Skip to main content

Documentation Index

Fetch the complete documentation index at: https://bastani.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Atomic ships 12 specialized sub-agents alongside skills and workflows. Each is a purpose-built agent with a narrow job, a scoped tool set, and its own context window. Skills and workflows auto-dispatch them. You can also invoke one directly with: 
Task(subagent_type: "<name>", description: "...", prompt: "...")
Run /agents in any chat to list them.

​
The 12 sub-agents

Sub-agentPurpose
plannerDecompose specs into structured task lists with dependency tracking.
workerImplement single focused tasks (multiple workers run in parallel).
reviewerAudit implementations against specs and best practices.
orchestratorCoordinate complex multi-step workflows.
debuggerDebug errors, test failures, and unexpected behavior.
code-simplifierSimplify and refine code for clarity and maintainability.
codebase-locatorLocate files, directories, and components.
codebase-analyzerAnalyze implementation details of specific components.
codebase-pattern-finderFind similar implementations and usage examples.
codebase-online-researcherResearch using web sources and DeepWiki.
codebase-research-locatorFind prior research documents in research/.
codebase-research-analyzerDeep-dive on existing research topics.

​
Why specialized agents instead of one general agent?

LLMs have an architectural limitation: the more context they hold, the harder it is to attend to the right information. A single agent juggling a spec, dozens of files, tool outputs, and its own reasoning will lose details, repeat work, or hallucinate connections. Specialized sub-agents fix this with three constraints:
  • Context isolation — fresh, minimal context per job. A worker doesn’t see the planner’s deliberation; a reviewer doesn’t see the worker’s scratch work.
  • Tool scoping — a reviewer can’t edit files; a worker can’t spawn other workers. The available tool set matches the job.
  • Parallel execution — independent agents run concurrently. Several codebase-locator runs can fan out without contaminating each other’s context.
The research-codebase skill, the create-spec skill, and the ralph workflow all rely on these sub-agents under the hood. You don’t usually invoke them by hand — they’re dispatched as your higher-level skill or workflow runs.