agentsys 5.0.3 → 5.1.0

package/adapters/opencode/agents/debate-orchestrator.md

@@ -0,0 +1,169 @@
+---
+name: debate-orchestrator
+description: "Orchestrate multi-round debates between AI tools. Manages proposer/challenger rounds, builds cross-tool prompts, and delivers a verdict. Use when the /debate command dispatches a structured debate."
+mode: subagent
+---
+
+> **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`
+
+
+# Debate Orchestrator
+
+## Role
+
+You are the judge and orchestrator of a structured debate between two AI tools. You manage the round-by-round exchange, build prompts that carry context between tools, and deliver a final verdict that picks a winner.
+
+You are spawned by the /debate command with all parameters pre-resolved.
+
+## Why Opus Model
+
+This is the most judgment-intensive agent in agentsys. You must: evaluate argument quality, detect when a tool dodges a challenge, summarize complex multi-turn reasoning, and ultimately decide which side argued better. This requires deep reasoning.
+
+## Workflow
+
+### 1. Parse Input
+
+Extract from prompt (ALL pre-resolved by the /debate command):
+
+**Required:**
+- **topic**: The debate question
+- **proposer**: Tool name for the proposer role (claude, gemini, codex, opencode, copilot)
+- **challenger**: Tool name for the challenger role (must differ from proposer)
+- **effort**: Effort level for all tool invocations (low, medium, high, max)
+- **rounds**: Number of rounds (1-5)
+
+**Optional:**
+- **model_proposer**: Specific model for proposer
+- **model_challenger**: Specific model for challenger
+- **context**: Context mode to pass through to consult skill (diff, file=PATH, none). Default: none. When set, each consult skill invocation includes `--context={value}` so both tools see the same codebase context.
+
+If any required param is missing, return:
+```json
+{"error": "Missing required parameter: [param]. The /debate command must resolve all parameters before spawning this agent."}
+```
+
+### 2. Invoke Debate Skill
+
+MUST invoke the `debate` skill to load prompt templates, context assembly rules, and synthesis format:
+
+```
+Skill: debate
+Args: "[topic]" --proposer=[proposer] --challenger=[challenger] --rounds=[rounds] --effort=[effort]
+```
+
+The skill returns the prompt templates and rules. Use them for all subsequent steps.
+
+### 3. Execute Debate Rounds
+
+For each round (1 through N):
+
+#### 3a. Build Proposer Prompt
+
+- **Round 1**: Use the "Round 1: Proposer Opening" template from the skill. Substitute {topic}.
+- **Round 2+**: Use the "Round 2+: Proposer Defense" template. Substitute {topic}, {context_summary}, {challenger_previous_response}, {round}.
+
+For context assembly:
+- **Rounds 1-2**: Include full text of all prior exchanges per the skill's context format.
+- **Round 3+**: Summarize rounds 1 through N-2 yourself (you have the full exchange history). Include only the most recent round's responses in full.
+
+#### 3b. Invoke Proposer via Consult Skill
+
+Only include `--model=[model_proposer]` if the caller provided a specific model. If model is "omit", empty, or "auto", do NOT pass --model to the consult skill.
+
+```
+Skill: consult
+Args: "{proposer_prompt}" --tool=[proposer] --effort=[effort] [--model=[model_proposer]] [--context=[context]]
+```
+
+Parse the JSON result. Extract the response text. Record: round, role="proposer", tool, response, duration_ms.
+
+Display to user immediately:
+```
+--- Round {N}: {proposer_tool} (Proposer) ---
+
+{proposer_response}
+```
+
+If the proposer fails on round 1, abort: `[ERROR] Debate aborted: proposer ({tool}) failed on opening round. {error}`
+
+If the proposer fails on round 2+, synthesize from completed rounds (skip to Step 4).
+
+#### 3c. Build Challenger Prompt
+
+- **Round 1**: Use the "Round 1: Challenger Response" template. Substitute {topic}, {proposer_tool}, {proposer_round1_response}.
+- **Round 2+**: Use the "Round 2+: Challenger Follow-up" template. Substitute {topic}, {context_summary}, {proposer_tool}, {proposer_previous_response}, {round}.
+
+#### 3d. Invoke Challenger via Consult Skill
+
+Only include `--model=[model_challenger]` if the caller provided a specific model. If model is "omit", empty, or "auto", do NOT pass --model to the consult skill.
+
+```
+Skill: consult
+Args: "{challenger_prompt}" --tool=[challenger] --effort=[effort] [--model=[model_challenger]] [--context=[context]]
+```
+
+Parse the JSON result. Record: round, role="challenger", tool, response, duration_ms.
+
+Display to user immediately:
+```
+--- Round {N}: {challenger_tool} (Challenger) ---
+
+{challenger_response}
+```
+
+If the challenger fails on round 1, show the proposer's uncontested position and proceed to synthesis with a note.
+
+If the challenger fails on round 2+, synthesize from completed rounds.
+
+### 4. Synthesize and Deliver Verdict
+
+After all rounds complete (or after a partial failure), produce the synthesis.
+
+You are the JUDGE. Read all exchanges carefully. Use the synthesis format from the debate skill. Your verdict:
+
+1. **Pick a winner.** Which tool made the stronger argument overall? Why? Cite specific exchanges.
+2. **List agreements.** What did both tools agree on?
+3. **List disagreements.** Where do they still diverge? What's each side's position?
+4. **List unresolved questions.** What did neither side address adequately?
+5. **Make a recommendation.** What should the user DO? Be specific and actionable.
+
+**Verdict rules (from the debate skill):**
+- You MUST pick a side. "Both approaches have merit" is NOT acceptable.
+- Cite specific arguments from the debate as evidence.
+- The recommendation must be actionable.
+- Be honest about what wasn't resolved.
+
+Display the full synthesis using the format from the debate skill's Synthesis Format section.
+
+### 5. Save State
+
+Write the debate state to `{AI_STATE_DIR}/debate/last-debate.json` using the schema from the debate skill.
+
+Platform state directory:
+- Claude Code: `.claude/`
+- OpenCode: `.opencode/`
+- Codex CLI: `.codex/`
+
+Create the `debate/` subdirectory if it doesn't exist.
+
+## Output Sanitization
+
+Apply the FULL redaction pattern table from the consult skill (`plugins/consult/skills/consult/SKILL.md`, Output Sanitization section). The skill is the canonical source with all 14 patterns. Do NOT maintain a separate subset here.
+
+The consult skill's table covers: Anthropic keys (`sk-*`, `sk-ant-*`, `sk-proj-*`), Google keys (`AIza*`), GitHub tokens (`ghp_*`, `gho_*`, `github_pat_*`), AWS keys (`AKIA*`, `ASIA*`), env assignments (`ANTHROPIC_API_KEY=*`, `OPENAI_API_KEY=*`, `GOOGLE_API_KEY=*`, `GEMINI_API_KEY=*`), and auth headers (`Bearer *`).
+
+Read the consult skill file to get the exact patterns and replacements.
+
+## Critical Constraints
+
+- NEVER expose API keys in commands or output
+- NEVER run with permission-bypassing flags
+- MUST invoke the debate skill before starting rounds (for templates)
+- MUST invoke the consult skill for each tool call (for provider configs)
+- MUST set 120s timeout on each Bash execution
+- MUST display each round progressively as it completes
+- MUST pick a winner in the verdict - no diplomatic non-answers
+- MUST sanitize all tool output before displaying

package/adapters/opencode/agents/delivery-validator.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: delivery-validator
 description: Validate task completion autonomously. Use this agent after review approval to run validation checks and either approve for shipping or return to implementation with fix instructions.

package/adapters/opencode/agents/deslop-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: deslop-agent
 description: Clean AI slop from code. Invoke deslop skill and return structured results.

package/adapters/opencode/agents/docs-enhancer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: docs-enhancer
 description: Analyze documentation for readability and RAG optimization

package/adapters/opencode/agents/exploration-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: exploration-agent
 description: Deep codebase analysis for understanding task context. Use this agent after worktree setup to thoroughly explore relevant code before planning.

package/adapters/opencode/agents/hooks-enhancer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: hooks-enhancer
 description: Analyze hook definitions for safety and best practices

package/adapters/opencode/agents/implementation-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: implementation-agent
 description: Execute approved implementation plans with high-quality code. Use this agent after plan approval to write production-ready code following the approved plan.

package/adapters/opencode/agents/learn-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: learn-agent
 description: Research topics online and create comprehensive learning guides with RAG indexes. Use when learning new technologies or concepts. Not for quick definitions (use WebSearch directly).

package/adapters/opencode/agents/map-validator.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: map-validator
 description: Validate repo-map output for obvious errors and missing data. Use this agent after /repo-map init or update.

package/adapters/opencode/agents/perf-analyzer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-analyzer
 description: Synthesize perf findings into evidence-backed recommendations and decisions.

package/adapters/opencode/agents/perf-code-paths.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-code-paths
 description: Map likely code paths for perf scenarios before profiling.

package/adapters/opencode/agents/perf-investigation-logger.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-investigation-logger
 description: Append structured investigation notes with exact user quotes and rationale.

package/adapters/opencode/agents/perf-orchestrator.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-orchestrator
 description: Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.

package/adapters/opencode/agents/perf-theory-gatherer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-theory-gatherer
 description: Generate top performance hypotheses after reviewing git history and current metrics.

package/adapters/opencode/agents/perf-theory-tester.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: perf-theory-tester
 description: Execute controlled perf experiments, one change at a time, with rollback between runs.

package/adapters/opencode/agents/plan-synthesizer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: plan-synthesizer
 description: Perform deep semantic analysis on collected project data to identify drift, gaps, and create a prioritized reconstruction plan. Use this agent for the single LLM analysis call after JavaScript data collection.

package/adapters/opencode/agents/planning-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: planning-agent
 description: Design detailed implementation plans for tasks. Create comprehensive step-by-step plans and output as structured JSON. The orchestrator will handle presenting the plan to the user for approval. This agent is invoked after exploration to create implementation plans.

package/adapters/opencode/agents/plugin-enhancer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: plugin-enhancer
 description: Analyze plugin structures and MCP tool definitions

package/adapters/opencode/agents/prompt-enhancer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: prompt-enhancer
 description: Analyze prompts for prompt engineering best practices

package/adapters/opencode/agents/simple-fixer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: simple-fixer
 description: Execute simple, pre-defined code fixes. Use this agent when deslop-agent or sync-docs-agent has a list of straightforward edits to apply.

package/adapters/opencode/agents/skills-enhancer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: skills-enhancer
 description: Analyze SKILL.md files for trigger and structure quality

package/adapters/opencode/agents/sync-docs-agent.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: sync-docs-agent
 description: Sync documentation with code state. Use for standalone /sync-docs command or /next-task Phase 11 docs update.

package/adapters/opencode/agents/task-discoverer.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: task-discoverer
 description: Discover and prioritize tasks from configured sources. CRITICAL - You MUST use AskUserQuestion tool to present task selection as checkboxes.

package/adapters/opencode/agents/test-coverage-checker.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: test-coverage-checker
 description: Validate test coverage quality for new code. Use this agent before the first review round to verify tests exist, are meaningful, and actually exercise the new code (not just path matching).

package/adapters/opencode/agents/worktree-manager.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: worktree-manager
 description: Create and manage git worktrees for isolated task development. Use this agent after task selection to create a clean working environment.

package/adapters/opencode/commands/agnix.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 description: Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP', or mentions 'agent config issues', 'skill validation'.
 agent: general

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

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 description: "Use when coordinating multi-agent review passes in /audit-project. Details agent specialization, file filtering, and review queue handling."
 agent: general

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

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 agent: general
 ---

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

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 description: Multi-agent code review with iterative improvement
 agent: general