| ### Agents Bind models, tools, MCP servers, and system prompts to named profiles. Route by task complexity. ```yaml agents: default: model: claude-sonnet-4-6 tool: claude mcp_servers: ["animus", "context7"] work-planner: system_prompt: | Scan tasks, check dependencies, enqueue ready work for the daemon. model: claude-sonnet-4-6 tool: claude ``` | ### Phases Reusable execution units. Three modes: **agent** (AI with decision contracts), **command** (shell), **manual** (human gate). ```yaml phases: implementation: mode: agent agent: default directive: "Implement production code." decision_contract: min_confidence: 0.7 max_risk: medium push-branch: mode: command command: program: git args: ["push", "-u", "origin", "HEAD"] ``` |
| ### Workflows Compose phases into pipelines with skip conditions and post-success hooks. ```yaml workflows: - id: standard phases: - requirements - implementation - push-branch - create-pr post_success: merge: strategy: squash auto_merge: true cleanup_worktree: true ``` | ### Schedules & Triggers Cron-based autonomous execution and event-driven triggers. Trigger types: `file_watcher`, `webhook` (generic HTTP), `github_webhook` (with event filtering). ```yaml schedules: - id: work-planner cron: "*/5 * * * *" workflow_ref: work-planner enabled: true triggers: - id: pr-opened type: github_webhook workflow_ref: pr-reviewer enabled: true config: events: ["pull_request"] ``` |
| **Decision Contracts** Every agent phase returns a typed verdict: `advance`, `rework`, `skip`, or `fail`. Rework loops pass the reviewer's feedback back to the implementer. Configurable `max_rework_attempts` prevents infinite loops. | **Model Routing** Route tasks to different models by type and complexity. Low-priority bugfixes go to cheap models. Critical architecture tasks go to Opus. The work-planner agent manages this automatically. | **Worktree Isolation** Every task gets its own git worktree. Agents work in parallel on separate branches without conflicts. Post-success hooks handle merge, cleanup, and PR creation. |
| **Slash Commands** | Command | What it does | |:---|:---| | `/animus-setup` | Initialize Animus in your project | | `/animus-getting-started` | Install, concepts, first task | | `/animus-mcp-setup` | Connect AI tools via MCP | | `/animus-workflow-authoring` | Write custom YAML workflows | | `/animus-pack-authoring` | Build workflow packs | | `/animus-skill-authoring` | Author Animus skills | | `/animus-troubleshooting` | Debug common issues | | **Auto-Loaded References** | Skill | Coverage | |:---|:---| | `animus-configuration` | Config files, state layout, model routing | | `animus-task-management` | Full task lifecycle via CLI and MCP | | `animus-daemon-operations` | Daemon monitoring and troubleshooting | | `animus-queue-management` | Dispatch queue operations | | `animus-workflow-patterns` | Patterns from 150+ autonomous PRs | | `animus-agent-personas` | PO, architect, auditor agents | | `animus-mcp-tools` | Complete `animus.*` tool reference | | `animus-mcp-servers-for-agents` | Context7, GitHub, memory MCP wiring | |