_DEBT.md updated (if enabled)
-
-Begin Phase 1 now.

package/adapters/opencode/commands/consult.md

@@ -1,252 +0,0 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
----
-description: Consult another AI CLI tool for a second opinion. Use when you want to cross-check ideas, get alternative approaches, or validate decisions with Gemini, Codex, Claude, OpenCode, or Copilot.
-agent: general
----
-
-> **OpenCode Note**: Invoke agents using `@agent-name` syntax.
-> Available agents: task-discoverer, exploration-agent, planning-agent,
-> implementation-agent, deslop-agent, delivery-validator, sync-docs-agent, consult-agent
-> Example: `@exploration-agent analyze the codebase`
-
-
-# /consult - Cross-Tool AI Consultation
-
-You are executing the /consult command. Your job is to consult another AI CLI tool, get its response, and present the results to the user.
-
-## Constraints
-
-- NEVER expose API keys in commands or output
-- NEVER run with permission-bypassing flags (`--dangerously-skip-permissions`, `bypassPermissions`)
-- MUST use safe-mode defaults (`-a suggest` for Codex, `--allowedTools "Read,Glob,Grep"` for Claude)
-- MUST enforce 120s timeout on all tool executions
-- MUST validate `--tool` against allow-list: gemini, codex, claude, opencode, copilot (reject all others)
-- MUST validate `--context=file=PATH` is within the project directory (reject absolute paths outside cwd)
-- MUST quote all user-provided values in shell commands to prevent injection
-- NEVER execute tools the user has not explicitly requested
-
-## Arguments
-
-Parse from $ARGUMENTS:
-
-- **question**: What to ask the consulted tool (required unless --continue)
-- **--tool**: Target tool: `gemini`, `codex`, `claude`, `opencode`, `copilot` (interactive picker if omitted)
-- **--effort**: Thinking effort: `low`, `medium`, `high`, `max` (interactive picker if omitted)
-- **--model**: Specific model name (interactive picker if omitted). Free text.
-- **--context**: Auto-include context: `diff` (git diff), `file=PATH` (attach specific file), `none` (default)
-- **--continue**: Continue last consultation session, or `--continue=SESSION_ID` for specific session
-
-## Execution
-
-### Phase 1: Parse Arguments
-
-Extract these values from `$ARGUMENTS`:
-
-1. Look for `--tool=VALUE` or `--tool VALUE` where VALUE MUST be one of: gemini, codex, claude, opencode, copilot (reject others)
-2. Look for `--effort=VALUE` or `--effort VALUE` where VALUE MUST be one of: low, medium, high, max
-3. Look for `--model=VALUE` or `--model VALUE` (any string, including quoted strings like `"my model"`)
-4. Look for `--context=VALUE` where VALUE is: diff, file=PATH, or none
-5. Look for `--continue` (optionally `--continue=SESSION_ID`)
-6. Remove all matched flags (including their values) from `$ARGUMENTS`. Handle quoted flag values (e.g., `--model "gpt 4"`) by removing the entire quoted string. Everything remaining is the **question**.
-
-If no question text and no `--continue` flag found, show:
-```
-[ERROR] Usage: /consult "your question" [--tool=gemini|codex|claude|opencode|copilot] [--effort=low|medium|high|max]
-```
-
-### Phase 2: Interactive Parameter Selection
-
-MUST resolve ALL missing parameters interactively before Phase 3. ONLY skip this phase if ALL of --tool, --effort, AND --model are explicitly provided by the user in $ARGUMENTS. Do NOT silently default any parameter.
-
-#### Step 2a: Handle --continue
-
-If `--continue` is present:
-1. Read the session file at `{AI_STATE_DIR}/consult/last-session.json`
-
-   Platform state directory:
-   - Claude Code: `.opencode/`
-   - OpenCode: `.opencode/`
-   - Codex CLI: `.codex/`
-2. If the file exists, restore the saved tool, session_id, and model from it
-3. If the file does not exist, show `[WARN] No previous session found` and proceed as a fresh consultation
-
-#### Step 2b: Batch Selection (tool + effort)
-
-First, detect which tools are installed by running all 5 checks **in parallel** via Bash:
-
-- `where.exe <tool> 2>nul && echo FOUND || echo NOTFOUND` (Windows)
-- `which <tool> 2>/dev/null && echo FOUND || echo NOTFOUND` (Unix)
-
-Check for: claude, gemini, codex, opencode, copilot.
-
-If zero tools are installed: `[ERROR] No AI CLI tools found. Install at least one: npm i -g @anthropic-ai/claude-code, npm i -g @openai/codex, npm i -g opencode-ai`
-
-Then use a SINGLE AskUserQuestion call to ask all missing parameters at once. Include only the questions for parameters NOT already provided in $ARGUMENTS:
-
-```
-AskUserQuestion:
-  questions:
-    - header: "AI Tool"                          # SKIP if --tool provided
-      question: "Which AI tool should I consult?"
-      multiSelect: false
-      options (only if installed):
-        - label: "Claude"       description: "Deep code reasoning"
-        - label: "Gemini"       description: "Fast multimodal analysis"
-        - label: "Codex"        description: "Agentic coding"
-        - label: "OpenCode"     description: "Flexible model choice"
-        - label: "Copilot"      description: "GitHub-integrated AI"
-
-    - header: "Effort"                           # SKIP if --effort provided
-      question: "What thinking effort level?"
-      multiSelect: false
-      options:
-        - label: "Medium (Recommended)"  description: "Balanced speed and quality"
-        - label: "Low"                   description: "Fast, minimal reasoning"
-        - label: "High"                  description: "Thorough analysis"
-        - label: "Max"                   description: "Maximum reasoning depth"
-```
-
-Map tool choice to lowercase: "Claude" -> "claude", "Codex" -> "codex", etc.
-Map effort choice: "Medium (Recommended)" -> "medium", "Low" -> "low", "High" -> "high", "Max" -> "max".
-
-IMPORTANT: Do NOT skip any missing parameter. Do NOT silently default --effort to "medium" or --tool to any value. Present pickers for ALL unresolved parameters.
-
-#### Step 2c: Model Selection (MUST ask if no --model)
-
-After tool is resolved (from Step 2b or $ARGUMENTS), present a model picker with options specific to the selected tool. The user can always type a custom model name via the "Other" option.
-
-**For Claude:**
-```
-AskUserQuestion:
-  questions:
-    - header: "Model"
-      question: "Which Claude model?"
-      multiSelect: false
-      options:
-        - label: "sonnet (Recommended)"  description: "Sonnet 4.5 - balanced speed and intelligence"
-        - label: "opus"                  description: "Opus 4.6 - most capable, adaptive thinking"
-        - label: "haiku"                 description: "Haiku 4.5 - fastest, lightweight"
-```
-
-**For Gemini:**
-```
-AskUserQuestion:
-  questions:
-    - header: "Model"
-      question: "Which Gemini model?"
-      multiSelect: false
-      options:
-        - label: "gemini-3-pro"          description: "Most capable, strong reasoning"
-        - label: "gemini-3-flash"        description: "Fast, 78% SWE-bench"
-        - label: "gemini-2.5-pro"        description: "Previous gen pro model"
-        - label: "gemini-2.5-flash"      description: "Previous gen flash model"
-```
-
-**For Codex:**
-```
-AskUserQuestion:
-  questions:
-    - header: "Model"
-      question: "Which Codex model?"
-      multiSelect: false
-      options:
-        - label: "gpt-5.3-codex"        description: "Latest, most capable coding model"
-        - label: "gpt-5.2-codex"        description: "Strong coding model"
-        - label: "gpt-5.2"              description: "General purpose GPT-5.2"
-        - label: "gpt-5-codex-mini"     description: "Cost-effective, 4x more usage"
-```
-
-**For OpenCode:**
-```
-AskUserQuestion:
-  questions:
-    - header: "Model"
-      question: "Which model? (type via Other for paid: anthropic/claude-opus-4-6, openai/gpt-5.3-codex)"
-      multiSelect: false
-      options:
-        - label: "opencode/big-pickle"             description: "Free - Zen stealth model, 200K context"
-        - label: "opencode/minimax-m2.1-free"      description: "Free - 230B MoE, strong multilingual coding"
-        - label: "opencode/kimi-k2.5-free"         description: "Free - 1T multimodal, strong coding and agentic"
-        - label: "opencode/trinity-large-preview"  description: "Free - 400B sparse MoE by Arcee AI, 512K context"
-```
-
-**For Copilot:**
-```
-AskUserQuestion:
-  questions:
-    - header: "Model"
-      question: "Which Copilot model?"
-      multiSelect: false
-      options:
-        - label: "claude-sonnet-4-5"        description: "Default Copilot model"
-        - label: "claude-opus-4-6"          description: "Most capable Claude model"
-        - label: "gpt-5.3-codex"              description: "OpenAI GPT-5.3 Codex"
-        - label: "gemini-3-pro"             description: "Google Gemini 3 Pro"
-```
-
-Map the user's choice to the model string (strip " (Recommended)" suffix if present). Pass the selected model to the skill via `--model`.
-
-IMPORTANT: Do NOT skip this step. Do NOT silently use a default model. If --model was not explicitly provided in $ARGUMENTS, you MUST present this picker. The model lists above are current as of Feb 2026 - the user may type any model name supported by their tool via the "Other" option.
-
-### Phase 3: Invoke Consult Skill
-
-With all parameters resolved (tool, effort, model, question, and optionally context, continue), invoke the `consult` skill using the Skill tool:
-
-```
-Skill: consult
-Args: "[question]" --tool=[tool] --effort=[effort] --model=[model] [--context=[context]] [--continue=[session_id]]
-
-Example: "Is this the right approach?" --tool=gemini --effort=high --model=gemini-3-pro
-```
-
-The skill handles the full consultation lifecycle: it resolves the model from the effort level, builds the CLI command, packages any context, executes the command via Bash with a 120-second timeout, and returns a plain JSON result.
-
-### Phase 4: Parse Skill Output
-
-The skill returns a plain JSON object containing: `tool`, `model`, `effort`, `duration_ms`, `response`, `session_id`, and `continuable`. Parse the JSON directly from the skill output.
-
-### Phase 5: Present Results
-
-After parsing the JSON, format and display the result as human-friendly text:
-
-```
-Tool: {tool}, Model: {model}, Effort: {effort}, Duration: {duration_ms}ms.
-
-The results of the consultation are:
-{response}
-```
-
-For continuable tools (Claude, Gemini, Codex, OpenCode), display: `Session: {session_id} - use /consult --continue to resume`
-
-Save session state for continuable tools (Claude, Gemini, Codex, OpenCode) to `{AI_STATE_DIR}/consult/last-session.json`.
-
-Platform state directory:
-- Claude Code: `.opencode/`
-- OpenCode: `.opencode/`
-- Codex CLI: `.codex/`
-
-On failure: `[ERROR] Consultation Failed: {specific error message}`
-
-## Error Handling
-
-| Error | Output |
-|-------|--------|
-| No question provided | `[ERROR] Usage: /consult "your question" [--tool=gemini\|codex\|claude\|opencode\|copilot] [--effort=low\|medium\|high\|max]` |
-| Tool not installed | `[ERROR] {tool} is not installed. Install with: {install command from skill}` |
-| Tool execution fails | `[ERROR] {tool} failed: {error}. Try a different tool with --tool=[other]` |
-| Timeout (>120s) | `[ERROR] {tool} timed out after 120s. Try --effort=low for faster response` |
-| No tools available | `[ERROR] No AI CLI tools found. Install: npm i -g @anthropic-ai/claude-code` |
-| Session not found | `[WARN] No previous session found. Starting fresh consultation.` |
-| API key missing | `[ERROR] {tool} requires API key. Set {env var} (see skill for details)` |
-
-## Example Usage
-
-```bash
-/consult "Is this the right approach for error handling?" --tool=gemini --effort=high
-/consult "Review this function for performance issues" --tool=codex
-/consult "What alternative patterns would you suggest?" --tool=claude --effort=max
-/consult "Suggest improvements" --tool=opencode --model=github-copilot/claude-opus-4-6
-/consult "Continue from where we left off" --continue
-/consult "Explain this error" --context=diff --tool=gemini
-/consult "Review this file" --context=file=src/index.js --tool=claude
-```