agentsys 5.0.2 → 5.1.0

package/.claude-plugin/marketplace.json

@@ -1,7 +1,7 @@
 {
   "name": "agentsys",
-  "description": "12 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, and cross-tool AI consultation",
-  "version": "5.0.2",
+  "description": "13 specialized plugins for AI workflow automation - task orchestration, PR workflow, slop detection, code review, drift detection, enhancement analysis, documentation sync, repo mapping, perf investigations, topic research, agent config linting, cross-tool AI consultation, and structured AI debate",
+  "version": "5.1.0",
   "owner": {
     "name": "Avi Fenesh",
     "url": "https://github.com/avifenesh"
@@ -26,84 +26,91 @@
       "name": "next-task",
       "source": "./plugins/next-task",
       "description": "Master workflow orchestrator: autonomous workflow with model optimization (opus/sonnet/haiku), two-file state management, workflow enforcement gates, 14 specialist agents",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "productivity"
     },
     {
       "name": "ship",
       "source": "./plugins/ship",
       "description": "Complete PR workflow: commit to production, skips review when called from next-task, removes task from registry on cleanup, automatic rollback",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "deployment"
     },
     {
       "name": "deslop",
       "source": "./plugins/deslop",
       "description": "3-phase AI slop detection: regex patterns (HIGH), multi-pass analyzers (MEDIUM), CLI tools (LOW)",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "audit-project",
       "source": "./plugins/audit-project",
       "description": "Multi-agent iterative code review until zero issues remain",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "drift-detect",
       "source": "./plugins/drift-detect",
       "description": "Deep repository analysis to realign project plans with code reality - detects drift, gaps, and creates prioritized reconstruction plans",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "productivity"
     },
     {
       "name": "enhance",
       "source": "./plugins/enhance",
       "description": "Master enhancement orchestrator: parallel analyzer execution for plugins, agents, docs, CLAUDE.md, and prompts with unified reporting",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "sync-docs",
       "source": "./plugins/sync-docs",
       "description": "Standalone documentation sync: find outdated refs, update CHANGELOG, flag stale examples based on code changes",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "repo-map",
       "source": "./plugins/repo-map",
       "description": "AST-based repository map generation using ast-grep with incremental updates for faster drift analysis",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "perf",
       "source": "./plugins/perf",
       "description": "Rigorous performance investigation workflow with baselines, profiling, hypotheses, and evidence-backed decisions",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "learn",
       "source": "./plugins/learn",
       "description": "Research topics online and create comprehensive learning guides with RAG-optimized indexes",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "productivity"
     },
     {
       "name": "agnix",
       "source": "./plugins/agnix",
       "description": "Lint agent configuration files (SKILL.md, CLAUDE.md, hooks, MCP) against 155 rules across 10+ AI tools",
-      "version": "5.0.2",
+      "version": "5.1.0",
       "category": "development"
     },
     {
       "name": "consult",
       "source": "./plugins/consult",
       "description": "Cross-tool AI consultation: get second opinions from Gemini CLI, Codex CLI, Claude Code, OpenCode, or Copilot CLI with model and thinking effort control",
-      "version": "5.0.2",
+      "version": "5.1.0",
+      "category": "productivity"
+    },
+    {
+      "name": "debate",
+      "source": "./plugins/debate",
+      "description": "Structured multi-round debate between AI tools with proposer/challenger roles and verdict",
+      "version": "5.1.0",
       "category": "productivity"
     }
   ]

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agentsys",
-  "version": "5.0.2",
+  "version": "5.1.0",
   "description": "Professional-grade slash commands for Claude Code with cross-platform support",
   "keywords": [
     "workflow",

package/AGENTS.md

@@ -76,7 +76,7 @@
 <!-- GEN:START:claude-architecture -->
 ```
 lib/          → Shared library (vendored to plugins)
-plugins/      → 12 plugins, 41 agents (31 file-based + 10 role-based), 27 skills
+plugins/      → 13 plugins, 42 agents (32 file-based + 10 role-based), 28 skills
 adapters/     → Platform adapters (opencode-plugin/, opencode/, codex/)
 checklists/   → Action checklists (9 files)
 bin/cli.js    → npm CLI installer
@@ -87,6 +87,7 @@ bin/cli.js    → npm CLI installer
 | agnix | 1 | 1 | Agent config linting |
 | audit-project | 10 | 0 | Multi-agent code review |
 | consult | 1 | 1 | Cross-tool AI consultation |
+| debate | 1 | 1 | Multi-perspective debate analysis |
 | deslop | 1 | 1 | AI slop cleanup |
 | drift-detect | 1 | 1 | Plan drift detection |
 | enhance | 8 | 9 | Code quality analyzers |

package/CHANGELOG.md

@@ -9,10 +9,33 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [5.1.0] - 2026-02-18
+
+### Added
+
+- **`/debate` plugin** — New plugin for structured multi-round AI dialectic. Pick two tools (e.g. `codex vs gemini`), set 1–5 rounds, and get a proposer/challenger debate with a synthesized verdict. Supports natural language input, effort levels (`--effort=low|high|max`), and context injection (`--context=diff` or `--context=file=PATH`). Available on Claude Code, OpenCode, and Codex CLI.
+- **`/consult` multi-instance support** — Run N parallel consultations with the same tool using `--count=N` (or natural language: "ask 3 gemini about this"). Responses are numbered and a brief synthesis highlights agreements and differences.
+- **`/consult` natural language parsing** — Free-form queries are now parsed automatically without requiring explicit flags. "with codex about my auth approach", "ask gemini thoroughly about this design", or "3 claude opinions on error handling" all work out of the box.
+
+### Changed
+
+- **Agent model optimization** — `exploration-agent` and `learn-agent` switched from opus to sonnet, reducing cost and latency for exploration and research passes with no quality regression.
+
+### Fixed
+
+- **Debate `--context=file` path validation** — Added path containment checks to prevent directory traversal when passing file paths as context.
+- **Debate prompt hardening** — Context passthrough, canonical output redaction, and relaxed disagreement rules applied consistently across all debate rounds.
+- **Consult model/flag issues** — Hardened model flag handling and non-interactive invocation across all four supported tools (Claude, Gemini, Codex, OpenCode).
+
+## [5.0.3] - 2026-02-17
+
+### Fixed
+- **Consult: Codex command corrected to `codex exec`** - Codex CLI uses `codex exec` for non-interactive mode (not `-q` flag). Non-interactive resume uses `codex exec resume SESSION_ID "prompt" --json`. All four tools (Claude, Gemini, Codex, OpenCode) now have correct native session resume support.
+
 ## [5.0.2] - 2026-02-17
 
 ### Fixed
-- **Consult: Codex and OpenCode marked as continuable** - Both tools support session resume but were incorrectly marked as non-continuable. Codex supports `codex resume` (TUI-only; non-interactive uses context prepending). OpenCode supports `--session SESSION_ID` and `--continue` flags in non-interactive mode.
+- **Consult: Codex and OpenCode marked as continuable** - Both tools support session resume but were incorrectly marked as non-continuable. OpenCode supports `--session SESSION_ID` and `--continue` flags in non-interactive mode.
 
 ## [5.0.1] - 2026-02-14
 

package/README.md

@@ -21,7 +21,7 @@
 </p>
 
 <p align="center">
-  <b>12 plugins · 41 agents · 27 skills · 26k lines of lib code · 3,357 tests · 3 platforms</b>
+  <b>13 plugins · 42 agents · 28 skills · 26k lines of lib code · 3,357 tests · 3 platforms</b>
 </p>
 
 <p align="center">
@@ -46,7 +46,7 @@ AI models can write code. That's not the hard part anymore. The hard part is eve
 
 ## What This Is
 
-An agent orchestration system — 12 plugins, 41 agents, and 27 skills that compose into structured pipelines for software development.
+An agent orchestration system — 13 plugins, 42 agents, and 28 skills that compose into structured pipelines for software development.
 
 Each agent has a single responsibility, a specific model assignment, and defined inputs/outputs. Pipelines enforce phase gates so agents can't skip steps. State persists across sessions so work survives interruptions.
 
@@ -91,6 +91,7 @@ This came from testing on 1,000+ repositories.
 | [`/sync-docs`](#sync-docs) | Finds outdated references, stale examples, missing CHANGELOG entries |
 | [`/learn`](#learn) | Research any topic, gather online sources, create learning guide with RAG index |
 | [`/consult`](#consult) | 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. |
+| [`/debate`](#debate) | Structured debate between two AI tools to stress-test ideas. Proposer/Challenger format with a verdict. |
 <!-- GEN:END:readme-commands -->
 
 Each command works standalone. Together, they compose into end-to-end pipelines.
@@ -100,7 +101,7 @@ Each command works standalone. Together, they compose into end-to-end pipelines.
 ## Skills
 
 <!-- GEN:START:readme-skills -->
-27 skills included across the plugins:
+28 skills included across the plugins:
 
 | Category | Skills |
 |----------|--------|
@@ -108,7 +109,7 @@ Each command works standalone. Together, they compose into end-to-end pipelines.
 | **Enhancement** | `enhance:enhance-agent-prompts`, `enhance:enhance-claude-memory`, `enhance:enhance-cross-file`, `enhance:enhance-docs`, `enhance:enhance-hooks`, `enhance:enhance-orchestrator`, `enhance:enhance-plugins`, `enhance:enhance-prompts`, `enhance:enhance-skills` |
 | **Workflow** | `next-task:discover-tasks`, `next-task:orchestrate-review`, `next-task:validate-delivery` |
 | **Cleanup** | `deslop:deslop`, `sync-docs:sync-docs` |
-| **Analysis** | `drift-detect:drift-analysis`, `repo-map:repo-mapping` |
+| **Analysis** | `debate:debate`, `drift-detect:drift-analysis`, `repo-map:repo-mapping` |
 | **Productivity** | `consult:consult` |
 | **Learning** | `learn:learn` |
 | **Linting** | `agnix:agnix` |
@@ -124,7 +125,7 @@ Skills are the reusable implementation units. Agents invoke skills; commands orc
 |---------|--------------|
 | [The Approach](#the-approach) | Why it's built this way |
 | [Commands](#commands) | All 12 commands overview |
-| [Skills](#skills) | 27 skills across plugins |
+| [Skills](#skills) | 28 skills across plugins |
 | [Command Details](#command-details) | Deep dive into each command |
 | [How Commands Work Together](#how-commands-work-together) | Standalone vs integrated |
 | [Design Philosophy](#design-philosophy) | The thinking behind the architecture |
@@ -650,7 +651,7 @@ agent-knowledge/
 | Tool | Default Model (high) | Reasoning Control |
 |------|---------------------|-------------------|
 | Claude | opus | max-turns |
-| Gemini | gemini-3-pro-preview | built-in |
+| Gemini | gemini-3-pro | built-in |
 | Codex | gpt-5.3-codex | model_reasoning_effort |
 | OpenCode | github-copilot/claude-opus-4-6 | --variant |
 | Copilot | (default) | none |

package/adapters/codex/skills/agnix/SKILL.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: agnix
 description: "Use when user asks to \"lint agent configs\", \"validate skills\", \"check CLAUDE.md\", \"validate hooks\", \"lint MCP\". Validates agent configuration files against 155 rules across 10+ AI tools."

package/adapters/codex/skills/audit-project/SKILL.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: audit-project
 description: "Use when user asks to \"review my code\", \"check for issues\", \"run code review\", \"analyze PR quality\". Multi-agent iterative review that loops until all critical/high issues are resolved."

package/adapters/codex/skills/audit-project-agents/SKILL.md

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

package/adapters/codex/skills/audit-project-github/SKILL.md

@@ -1,4 +1,3 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: audit-project-github
 description: "Create GitHub issues for non-security deferred findings identified by /audit-project."

package/adapters/codex/skills/consult/SKILL.md

@@ -1,59 +1,85 @@
-<!-- AUTO-GENERATED by scripts/gen-adapters.js - DO NOT EDIT -->
 ---
 name: consult
-description: "Use when user asks to \"consult gemini\", \"ask codex\", \"get second opinion\", \"cross-check with claude\", \"consult another AI\", \"ask opencode\", \"copilot opinion\". Queries another AI CLI tool and returns the response."
+description: "Use when user asks to \"consult gemini\", \"ask codex\", \"get second opinion\", \"cross-check with claude\", \"consult another AI\", \"ask opencode\", \"copilot opinion\", \"ask 3 codex\", \"multi-consult\". Queries another AI CLI tool and returns the response."
 ---
 
 # /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.
+You are executing the /consult command. Your job is to parse the user's request (natural language or flags), resolve missing parameters interactively, and execute the consultation.
 
 ## 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 use safe-mode defaults (`--allowedTools "Read,Glob,Grep"` for Claude, `-c model_reasoning_effort` for Codex)
 - MUST enforce 120s timeout on all tool executions
-- MUST validate `--tool` against allow-list: gemini, codex, claude, opencode, copilot (reject all others)
+- MUST validate tool names 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
+## Execution
 
-Parse from $ARGUMENTS:
+### Phase 1: Parse Input (Flags + Natural Language)
 
-- **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
+Parse `$ARGUMENTS` using both explicit flags and natural language extraction. Flags always take priority over NLP when both provide the same parameter.
 
-## Execution
+#### Step 1a: Extract explicit flags
+
+Look for and remove these flags from `$ARGUMENTS`:
+
+1. `--tool=VALUE` or `--tool VALUE` where VALUE is one of: gemini, codex, claude, opencode, copilot
+2. `--effort=VALUE` or `--effort VALUE` where VALUE is one of: low, medium, high, max
+3. `--model=VALUE` or `--model VALUE` (any string, including quoted)
+4. `--context=VALUE` where VALUE is: diff, file=PATH, or none
+5. `--continue` (optionally `--continue=SESSION_ID`)
+6. `--count=N` where N is 1-5
+
+Remove all matched flags and their values from `$ARGUMENTS`.
+
+#### Step 1b: Natural language extraction (on remaining text)
+
+After removing flags, parse the remaining text for these patterns:
 
-### Phase 1: Parse Arguments
+**Tool extraction** (case-insensitive):
+- "with {tool}" (e.g., "with codex") -> tool
+- "ask {tool}" (e.g., "ask gemini") -> tool
+- "consult {tool}" -> tool
+- "{tool} about" (e.g., "codex about") -> tool
+- Tool names: claude, gemini, codex, opencode, copilot
 
-Extract these values from `$ARGUMENTS`:
+**Count extraction**:
+- "ask {N} {tool}" (e.g., "ask 3 codex") -> count=N, tool
+- "{N} {tool}" (e.g., "3 codex") -> count=N, tool
+- "{N} instances" -> count=N
+- "few instances" / "multiple" / "several" -> count=ambiguous (ask user in Phase 2)
 
-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**.
+**Count validation**: After extracting count (from flags or NLP), validate: 1 <= count <= 5. If count < 1 or count > 5, show `[ERROR] Instance count must be 1-5. Got: {count}` and stop.
 
-If no question text and no `--continue` flag found, show:
+**Effort extraction**:
+- "quick" / "fast" / "brief" -> effort=low
+- "thorough" / "deep" / "carefully" / "detailed" -> effort=high
+- "maximum" / "max effort" / "exhaustive" -> effort=max
+
+**Question extraction**:
+- Text after "about" is the question (e.g., "with codex about my auth approach" -> question="my auth approach")
+- If no "about" pattern, everything remaining after removing tool/count/effort markers is the question
+
+**Precedence rule**: Flags from Step 1a always override NLP from Step 1b.
+
+If no question text and no `--continue` flag found after both steps:
 ```
-[ERROR] Usage: /consult "your question" [--tool=gemini|codex|claude|opencode|copilot] [--effort=low|medium|high|max]
+[ERROR] Usage: /consult "your question" or /consult with gemini about your question
 ```
 
-### Phase 2: Interactive Parameter Selection
+### Phase 2: Interactive Parameter Resolution
 
-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.
+MUST resolve ALL missing parameters interactively. ONLY skip this phase if ALL required params (tool, effort, model) are resolved AND either a question exists or --continue is present. Do NOT silently default any parameter.
 
 #### Step 2a: Handle --continue
 
+**Note:** `--continue` and `--count > 1` are mutually exclusive. Session resume applies to a single tool session. If both are present, show `[ERROR] Cannot use --continue with --count > 1. Use --continue for single session resume.` and stop.
+
 If `--continue` is present:
 1. Read the session file at `{AI_STATE_DIR}/consult/last-session.json`
 
@@ -64,9 +90,9 @@ If `--continue` is present:
 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)
+#### Step 2b: Detect installed tools
 
-First, detect which tools are installed by running all 5 checks **in parallel** via Bash:
+Run 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)
@@ -75,13 +101,15 @@ 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 request_user_input call to ask all missing parameters at once. Include only the questions for parameters NOT already provided in $ARGUMENTS:
+#### Step 2c: Batch selection for missing params
+
+Use a SINGLE request_user_input call to ask all missing parameters at once. Include ONLY questions for parameters NOT already resolved from Phase 1:
 
 ```
 request_user_input:
 > **Codex**: Each question MUST include a unique `id` field (e.g., `id: "q1"`).
   questions:
-    - header: "AI Tool"                          # SKIP if --tool provided
+    - header: "AI Tool"                          # SKIP if tool resolved
       question: "Which AI tool should I consult?"
       options (only if installed):
         - label: "Claude"       description: "Deep code reasoning"
@@ -90,23 +118,35 @@ request_user_input:
         - label: "OpenCode"     description: "Flexible model choice"
         - label: "Copilot"      description: "GitHub-integrated AI"
 
-    - header: "Effort"                           # SKIP if --effort provided
+    - header: "Effort"                           # SKIP if effort resolved
       question: "What thinking effort level?"
       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"
+
+    - header: "Instances"                        # SKIP if count resolved or not hinted
+      question: "How many parallel consultations?"
+      options:
+        - label: "1 (Single)"             description: "Standard single consultation"
+        - label: "2 (Compare)"            description: "Two responses to compare"
+        - label: "3 (Panel)"              description: "Three perspectives"
+        - label: "5 (Full spread)"        description: "Five diverse perspectives"
 ```
 
-Map tool choice to lowercase: "Claude" -> "claude", "Codex" -> "codex", etc.
-Map effort choice: "Medium (Recommended)" -> "medium", "Low" -> "low", "High" -> "high", "Max" -> "max".
+ONLY show the Instances question if:
+- The user explicitly mentioned multiple instances (e.g., "few", "multiple", "several")
+- The count was set but ambiguous
+Do NOT show Instances question for simple single-tool requests. Default count=1 silently when no multi-instance intent detected.
 
-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.
+Map tool choice to lowercase: "Claude" -> "claude", "Codex" -> "codex", etc.
+Map effort choice: "Medium (Recommended)" -> "medium", "Low" -> "low", etc.
+Map count choice: "1 (Single)" -> 1, "2 (Compare)" -> 2, "3 (Panel)" -> 3.
 
-#### Step 2c: Model Selection (MUST ask if no --model)
+#### Step 2d: 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.
+After tool is resolved, 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:**
 ```
@@ -146,7 +186,7 @@ request_user_input:
         - 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"
+        - label: "gpt-5.3-codex-spark"   description: "Cost-effective, 4x more usage"
 ```
 
 **For OpenCode:**
@@ -173,17 +213,21 @@ request_user_input:
       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: "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`.
+Map the user's choice to the model string (strip " (Recommended)" suffix if present).
 
-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.
+IMPORTANT: Do NOT skip model selection. Do NOT silently use a default model. If --model was not explicitly provided, you MUST present this picker.
 
-### Phase 3: Invoke Consult Skill
+### Phase 3: Execute Consultation
 
-With all parameters resolved (tool, effort, model, question, and optionally context, continue), invoke the `consult` skill using the Skill tool:
+With all parameters resolved (tool, effort, model, question, count, and optionally context/continue):
+
+#### Single instance (count=1, the default)
+
+Invoke the `consult` skill directly using the Skill tool:
 
 ```
 Skill: consult
@@ -192,15 +236,35 @@ Args: "[question]" --tool=[tool] --effort=[effort] --model=[model] [--context=[c
 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.
+The skill handles the full consultation lifecycle: model resolution, command building, context packaging, execution with 120s timeout, and returns a plain JSON result.
+
+#### Multi-instance (count > 1)
 
-### Phase 4: Parse Skill Output
+Spawn the `consult:consult-agent` via the Task tool with all resolved parameters:
 
-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.
+```
+Task:
+  subagent_type: "consult:consult-agent"
+  prompt: |
+    Execute a multi-instance consultation with these pre-resolved parameters:
+    - tool: [tool]
+    - model: [model]
+    - effort: [effort]
+    - question: [question]
+    - count: [count]
+    - context: [context or none]
+
+    Run [count] parallel consultations with the same tool and parameters.
+    Return all responses formatted with numbered headers and a brief synthesis.
+```
+
+The agent handles parallel execution, temp file management, result parsing, and synthesis.
 
-### Phase 5: Present Results
+### Phase 4: Present Results
 
-After parsing the JSON, format and display the result as human-friendly text:
+#### Single instance
+
+Parse the skill's plain JSON output and display:
 
 ```
 Tool: {tool}, Model: {model}, Effort: {effort}, Duration: {duration_ms}ms.
@@ -209,15 +273,13 @@ The results of the consultation are:
 {response}
 ```
 
-For continuable tools with a session_id (Claude, Gemini, OpenCode), display: `Session: {session_id} - use /consult --continue to resume`
-For Codex (context-based continuation, no session_id), display: `Use /consult --continue to continue this conversation (prior context will be prepended)`
+For continuable tools (Claude, Gemini, Codex, OpenCode), display: `Session: {session_id} - use /consult --continue to resume`
+
+Save session state to `{AI_STATE_DIR}/consult/last-session.json`.
 
-Save session state for continuable tools (Claude, Gemini, Codex, OpenCode) to `{AI_STATE_DIR}/consult/last-session.json`.
+#### Multi-instance
 
-Platform state directory:
-- Claude Code: `.claude/`
-- OpenCode: `.opencode/`
-- Codex CLI: `.codex/`
+Display the agent's formatted output directly. The agent returns numbered responses with a synthesis section.
 
 On failure: `[ERROR] Consultation Failed: {specific error message}`
 
@@ -225,22 +287,34 @@ On failure: `[ERROR] Consultation Failed: {specific error message}`
 
 | Error | Output |
 |-------|--------|
-| No question provided | `[ERROR] Usage: /consult "your question" [--tool=gemini\|codex\|claude\|opencode\|copilot] [--effort=low\|medium\|high\|max]` |
+| No question provided | `[ERROR] Usage: /consult "your question" or /consult with gemini about your question` |
 | 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)` |
+| Count out of range | `[ERROR] Instance count must be 1-5. Got: {count}` |
+| Multi-instance partial failure | Show successful responses, note failures |
 
 ## 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
+# Natural language (NLP parsing)
+/consult with codex about my auth approach
+/consult ask 3 codex about this design
+/consult gemini should I use redis or postgres
+/consult thoroughly ask claude about error handling
+/consult codex few instances about performance
+
+# Explicit flags (backward compatible)
+/consult "Is this the right approach?" --tool=gemini --effort=high
+/consult "Review this function" --tool=codex --count=3
 /consult "Suggest improvements" --tool=opencode --model=github-copilot/claude-opus-4-6
-/consult "Continue from where we left off" --continue
+/consult --continue
 /consult "Explain this error" --context=diff --tool=gemini
 /consult "Review this file" --context=file=src/index.js --tool=claude
+
+# Mixed (flags + natural language)
+/consult with gemini --effort=max about database schema design
 ```