6 tagged fable, measured the same way as everything else here.
Agent
A delegation-only subagent based on Sonnet Fable 5 for independent implementation, analysis, research, or writing tasks. It returns readable results to the main session instead of applying a working mode directly.
Agent
Fresh-context verifier. Use PROACTIVELY after completing any multi-step task - verifies work against its specification by running real checks, immune to the implementer's rationalizations.
Agent
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.
Agent
Standard engineering execution. Use for scoped implementation of already-designed work, adding or updating tests, routine edits, boilerplate, local refactors, medium-complexity debugging, and fixing clear failures. Does not make product calls or change architecture.
Agent
Independent evidence-based verification. Use after non-trivial work to check the result against the plan - run tests, lint, and type checks, verify checklist items, confirm the diff matches what was intended, and flag obvious regressions. Reports pass/fail with evidence; never fixes anything.