opencode-multiagent 0.3.0-next.1 → 0.5.0

package/commands/brainstorm.md

@@ -0,0 +1,14 @@
+---
+description: Start a brainstorming session to explore an idea before planning
+agent: brainstormer
+---
+
+Start a brainstorming session about: $ARGUMENTS
+
+Requirements:
+
+- explore the idea from multiple angles before converging on a direction
+- inspect the current repository reality to ground the discussion
+- challenge assumptions and surface alternatives the user may not have considered
+- identify gaps and open questions early
+- do not rush to a conclusion — the user decides when to wrap up with `/brainstorm:conclude`

package/commands/execute.md

@@ -1,7 +1,7 @@
 ---
-description: Lead the request through bounded execution
-agent: lead
-model: anthropic/claude-opus-4-6
+description: Execute a plan or bounded task end to end
+agent: executor
+model: anthropic/claude-sonnet-4-6
 ---
 
 Own this execution request end to end: $ARGUMENTS
@@ -9,7 +9,8 @@ Own this execution request end to end: $ARGUMENTS
 Requirements:
 
 - if `$ARGUMENTS` points to a `.magent/plans/*.md` file, treat that as the source of truth
-- if the request is too ambiguous for safe execution, use `critic` and `planner` before routing to `executor`
-- keep the execution brief concise and only include the context `executor` actually needs
-- initialize or update `.magent/exec/<slug>/task.md` through `scribe` when execution begins
-- let `executor` own worker routing, tiered validation, and the internal QA loop
+- if the request is too ambiguous for safe execution, hand to `planner` first
+- keep the execution brief concise and only include the context coders actually need
+- initialize or update `.magent/exec/<slug>/task.md`, `learn.md`, and `error.md` through `docmaster` when execution begins
+- before dispatching work, call `task_list` to check existing board state and avoid duplicate task creation
+- route to the right coder: `coder` (standard), `ui-coder` (UI/UX), `sec-coder` (security-sensitive)

package/commands/init-deep.md

@@ -1,10 +1,10 @@
 ---
-description: Lead a deep repo initialization pass through critic inspection mode
-agent: lead
+description: Deep repo initialization pass
+agent: planner
 model: anthropic/claude-opus-4-6
 ---
 
-Own this initialization request and use `critic` in inspection mode to perform a deep repository initialization pass.
+Perform a deep repository initialization pass using Tier 3 inspection mode.
 
 User focus or extra constraints:
 
@@ -12,8 +12,8 @@ $ARGUMENTS
 
 Requirements:
 
-- walk all major top-level directories and identify their purpose, build surface, and distinct conventions when they materially affect agent guidance
+- walk all major top-level directories and identify their purpose, build surface, and distinct conventions
 - inspect root and directory-scoped `AGENTS.md` or `AGENT.md` files if they exist
 - decide whether one root `AGENTS.md` is enough or whether additional directory-scoped guidance is warranted
-- if updates are needed, delegate each exact write to `scribe`
-- stay in inspection mode and do not emit a planner or executor handoff block
+- if updates are needed, delegate each exact write to `docmaster`
+- stay in inspection mode and do not emit an execution handoff

package/commands/init.md

@@ -1,10 +1,10 @@
 ---
-description: Lead a bounded repo initialization pass through critic inspection mode
-agent: lead
+description: Bounded repo initialization pass
+agent: planner
 model: anthropic/claude-opus-4-6
 ---
 
-Own this initialization request and use `critic` in inspection mode to perform a bounded repository initialization pass.
+Perform a bounded repository initialization pass using Tier 3 inspection mode.
 
 User focus or extra constraints:
 
@@ -14,6 +14,5 @@ Requirements:
 
 - inspect root-level repository signals first: `AGENTS.md`, `AGENT.md`, obvious rule files, workflow docs, and the build or test surface
 - keep the pass bounded and fast; do not exhaustively scan the full tree
-- if `AGENTS.md` is missing or clearly outdated, delegate the exact write to `scribe`
+- if `AGENTS.md` is missing or clearly outdated, delegate the exact write to `docmaster`
 - if the existing guidance is already accurate, say so clearly and stop
-- do not emit a planner or executor handoff block

package/commands/inspect.md

@@ -1,14 +1,14 @@
 ---
-description: Lead a repository inspection request through critic inspection mode
-agent: lead
+description: Inspect repository state, conventions, and workflow configuration
+agent: planner
 model: anthropic/claude-opus-4-6
 ---
 
-Own this inspection request and use `critic` in inspection mode for: $ARGUMENTS
+Inspect this repository using Tier 3 inspection mode for: $ARGUMENTS
 
 Requirements:
 
 - inspect `AGENTS.md`, `AGENT.md`, rule files, command files, plan artifacts, and operational conventions
-- stay in inspection mode; do not return a planner or executor handoff unless I explicitly ask for routing
-- if durable docs or repo memory should be updated, delegate the exact write to `scribe`
+- stay in inspection mode; do not return an execution handoff unless I explicitly ask for routing
+- if durable docs or repo memory should be updated, delegate the exact write to `docmaster`
 - reply with the inspection-mode output contract

package/commands/plan.md

@@ -1,6 +1,6 @@
 ---
-description: Lead the request into a durable implementation plan
-agent: lead
+description: Create or update a durable implementation plan
+agent: planner
 model: anthropic/claude-opus-4-6
 ---
 
@@ -9,8 +9,9 @@ Own this request and create or update a durable implementation plan for: $ARGUME
 Requirements:
 
 - inspect the current repository reality first
-- use `planner` for the actual durable plan work unless the request is obviously only inspection
-- keep the planning brief concise and task-shaped instead of dumping broad repository context
-- persist the result under `.magent/plans/<slug>.md` through `scribe` unless I explicitly asked for a dry run
-- identify verification gates, risks, affected files, and likely worker routing hints for `executor`
+- use `auditor` to pressure-test the direction before finalizing
+- keep the planning brief concise and task-shaped
+- persist the result under `.magent/plans/<slug>.md` through `docmaster` unless I explicitly asked for a dry run
+- identify verification gates, risks, affected files, and likely coder routing hints for `executor`
 - if a matching plan already exists, reuse and refine it instead of inventing a second parallel plan
+- when the plan has 3 or more execution phases, seed the task board with `task_create` entries — one per phase

package/commands/quality.md

@@ -1,7 +1,7 @@
 ---
-description: Run bounded verification with validator
-agent: validator
-model: openai/gpt-5.3-codex
+description: Run bounded verification and quality checks
+agent: reviewer
+model: anthropic/claude-sonnet-4-6
 subtask: true
 ---
 

package/commands/review.md

@@ -1,7 +1,7 @@
 ---
-description: Run a bounded local code review with reviewer
+description: Run a bounded local code review
 agent: reviewer
-model: github-copilot/grok-code-fast-1
+model: anthropic/claude-sonnet-4-6
 subtask: true
 ---
 
@@ -9,7 +9,8 @@ Review this bounded local scope: $ARGUMENTS
 
 Rules:
 
-- keep the review at 1-3 files or one small diff slice
+- keep the review at 1-5 files or one small diff slice
 - report only material issues
 - cite local evidence
+- run verification commands when appropriate
 - if the scope is too broad, say it must be split

package/commands/status.md

@@ -1,10 +1,10 @@
 ---
-description: Lead a .magent status inspection request through critic inspection mode
-agent: lead
+description: Inspect .magent execution state and repository workflow status
+agent: planner
 model: anthropic/claude-opus-4-6
 ---
 
-Own this status request and use `critic` in inspection mode to inspect the current repository execution state.
+Inspect the current repository execution state using Tier 3 inspection mode.
 
 Focus on:
 
@@ -12,5 +12,6 @@ Focus on:
 - `.magent/exec/**`
 - active or stale execution artifacts
 - the next best action if the repository already contains plan history
+- `.magent/board.json` — query live task board with `task_list` and include active/pending/blocked tasks
 
 If `.magent` does not exist, say so clearly and summarize what durable state is currently missing.

package/defaults/AGENTS.md

@@ -0,0 +1,48 @@
+# defaults/
+
+Unified plugin configuration defaults and JSON Schema. These two files must always stay in sync.
+
+## Files
+
+- `opencode-multiagent.json` — runtime default values
+- `opencode-multiagent.schema.json` — JSON Schema for validation
+
+## Validation
+
+Run `mise run validate-config` after any change. This uses a **hand-rolled validator** in `scripts/schema-lib.ts` — not `ajv` or any standard JSON Schema library. Do not introduce external schema validation dependencies.
+
+## Schema Structure
+
+The schema enforces `additionalProperties: false` throughout. Adding a new field requires updating both the schema and the defaults file.
+
+Four top-level required sections:
+
+| Section         | Purpose                                                         |
+| --------------- | --------------------------------------------------------------- |
+| `flags`         | Runtime feature flags and configuration                         |
+| `agentSettings` | Per-agent model, temperature, and step overrides                |
+| `mcpDefaults`   | MCP server definitions injected when missing from active config |
+| `profiles`      | Named flag bundles (`minimal`, `standard`, `strict`)            |
+
+## Profile Merge Order
+
+At runtime, flags are resolved in this order (later wins):
+
+1. `defaultFlags` (hardcoded in `constants.ts`)
+2. Profile values (from `profiles[selectedProfile]`)
+3. User flags (from user's `opencode-multiagent.json` in `~/.config/opencode/plugins/`)
+
+## agentSettings
+
+Each entry requires at minimum a `model` field (`provider/model` format). Optional: `temperature` (0–2), `steps` (minimum 1). Every agent in `agents/*.md` must have a corresponding entry here.
+
+## mcpDefaults
+
+MCP server definitions are injected **conservatively** — only when the key is absent from the user's active OpenCode config. They are never overwritten.
+
+## Key Constraints
+
+- **Always run `mise run validate-config` after changes.** The build task depends on it.
+- **Do not use `ajv` or standard JSON Schema validators.** The hand-rolled validator in `scripts/schema-lib.ts` has intentional limitations.
+- **`additionalProperties: false` is enforced everywhere.** Unknown fields will fail validation.
+- **Keep defaults and schema in sync.** A field in one must exist in the other.

package/defaults/opencode-multiagent.json

@@ -1,135 +1,54 @@
 {
-  "flags": {
-    "profile": "standard",
-    "enforcement": true,
-    "observation": true,
-    "prompt_controls": true,
-    "agent_compilation": true,
-    "command_compilation": true,
-    "mcp_compilation": true,
-    "telemetry": true,
-    "supervision": true,
-    "quality_gate": true,
-    "skill_sources": ["${plugin_root}/skills", "${home}/.agents/skills", "${home}/skills"],
-    "skill_injection": false,
-    "compiler": {
-      "permission_compilation": true
-    },
-    "experimental": {
-      "chat_system_transform": false,
-      "chat_messages_transform": false,
-      "session_compacting": false,
-      "text_complete": false
-    },
-    "supervision_config": {
-      "idle_timeout_ms": 180000,
-      "cooldown_ms": 300000
-    },
-    "quality_config": {
-      "reminder_idle_ms": 120000,
-      "reminder_cooldown_ms": 300000
-    }
-  },
   "agentSettings": {
-    "lead": {
-      "model": "anthropic/claude-opus-4-6",
-      "temperature": 0,
-      "steps": 500
-    },
-    "critic": {
-      "model": "openai/gpt-5.4",
-      "temperature": 0,
-      "steps": 200
-    },
     "planner": {
       "model": "anthropic/claude-opus-4-6",
       "temperature": 0,
-      "steps": 100
+      "steps": 200
     },
     "executor": {
       "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
       "steps": 200
     },
-    "scout": {
+    "coder": {
       "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
-      "steps": 24
-    },
-    "worker": {
-      "model": "openai/gpt-5.3-codex",
-      "temperature": 0,
-      "steps": 30
+      "steps": 40
     },
-    "heavy-worker": {
-      "model": "openai/gpt-5.4",
+    "ui-coder": {
+      "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
       "steps": 40
     },
-    "deep-worker": {
+    "sec-coder": {
       "model": "anthropic/claude-opus-4-6",
       "temperature": 0,
       "steps": 60
     },
-    "ui-worker": {
-      "model": "anthropic/claude-opus-4-6",
-      "temperature": 0,
-      "steps": 30
-    },
-    "ui-heavy-worker": {
-      "model": "anthropic/claude-opus-4-6",
-      "temperature": 0,
-      "steps": 40
-    },
-    "quick": {
-      "model": "opencode-go/minimax-m2.5",
-      "temperature": 0,
-      "steps": 16
-    },
     "reviewer": {
-      "model": "github-copilot/grok-code-fast-1",
-      "temperature": 0,
-      "steps": 24
-    },
-    "validator": {
-      "model": "openai/gpt-5.3-codex",
-      "temperature": 0,
-      "steps": 24
-    },
-    "qa": {
-      "model": "openai/gpt-5.4",
-      "temperature": 0,
-      "steps": 24
-    },
-    "advisor": {
-      "model": "openai/gpt-5.4",
+      "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
-      "steps": 20
+      "steps": 30
     },
     "auditor": {
-      "model": "openai/gpt-5.4",
-      "temperature": 0,
-      "steps": 24
-    },
-    "strategist": {
       "model": "anthropic/claude-opus-4-6",
       "temperature": 0,
-      "steps": 20
+      "steps": 40
     },
-    "devil": {
+    "scout": {
       "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
-      "steps": 8
+      "steps": 30
     },
-    "scribe": {
+    "docmaster": {
       "model": "anthropic/claude-sonnet-4-6",
       "temperature": 0,
       "steps": 30
     },
-    "librarian": {
-      "model": "anthropic/claude-sonnet-4-6",
-      "temperature": 0,
-      "steps": 24
+    "brainstormer": {
+      "model": "anthropic/claude-opus-4-6",
+      "temperature": 0.3,
+      "steps": 200
     }
   },
   "mcpDefaults": {
@@ -166,58 +85,5 @@
       },
       "enabled": false
     }
-  },
-  "profiles": {
-    "minimal": {
-      "enforcement": true,
-      "observation": false,
-      "prompt_controls": false,
-      "agent_compilation": true,
-      "command_compilation": true,
-      "mcp_compilation": true,
-      "telemetry": false,
-      "supervision": false,
-      "quality_gate": false,
-      "experimental": {
-        "chat_system_transform": false,
-        "chat_messages_transform": false,
-        "session_compacting": false,
-        "text_complete": false
-      }
-    },
-    "standard": {
-      "enforcement": true,
-      "observation": true,
-      "prompt_controls": true,
-      "agent_compilation": true,
-      "command_compilation": true,
-      "mcp_compilation": true,
-      "telemetry": true,
-      "supervision": true,
-      "quality_gate": true,
-      "experimental": {
-        "chat_system_transform": false,
-        "chat_messages_transform": false,
-        "session_compacting": false,
-        "text_complete": false
-      }
-    },
-    "strict": {
-      "enforcement": true,
-      "observation": true,
-      "prompt_controls": true,
-      "agent_compilation": true,
-      "command_compilation": true,
-      "mcp_compilation": true,
-      "telemetry": true,
-      "supervision": true,
-      "quality_gate": true,
-      "experimental": {
-        "chat_system_transform": true,
-        "chat_messages_transform": true,
-        "session_compacting": true,
-        "text_complete": true
-      }
-    }
   }
 }