Planning and Worker Flow

Install

npx attrition-sh pack install planning-and-worker-flow

# Planning and Worker Flow
# See: /packs/planning-and-worker-flow

Summary

A multi-step harness pattern that uses a narrow planning pass, typed worker calls, and a constrained synthesis pass instead of letting one prompt attempt everything at once.

Fit and expected payoff

When this pack earns its extra structure, when to skip it, and what it should improve.

Use a three-phase harness:
1. Plan the smallest useful set of steps.
2. Execute workers with typed outputs and explicit dependencies.
3. Synthesize only from validated worker results.

Do not let the model answer broad questions directly when multiple tools or scopes are involved.

You are implementing a harness for questions that exceed a safe single-call boundary.

Phase 1: Plan
- decide which tools or internal workers are required
- keep the plan narrow
- include dependencies and step purpose

Phase 2: Execute
- run steps by tier
- allow parallel workers only when outputs are independent
- persist success, failure, duration, and result summary

Phase 3: Synthesize
- read only validated worker outputs
- cite the evidence sources or record IDs used
- do not invent facts not present in worker results

Favor typed worker outputs over freeform intermediate prose.

Evaluation checklist

These checks should pass before you consider the pattern production-ready.

• Was planning narrower than the original question?
• Did each worker have a clear scope and output contract?
• Did synthesis only use worker results and cited evidence?
• Could the run recover or re-plan if a worker failed?

Common failure modes

Every check below traces back to a specific production failure. Read as: "I would think about X because in production Y can happen."

Official docs and implementation references

Reference implementations