agentsys 5.1.0 → 5.2.1

package/plugins/debate/skills/debate/SKILL.md

@@ -1,264 +0,0 @@
----
-name: debate
-description: "Structured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 'stress test idea', 'devil advocate'."
-version: 5.1.0
-argument-hint: "[topic] [--proposer=tool] [--challenger=tool] [--rounds=N] [--effort=level]"
----
-
-# debate
-
-Prompt templates, context assembly rules, and synthesis format for structured multi-round debates between AI tools.
-
-## Arguments
-
-Parse from `$ARGUMENTS`:
-- **topic**: The debate question/topic (required)
-- **--proposer**: Tool for the proposer role (claude, gemini, codex, opencode, copilot)
-- **--challenger**: Tool for the challenger role (must differ from proposer)
-- **--rounds**: Number of back-and-forth rounds (1-5, default: 2)
-- **--effort**: Thinking effort applied to all tool invocations (low, medium, high, max)
-- **--model-proposer**: Specific model for proposer (optional)
-- **--model-challenger**: Specific model for challenger (optional)
-
-## Universal Rules
-
-ALL participants (proposer AND challenger) MUST support claims with specific evidence (file path, code pattern, benchmark, or documented behavior). Unsupported claims from either side will be flagged by the other participant and noted in the verdict. This applies to every round.
-
-## Prompt Templates
-
-### Round 1: Proposer Opening
-
-```
-You are participating in a structured debate as the PROPOSER.
-
-Topic: {topic}
-
-Your job: Analyze this topic thoroughly and present your position. Take a clear stance. Do not hedge excessively.
-
-You MUST support each claim with specific evidence (file path, code pattern, benchmark, or documented behavior). Unsupported claims will be challenged. "I think" or "generally speaking" without evidence is not acceptable.
-
-Provide your analysis:
-```
-
-### Round 1: Challenger Response
-
-```
-You are participating in a structured debate as the CHALLENGER.
-
-Topic: {topic}
-
-The PROPOSER ({proposer_tool}) argued:
-
----
-{proposer_round1_response}
----
-
-Your job: Find weaknesses, blind spots, and flaws in the proposer's argument. You MUST identify at least one genuine flaw or overlooked consideration before agreeing on anything. Propose concrete alternatives where you disagree.
-
-Rules:
-- Do NOT say "great point" or validate the proposer's reasoning before critiquing it
-- Lead with what's WRONG or MISSING, then acknowledge what's right
-- If you genuinely agree on a point, explain what RISK remains despite the agreement
-- Propose at least one concrete alternative approach
-- You MUST address at least these categories: correctness, security implications, and developer experience
-- Do NOT agree with ANY claim unless you can cite specific evidence (file path, code pattern, or documented behavior) that supports the agreement. Unsupported agreement is not allowed.
-- If the proposer makes a claim without evidence, call it out: "This claim is unsupported."
-
-Provide your challenge:
-```
-
-### Round 2+: Proposer Defense
-
-```
-You are the PROPOSER in round {round} of a structured debate.
-
-Topic: {topic}
-
-{context_summary}
-
-The CHALLENGER ({challenger_tool}) raised these points in round {previous_round}:
-
----
-{challenger_previous_response}
----
-
-Your job: Address each challenge directly. For each point:
-- If they're right, concede explicitly and explain how your position evolves
-- If they're wrong, explain why with specific evidence (file path, code pattern, benchmark, or documented behavior)
-- If it's a tradeoff, acknowledge the tradeoff and explain why you still favor your approach with evidence
-
-Every claim you make -- whether concession, rebuttal, or new argument -- MUST cite specific evidence. The challenger will reject unsupported claims.
-
-Do NOT simply restate your original position. Your response must show you engaged with the specific challenges raised.
-
-Provide your defense:
-```
-
-### Round 2+: Challenger Follow-up
-
-```
-You are the CHALLENGER in round {round} of a structured debate.
-
-Topic: {topic}
-
-{context_summary}
-
-The PROPOSER ({proposer_tool}) responded to your challenges:
-
----
-{proposer_previous_response}
----
-
-IMPORTANT: Do NOT let the proposer reframe your challenges as agreements. If they say "we actually agree" but haven't addressed the substance, reject it. Default to suspicion, not acceptance.
-
-Your job: Evaluate the proposer's defense. For each point they addressed:
-- Did they dodge, superficially address, or respond without evidence? Call it out: "This defense is unsupported" or "This dodges the original concern"
-- Did they concede any point? Hold them to it -- they cannot walk it back later without new evidence
-- Are there NEW weaknesses in their revised position?
-- Did they adequately address your concern with specific evidence? Only then acknowledge it, and cite what convinced you
-
-You MUST either identify at least one new weakness or unresolved concern, OR explicitly certify a previous concern as genuinely resolved with specific evidence for why you're now satisfied. "I'm convinced because [evidence]" is acceptable. "I agree now" without evidence is not.
-If you see new problems, raise them.
-
-Provide your follow-up:
-```
-
-## Context Assembly
-
-### Rounds 1-2: Full context
-
-Include the full text of all prior exchanges in the prompt. Context is small enough (typically under 5000 tokens total).
-
-Format for context block:
-```
-Previous exchanges:
-
-Round 1 - Proposer ({proposer_tool}):
-{full response}
-
-Round 1 - Challenger ({challenger_tool}):
-{full response}
-```
-
-### Round 3+: Summarized context
-
-For rounds 3 and beyond, replace full exchange text from rounds 1 through N-2 with a summary. Only include the most recent round's responses in full.
-
-Format:
-```
-Summary of rounds 1-{N-2}:
-{summary of key positions, agreements, and open disagreements}
-
-Round {N-1} - Proposer ({proposer_tool}):
-{full response}
-
-Round {N-1} - Challenger ({challenger_tool}):
-{full response}
-```
-
-The orchestrator agent (opus) generates the summary. Target: 500-800 tokens. MUST preserve:
-- Each side's core position
-- All concessions (verbatim quotes, not paraphrased)
-- All evidence citations that support agreements
-- Points of disagreement (unresolved)
-- Any contradictions between rounds (e.g., proposer concedes in round 1 but walks it back in round 2 -- note both explicitly)
-
-## Synthesis Format
-
-After all rounds complete, the orchestrator produces this structured output:
-
-```
-## Debate Summary
-
-**Topic**: {topic}
-**Proposer**: {proposer_tool} ({proposer_model})
-**Challenger**: {challenger_tool} ({challenger_model})
-**Rounds**: {rounds_completed}
-**Rigor**: Structured perspective comparison (prompt-enforced adversarial rules, no deterministic verification)
-
-### Verdict
-
-{winner_tool} had the stronger argument because: {specific reasoning citing debate evidence}
-
-### Debate Quality
-
-Rate the debate on these dimensions:
-- **Genuine disagreement**: Did the challenger maintain independent positions, or converge toward the proposer? (high/medium/low)
-- **Evidence quality**: Did both sides cite specific examples, or argue from generalities? (high/medium/low)
-- **Challenge depth**: Were the challenges substantive, or surface-level? (high/medium/low)
-
-### Key Agreements
-- {agreed point 1} (evidence: {what supports this agreement})
-- {agreed point 2} (evidence: {what supports this agreement})
-
-### Key Disagreements
-- {point}: {proposer_tool} argues {X}, {challenger_tool} argues {Y}
-
-### Unresolved Questions
-- {question that neither side adequately addressed}
-
-### Recommendation
-{Orchestrator's recommendation - must pick a direction, not "both have merit"}
-```
-
-**Synthesis rules:**
-- The verdict MUST pick a side. "Both approaches have merit" is NOT acceptable.
-- Cite specific arguments from the debate as evidence for the verdict.
-- The recommendation must be actionable - what should the user DO based on this debate.
-- Unresolved questions highlight where the debate fell short, not where both sides are "equally valid."
-
-## State File Schema
-
-Save to `{AI_STATE_DIR}/debate/last-debate.json`:
-
-```json
-{
-  "id": "debate-{ISO timestamp}-{4 char random hex}",
-  "topic": "original topic text",
-  "proposer": {"tool": "claude", "model": "opus"},
-  "challenger": {"tool": "gemini", "model": "gemini-3-pro"},
-  "effort": "high",
-  "rounds_completed": 2,
-  "max_rounds": 2,
-  "status": "completed",
-  "exchanges": [
-    {"round": 1, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 8500},
-    {"round": 1, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 12000},
-    {"round": 2, "role": "proposer", "tool": "claude", "response": "...", "duration_ms": 9200},
-    {"round": 2, "role": "challenger", "tool": "gemini", "response": "...", "duration_ms": 11000}
-  ],
-  "verdict": {
-    "winner": "claude",
-    "reasoning": "...",
-    "agreements": ["..."],
-    "disagreements": ["..."],
-    "recommendation": "..."
-  },
-  "timestamp": "{ISO 8601 timestamp}"
-}
-```
-
-Platform state directory:
-- Claude Code: `.claude/`
-- OpenCode: `.opencode/`
-- Codex CLI: `.codex/`
-
-## Error Handling
-
-| Error | Action |
-|-------|--------|
-| Proposer fails round 1 | Abort debate. Cannot proceed without opening position. |
-| Challenger fails round 1 | Show proposer's position with note: "[WARN] Challenger failed. Showing proposer's uncontested position." |
-| Any tool fails mid-debate | Synthesize from completed rounds. Note incomplete round in output. |
-| All rounds timeout | "[ERROR] Debate failed: all tool invocations timed out." |
-
-## Consult Skill Integration
-
-Each tool invocation uses the existing `consult` skill from the consult plugin. The orchestrator invokes it as:
-
-```
-Skill: consult
-Args: "{debate prompt with context}" --tool={tool} --effort={effort} --model={model}
-```
-
-The consult skill handles: provider command building, safe question passing (temp file), output parsing, and secret redaction. The debate skill does NOT duplicate this logic.

package/plugins/deslop/.claude-plugin/plugin.json

@@ -1,20 +0,0 @@
-{
-  "name": "deslop",
-  "version": "5.1.0",
-  "description": "AI slop cleanup with minimal diffs and behavior preservation",
-  "author": {
-    "name": "Avi Fenesh",
-    "email": "[email protected]",
-    "url": "https://github.com/avifenesh"
-  },
-  "homepage": "https://github.com/avifenesh/agentsys#deslop",
-  "repository": "https://github.com/avifenesh/agentsys",
-  "license": "MIT",
-  "keywords": [
-    "code-quality",
-    "cleanup",
-    "refactoring",
-    "maintenance",
-    "slop-detection"
-  ]
-}

package/plugins/deslop/agents/deslop-agent.md

@@ -1,88 +0,0 @@
----
-name: deslop-agent
-description: Clean AI slop from code. Invoke deslop skill and return structured results.
-tools:
-  - Bash(git:*)
-  - Bash(node:*)
-  - Skill
-  - Read
-  - Glob
-  - Grep
-model: sonnet
----
-
-# Deslop Agent
-
-Analyze codebase for AI slop patterns using the deslop skill, then return structured results.
-
-## Workflow
-
-### 1. Parse Arguments
-
-Extract from prompt:
-- **Mode**: `report` (default) or `apply`
-- **Scope**: `all` (default), `diff`, or path
-- **Thoroughness**: `quick`, `normal` (default), or `deep`
-
-### 2. Invoke Deslop Skill
-
-```
-Skill: deslop
-Args: <mode> --scope=<scope> --thoroughness=<level>
-```
-
-The skill returns structured findings with certainty levels (HIGH, MEDIUM, LOW).
-
-### 3. Extract Fixable Items
-
-From the skill results, extract items where:
-- `certainty === 'HIGH'`
-- `autoFix` is a fix strategy (not `'flag'` or `'none'`)
-
-Valid autoFix strategies: `'remove'`, `'replace'`, `'add_logging'`
-
-Build the `fixes` array for orchestrator to pass to simple-fixer.
-
-### 4. Return Structured Results
-
-Always output structured JSON between markers:
-
-```
-=== DESLOP_RESULT ===
-{
-  "mode": "report|apply",
-  "scope": "all|diff|path",
-  "filesScanned": N,
-  "findings": {
-    "high": N,
-    "medium": N,
-    "low": N
-  },
-  "fixes": [
-    {
-      "file": "src/api.js",
-      "line": 42,
-      "fixType": "remove-line",
-      "pattern": "debug-statement"
-    }
-  ],
-  "autoFixable": N,
-  "flagged": N
-}
-=== END_RESULT ===
-```
-
-## Constraints
-
-- Do NOT modify files - only report findings
-- Do NOT spawn subagents - return data for orchestrator
-- HIGH certainty items go in `fixes` array
-- MEDIUM/LOW items go in findings summary
-- Respect .gitignore and exclude patterns
-- Skip generated files (dist/, build/, *.min.js)
-
-## Error Handling
-
-- **Git not available**: Exit with error in result
-- **Invalid scope path**: Report error, return empty findings
-- **Parse errors**: Skip file, continue with others

package/plugins/deslop/commands/deslop.md

@@ -1,168 +0,0 @@
----
-description: This skill should be used when the user asks to "clean up slop", "remove AI artifacts", "deslop the codebase", "find debug statements", "remove console.logs", "repo hygiene", or mentions "AI slop", "code cleanup", "slop detection".
-codex-description: 'Use when user asks to "clean up slop", "remove AI artifacts", "deslop the codebase", "find debug statements", "remove console.logs", "repo hygiene". Detects and removes AI-generated slop patterns.'
-argument-hint: "[report|apply] [--scope=path] [--thoroughness=quick|normal|deep]"
-allowed-tools: Task, Read
----
-
-# /deslop - AI Slop Cleanup
-
-Senior maintainer performing periodic repo hygiene. Mission: remove AI-generated slop while preserving behavior and minimizing diffs.
-
-## Constraints (Priority Order)
-
-When constraints conflict, follow this priority:
-
-1. **Preserve behavior and public APIs** (highest priority)
-2. **Minimal diffs** - do not reformat unrelated code
-3. **Prefer deletion over invention**
-4. **No new dependencies or abstractions**
-5. **Respect repo conventions** (check CLAUDE.md/AGENTS.md)
-
-## Arguments
-
-Parse from $ARGUMENTS or use defaults:
-
-- **Mode**: `report` (default) or `apply`
-- **Scope**: `all` (default), `diff`, or path
-- **Thoroughness**: `quick`, `normal` (default), or `deep`
-
-## Execution
-
-### Phase 1: Spawn Deslop Agent
-
-```javascript
-// Parse arguments
-const args = '$ARGUMENTS'.split(' ').filter(Boolean);
-const mode = args.includes('apply') ? 'apply' : 'report';
-const thoroughness = args.find(a => a.startsWith('--thoroughness='))?.split('=')[1] || 'normal';
-const scope = args.find(a => a.startsWith('--scope='))?.split('=')[1] ||
-              args.find(a => !a.startsWith('-') && a !== 'report' && a !== 'apply') || 'all';
-
-// Spawn agent to get findings
-const result = await Task({
-  subagent_type: "deslop:deslop-agent",
-  prompt: `Scan for AI slop patterns.
-Mode: ${mode}
-Scope: ${scope}
-Thoroughness: ${thoroughness}
-
-Return structured results between === DESLOP_RESULT === markers.`
-});
-```
-
-### Phase 2: Parse Agent Results
-
-Extract structured JSON from agent output:
-
-```javascript
-function parseDeslop(output) {
-  const match = output.match(/=== DESLOP_RESULT ===[\s\S]*?({[\s\S]*?})[\s\S]*?=== END_RESULT ===/);
-  return match ? JSON.parse(match[1]) : { fixes: [] };
-}
-
-const findings = parseDeslop(result);
-```
-
-### Phase 3: Handle Mode
-
-#### Report Mode (Default)
-
-Present findings as markdown table:
-
-```markdown
-## Slop Hotspots
-
-| Priority | File | Issue | Certainty | Fix |
-|----------|------|-------|-----------|-----|
-| 1 | src/api.js:42 | console.log | HIGH | auto |
-| 2 | src/auth.js:15 | empty catch | HIGH | auto |
-| 3 | lib/utils.js:88 | excessive comments | MEDIUM | review |
-
-## Summary
-
-- **HIGH certainty**: N (auto-fixable)
-- **MEDIUM certainty**: N (review required)
-- **LOW certainty**: N (flagged only)
-
-## Do Next
-
-- [ ] Run `/deslop apply` to auto-fix HIGH certainty items
-- [ ] Review MEDIUM certainty items manually
-```
-
-#### Apply Mode
-
-If fixes array is non-empty, spawn simple-fixer:
-
-```javascript
-if (mode === 'apply' && findings?.fixes?.length > 0) {
-  await Task({
-    subagent_type: "next-task:simple-fixer",
-    model: "haiku",
-    prompt: `Apply these slop fixes:
-${JSON.stringify(findings.fixes, null, 2)}
-
-For each fix:
-- remove-line: Delete the line at the specified line number
-- add-comment: Add "// Error intentionally ignored" to empty catch
-- remove-block: Delete the entire code block
-
-Use Edit tool to apply. Commit message: "fix: clean up AI slop (auto-applied)"`
-  });
-}
-```
-
-Present results:
-
-```markdown
-## Applied Fixes
-
-| File | Line | Fix |
-|------|------|-----|
-| src/api.js | 42 | remove-line (console.log) |
-| src/auth.js | 15 | add-comment (empty catch) |
-
-**Total**: N fixes applied
-
-## Remaining (manual review needed)
-
-| File | Line | Issue | Certainty |
-|------|------|-------|-----------|
-| lib/utils.js | 88 | excessive comments | MEDIUM |
-```
-
-## Verification Strategy
-
-After fixes are applied, run project's test command:
-
-```bash
-npm test
-# or pytest, cargo test, go test ./...
-```
-
-On failure: `git restore .` and report which change failed.
-
-## Ignore Zones
-
-Skip these paths (handled by detection script):
-- Build artifacts: `dist/`, `build/`, `target/`, `out/`, `.next/`
-- Vendored: `vendor/`, `node_modules/`, `**/*.min.*`
-- Generated: `**/*.gen.*`, lockfiles
-
-## Error Handling
-
-- Git not available: Exit with "Git required for rollback safety"
-- Invalid scope path: Exit with "Path not found: <path>"
-- Verification fails: Rollback with `git restore .`, report failure
-
-## Additional Resources
-
-### Reference Files
-
-For detailed pattern documentation, consult:
-- **`references/slop-categories.md`** - All pattern categories, severity levels, certainty thresholds, auto-fix strategies
-
-### Scripts
-
-- **`scripts/detect.js`** - Detection pipeline CLI (run with `--help` for options)