GENERAL PUB_DATE: 2026.01.10

AGENTIC CODING: MAKE THE TODO/PLAN A FIRST-CLASS TOOL

A popular HN breakdown shows you can recreate a Claude Code–style assistant in a few hundred lines by centering the loop on a dynamic TODO/plan and persisting i...

A popular HN breakdown shows you can recreate a Claude Code–style assistant in a few hundred lines by centering the loop on a dynamic TODO/plan and persisting it with explicit tools instead of relying solely on the model’s context. Practitioners note large performance drops when planning/TODO is disabled and warn that production-grade context and memory management is the real work; YouTube summaries also claim Claude Code 2.1 adds sub-agents/skills and LSP hooks, but verify against official docs.

[ WHY_IT_MATTERS ]
01.

Explicit planning state improves reliability, observability, and repeatability versus context-only prompting.

02.

This pattern is fast to prototype but surfaces the true cost of context, memory, and guardrails you’ll need in production.

[ WHAT_TO_TEST ]
  • terminal

    Prototype a repo assistant that persists a structured TODO list (timestamps, branches, outcomes) to disk/Redis and compare task success with and without planning enabled.

  • terminal

    Evaluate LSP-based local edits versus patch generation on a target service and measure diff quality, latency, and reviewer acceptance.

[ BROWNFIELD_PERSPECTIVE ]

Legacy codebase integration strategies...

  • 01.

    Start read-only in monorepos and gate writes through CI; keep agent plan state outside the repo to avoid noisy churn.

  • 02.

    Map agent actions to code ownership and ticketing rules to prevent cross-boundary changes and ease rollback.

[ GREENFIELD_PERSPECTIVE ]

Fresh architecture paradigms...

  • 01.

    Define a plan/TODO schema and tool interface on day one, persist it in a durable KV, and log every step for traceability.

  • 02.

    Standardize editor/LSP setup and patch/rollback mechanics early to keep agent loops deterministic.