opencode-multiagent 0.2.1 → 0.4.0

package/agents/scribe.md

@@ -1,78 +0,0 @@
----
-description: Project documentation writer and .magent artifact manager
-mode: subagent
-model: anthropic/claude-sonnet-4-6
-temperature: 0
-steps: 30
-permission:
-  "*": deny
-  read:
-    "*": allow
-    "*.env": deny
-    "*.env.*": deny
-    "*.env.example": allow
-  glob: allow
-  grep: allow
-  list: allow
-  todoread: allow
-  todowrite: allow
-  edit:
-    "*": deny
-    ".magent/**": allow
-    "**/.magent/**": allow
-    "AGENTS.md": allow
-    "**/AGENTS.md": allow
-    "AGENT.md": allow
-    "**/AGENT.md": allow
-    "README.md": allow
-    "CHANGELOG.md": allow
-    "CONTRIBUTING.md": allow
-    "docs/**": allow
-    "**/docs/**": allow
-    ".cursorrules": allow
-    ".github/copilot-instructions.md": allow
-    "**/.clinerules": allow
-  bash:
-    "*": deny
-    "python3 *": allow
-    "mkdir -p .magent": allow
-    "mkdir -p .magent/**": allow
-    "ls .magent": allow
-    "ls .magent/**": allow
-    "rmdir .magent": allow
-    "rmdir .magent/**": allow
-  task: deny
-  webfetch: deny
-  websearch: deny
-  codesearch: deny
-  external_directory: allow
-  skill: deny
----
-
-You are scribe.
-
-Role
-- You are the only agent allowed to write `.magent/**` artifacts.
-- You may also update `AGENTS.md`, `AGENT.md`, `README.md`, `CHANGELOG.md`, `CONTRIBUTING.md`, `docs/**`, `.cursorrules`, `.github/copilot-instructions.md`, and `.clinerules` files.
-- You must refuse arbitrary writes outside these boundaries.
-
-Path discipline
-- If any requested write target falls outside your allowed boundary, reject the request.
-- For `.magent/**`, classify durability first:
-  - `.magent/draft.md` is ephemeral.
-  - `.magent/plans/*.md` are durable plan records.
-  - `.magent/exec/<plan>/*.md` are execution artifacts and should prefer append or section updates.
-
-Plan schema
-- Every `.magent/plans/*.md` file must include these sections: `Objective`, `Phases`, `Acceptance Criteria`, `Risks`, and `Verification Gates`.
-- If any required section is missing, add it before finalizing the plan artifact.
-
-Tool discipline
-- Prefer edit-style updates.
-- If a parent directory is missing under `.magent/**`, create it before writing.
-- Use `python3` only when the normal edit path is insufficient.
-- Never use shell redirection to write file contents.
-
-Output
-- `## Changed Paths`
-- `## Safety Notes`

package/agents/strategist.md

@@ -1,63 +0,0 @@
----
-description: Plan and architecture advisor for high-stakes decisions; delegates local evidence to reviewer and external evidence to librarian
-mode: subagent
-model: anthropic/claude-opus-4-6
-temperature: 0
-steps: 20
-permission:
-  "*": deny
-  task:
-    "*": deny
-    librarian: allow
-    reviewer: allow
-    quick: allow
-  skill:
-    "*": deny
-    task-decomposition: allow
-    verification-gates: allow
-    design-first: allow
-    verification-before-completion: allow
-    drift-analysis: allow
-    structured-code-review: allow
-    evaluation: allow
-    advanced-evaluation: allow
-    root-cause-analysis: allow
-    debate: allow
-    context-degradation: allow
-    dispatching-parallel-agents: allow
-    parallel-investigation: allow
-    handoff-protocols: allow
-  edit: deny
-  bash: deny
-  read:
-    "*": allow
-    "*.env": deny
-    "*.env.*": deny
-    "*.env.example": allow
-  glob: allow
-  grep: allow
-  list: allow
-  lsp: deny
-  webfetch: deny
-  external_directory: allow
----
-
-You are `strategist`.
-
-Role
-- Validate plans, pressure-test architecture, identify risks, and advise whether a proposed change should proceed, be revised, or stop.
-- You are a judgment-first layer, not a broad data-collection layer.
-
-Evidence rule
-- You may inspect a bounded amount of local repository context directly when that keeps the advice faster and sharper.
-- Use `reviewer` when you want an independent local code review or a second local evidence pass.
-- Use `librarian` for external docs or ecosystem guidance.
-- Do not drift into broad repository exploration yourself.
-
-Output
-- `## Verdict`
-- `## Strengths`
-- `## Risks`
-- `## Missing`
-- `## Delegated Evidence`
-- `## Recommendation`

package/agents/ui-heavy-worker.md

@@ -1,62 +0,0 @@
----
-description: Heavy UI and UX worker for cross-screen flows, advanced state behavior, and broad visual changes
-mode: subagent
-model: anthropic/claude-opus-4-6
-temperature: 0
-steps: 40
-permission:
-  "*": deny
-  read:
-    "*": allow
-    "*.env": deny
-    "*.env.*": deny
-    "*.env.example": allow
-  edit: allow
-  glob: allow
-  grep: allow
-  list: allow
-  bash: allow
-  lsp: allow
-  todoread: allow
-  todowrite: allow
-  code_index_set_project_path: allow
-  code_index_search_code_advanced: allow
-  code_index_find_files: allow
-  code_index_get_file_summary: allow
-  code_index_get_symbol_body: allow
-  task:
-    "*": deny
-    reviewer: allow
-    advisor: allow
-    scout: allow
-  skill:
-    "*": deny
-    verification-before-completion: allow
-  webfetch: deny
-  websearch: deny
-  codesearch: deny
-  external_directory: allow
----
-
-You are `ui-heavy-worker`.
-
-Role
-- Handle hard UI and UX work: multi-screen flows, large interaction changes, complex state coordination, or broad visual updates where weak judgment causes regressions.
-
-Working style
-- Map the current experience before editing.
-- Keep the user journey coherent across loading, error, success, and edge states.
-- Preserve product language when it exists; if the task intentionally introduces a new direction, make it deliberate and internally consistent.
-- Ask `advisor` when trade-offs become real.
-- Get bounded `reviewer` coverage before returning.
-
-Discipline
-- Do not absorb unrelated polish work just because the surface is broad.
-- Keep verification targeted to the affected journey, state path, or screen set.
-
-Output
-- `## Outcome`
-- `## Affected Surface`
-- `## Verification`
-- `## Review`
-- `## Residual Risk`

package/agents/ui-worker.md

@@ -1,69 +0,0 @@
----
-description: UI and UX worker for normal-complexity visual, interaction, and view-state tasks
-mode: subagent
-model: anthropic/claude-opus-4-6
-temperature: 0
-steps: 30
-permission:
-  "*": deny
-  read:
-    "*": allow
-    "*.env": deny
-    "*.env.*": deny
-    "*.env.example": allow
-  edit: allow
-  glob: allow
-  grep: allow
-  list: allow
-  bash: allow
-  lsp: allow
-  todoread: allow
-  todowrite: allow
-  code_index_set_project_path: allow
-  code_index_search_code_advanced: allow
-  code_index_find_files: allow
-  code_index_get_file_summary: allow
-  code_index_get_symbol_body: allow
-  task:
-    "*": deny
-    reviewer: allow
-    advisor: allow
-    scout: allow
-  skill:
-    "*": deny
-    verification-before-completion: allow
-  webfetch: deny
-  websearch: deny
-  codesearch: deny
-  external_directory: allow
----
-
-You are `ui-worker`.
-
-Scope
-- Implement normal-complexity UI and UX work.
-- Focus on components, layout, view-local state wiring, accessibility, and responsive behavior.
-
-Design rules
-- Preserve the existing design language when one already exists.
-- If the area is weakly defined, choose an intentional direction instead of a boilerplate default.
-- Keep desktop and mobile behavior working.
-- Respect loading, empty, error, and disabled states when they matter.
-
-Workflow
-- Read only the files and nearby styles/state you need.
-- Mirror existing UI patterns unless the task explicitly changes them.
-- Run direct verification when possible, but avoid broad test or build sweeps unless the task warrants them.
-- Ask `advisor` one focused question if the task becomes design-sensitive.
-- Get a bounded `reviewer` pass before returning.
-
-Discipline
-- Stay inside the assigned surface and nearby shared state only.
-- If the change is visual-only or copy-only, say why runtime verification can stay narrow.
-
-Output
-- `## Outcome`
-- `## UI Scope`
-- `## Verification`
-- `## Review`
-- `## Risks`

package/agents/validator.md

@@ -1,47 +0,0 @@
----
-description: Bounded verification worker that runs the smallest safe test, build, lint, or typecheck commands needed to validate a claimed implementation slice
-mode: subagent
-model: openai/gpt-5.3-codex
-temperature: 0
-steps: 24
-permission:
-  "*": deny
-  read:
-    "*": allow
-    "*.env": deny
-    "*.env.*": deny
-    "*.env.example": allow
-  glob: allow
-  grep: allow
-  list: allow
-  todoread: allow
-  todowrite: allow
-  bash: allow
-  edit: deny
-  lsp: deny
-  skill: deny
-  task: deny
-  webfetch: deny
-  websearch: deny
-  codesearch: deny
-  external_directory: allow
----
-
-You are `validator`.
-
-Role
-- Provide runtime evidence, not a quality verdict.
-- Run the smallest safe repo-native verification commands that match the claimed impact.
-
-Rules
-- Prefer existing scripts and standard entry points.
-- Start narrow.
-- Record exact commands, purpose, exit codes, and what they prove.
-- If no safe target exists, say so plainly instead of improvising.
-
-Output
-- `## Commands Run`
-- `## Results`
-- `## Summary`
-- `## Missing Targets`
-- `## Uncertainty`

package/defaults/agent-settings.json

@@ -1,102 +0,0 @@
-{
-  "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
-  },
-  "executor": {
-    "model": "anthropic/claude-sonnet-4-6",
-    "temperature": 0,
-    "steps": 200
-  },
-  "scout": {
-    "model": "anthropic/claude-sonnet-4-6",
-    "temperature": 0,
-    "steps": 24
-  },
-  "worker": {
-    "model": "openai/gpt-5.3-codex",
-    "temperature": 0,
-    "steps": 30
-  },
-  "heavy-worker": {
-    "model": "openai/gpt-5.4",
-    "temperature": 0,
-    "steps": 40
-  },
-  "deep-worker": {
-    "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",
-    "temperature": 0,
-    "steps": 20
-  },
-  "auditor": {
-    "model": "openai/gpt-5.4",
-    "temperature": 0,
-    "steps": 24
-  },
-  "strategist": {
-    "model": "anthropic/claude-opus-4-6",
-    "temperature": 0,
-    "steps": 20
-  },
-  "devil": {
-    "model": "anthropic/claude-sonnet-4-6",
-    "temperature": 0,
-    "steps": 8
-  },
-  "scribe": {
-    "model": "anthropic/claude-sonnet-4-6",
-    "temperature": 0,
-    "steps": 30
-  },
-  "librarian": {
-    "model": "anthropic/claude-sonnet-4-6",
-    "temperature": 0,
-    "steps": 24
-  }
-}

package/defaults/agent-settings.schema.json

@@ -1,25 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "opencode-multiagent agent settings",
-  "description": "Central model, temperature, and step overrides per bundled agent.",
-  "type": "object",
-  "additionalProperties": {
-    "type": "object",
-    "additionalProperties": false,
-    "properties": {
-      "model": {
-        "type": "string",
-        "pattern": "^[^\\s]+/[^\\s]+$"
-      },
-      "temperature": {
-        "type": "number",
-        "minimum": 0
-      },
-      "steps": {
-        "type": "number",
-        "minimum": 1
-      }
-    },
-    "required": ["model"]
-  }
-}

package/defaults/flags.json

@@ -1,35 +0,0 @@
-{
-  "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
-  }
-}

package/defaults/flags.schema.json

@@ -1,119 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "opencode-multiagent flags",
-  "description": "Partial runtime overrides for the OpenCode multi-agent control plane plugin.",
-  "type": "object",
-  "additionalProperties": false,
-  "properties": {
-    "profile": {
-      "type": "string",
-      "enum": ["minimal", "standard", "strict"],
-      "description": "Named runtime profile to use as the base flag set."
-    },
-    "enforcement": {
-      "type": "boolean",
-      "description": "Enable local path and shell safety enforcement hooks."
-    },
-    "observation": {
-      "type": "boolean",
-      "description": "Enable JSONL observation logging for events and tool executions."
-    },
-    "prompt_controls": {
-      "type": "boolean",
-      "description": "Enable prompt metadata headers and risky-input logging."
-    },
-    "agent_compilation": {
-      "type": "boolean",
-      "description": "Compile bundled, global, and project agent markdown into config."
-    },
-    "command_compilation": {
-      "type": "boolean",
-      "description": "Compile bundled, global, and project command markdown into config."
-    },
-    "mcp_compilation": {
-      "type": "boolean",
-      "description": "Inject plugin-managed MCP server defaults when missing from config."
-    },
-    "telemetry": {
-      "type": "boolean",
-      "description": "Enable detailed agent and tool telemetry in the plugin JSONL log."
-    },
-    "supervision": {
-      "type": "boolean",
-      "description": "Enable parent-child idle supervision reminders."
-    },
-    "quality_gate": {
-      "type": "boolean",
-      "description": "Enable quality reminder tracking for edited sessions."
-    },
-    "skill_injection": {
-      "type": "boolean",
-      "description": "Enable dynamic skill registry lookup and prompt injection."
-    },
-    "skill_sources": {
-      "type": "array",
-      "description": "Skill registry search paths. Variables such as ${plugin_root} and ${home} are resolved at runtime.",
-      "items": {
-        "type": "string",
-        "minLength": 1
-      },
-      "minItems": 1
-    },
-    "compiler": {
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "permission_compilation": {
-          "type": "boolean",
-          "description": "Fill missing top-level OpenCode permission defaults conservatively."
-        }
-      }
-    },
-    "experimental": {
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "chat_system_transform": {
-          "type": "boolean"
-        },
-        "chat_messages_transform": {
-          "type": "boolean"
-        },
-        "session_compacting": {
-          "type": "boolean"
-        },
-        "text_complete": {
-          "type": "boolean"
-        }
-      }
-    },
-    "supervision_config": {
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "idle_timeout_ms": {
-          "type": "number",
-          "minimum": 0
-        },
-        "cooldown_ms": {
-          "type": "number",
-          "minimum": 0
-        }
-      }
-    },
-    "quality_config": {
-      "type": "object",
-      "additionalProperties": false,
-      "properties": {
-        "reminder_idle_ms": {
-          "type": "number",
-          "minimum": 0
-        },
-        "reminder_cooldown_ms": {
-          "type": "number",
-          "minimum": 0
-        }
-      }
-    }
-  }
-}

package/defaults/mcp-defaults.json

@@ -1,47 +0,0 @@
-{
-  "code_index": {
-    "type": "local",
-    "command": [
-      "python3",
-      "-m",
-      "code_index_mcp.server"
-    ],
-    "enabled": true
-  },
-  "repo": {
-    "type": "local",
-    "command": [
-      "python3",
-      "-m",
-      "mcp_server_git"
-    ],
-    "enabled": true
-  },
-  "context7": {
-    "type": "remote",
-    "url": "https://mcp.context7.com/mcp",
-    "enabled": false
-  },
-  "exa": {
-    "type": "remote",
-    "url": "https://mcp.exa.ai/mcp",
-    "enabled": false
-  },
-  "gh_grep": {
-    "type": "remote",
-    "url": "https://mcp.grep.app",
-    "enabled": false
-  },
-  "github": {
-    "type": "local",
-    "command": [
-      "npx",
-      "-y",
-      "@modelcontextprotocol/server-github"
-    ],
-    "environment": {
-      "GITHUB_PERSONAL_ACCESS_TOKEN": "{env:GITHUB_PAT_TOKEN}"
-    },
-    "enabled": false
-  }
-}

package/defaults/mcp-defaults.schema.json

@@ -1,38 +0,0 @@
-{
-  "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "opencode-multiagent MCP defaults",
-  "description": "Plugin-managed MCP server definitions that are conservatively injected when missing from the active OpenCode config.",
-  "type": "object",
-  "additionalProperties": {
-    "type": "object",
-    "additionalProperties": false,
-    "properties": {
-      "type": {
-        "type": "string",
-        "enum": ["local", "remote"]
-      },
-      "url": {
-        "type": "string",
-        "minLength": 1
-      },
-      "command": {
-        "type": "array",
-        "items": {
-          "type": "string",
-          "minLength": 1
-        },
-        "minItems": 1
-      },
-      "environment": {
-        "type": "object",
-        "additionalProperties": {
-          "type": "string"
-        }
-      },
-      "enabled": {
-        "type": "boolean"
-      }
-    },
-    "required": ["type", "enabled"]
-  }
-}