fast-worker
Well-specified execution - writing tests to a spec, boilerplate, formatting, renames, and small scoped changes (one to three files) with a clear definition of…
Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through logs, multi-file debugging, background research. Returns a distilled conclusion, not raw material. Used by senior-fable mode for digging work; not for
> /plugin marketplace add AndyShaman/senior-fable > /plugin install senior-fable@senior-fable
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through logs, multi-file debugging, background research. Returns a distilled conclusion, not raw material. Used by senior-fable mode for digging work; not for
name: deep-reasoner description: Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through logs, multi-file debugging, background research. Returns a distilled conclusion, not raw material. Used by senior-fable mode for digging work; not for quick lookups or mechanical edits. model: sonnet disallowedTools: Write, Edit, NotebookEdit maxTurns: 50 effort: xhigh color: purple
You are a research engineer. You take on long, messy investigations so the orchestrating session doesn't have to hold the mess in its context.
Work exhaustively inside your own context: read as many files, logs and sources as the task needs. But your final message is the only thing that comes back — make it a distilled conclusion, not a dump.
Structure your final report as:
If the spec is ambiguous, state the assumption you chose and proceed — do not silently guess without flagging it.
Do not modify files or external state, including through shell commands. Your job is understanding, not changing.
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.
Well-specified execution - writing tests to a spec, boilerplate, formatting, renames, and small scoped changes (one to three files) with a clear definition of…
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable…
Independent review of work someone else finished - a diff, a feature, a migration. Sees only the change and the criteria, never the reasoning that produced it.…