← All artifacts · All patterns · Planning & Control Flow

Todo-List-Driven Autonomous Agent

aka todo.md Agent, Persistent Markdown Plan, Externalised Plan File

category: planning-control-flow · status: emerging

Intent

Have the agent author a plan file (e.g. todo.md) early in the run, tick items as it completes them, and re-inject the remaining plan into context; the file is durable plan and working memory.

Context

A long-horizon autonomous task in a sandboxed VM with file-system access; the run may span hundreds of tool calls and exceed any usable in-context plan.

Problem

In-context plans drift to the middle of the window where the model attends least; without a durable plan artefact, paused or context-truncated runs cannot recover; the agent forgets which sub-tasks are done.

Forces

Models attend most strongly to the end (and start) of the context window.
File-system memory is durable; in-context memory is volatile.
Re-injecting the full plan every turn is repetitive but combats attention drift.
Markdown is human- and model-readable, supports easy ticking.

Solution

Early in the run, the agent writes its plan as a checklist file (todo.md) in its sandbox. Each turn: read the file, work the next unticked item, update the file (tick the item, add follow-ups, drop dead-ends). Re-inject the unticked tail of the file into the prompt before the model's next turn. The file outlives any single context window. Paired with a sandboxed VM that gives the agent persistent storage and basic tools (browser, shell, file editor).

Structure

Sandbox VM (browser, shell, files) + agent loop: read(todo.md) -> select next item -> act -> update(todo.md) -> repeat.

Constrains

The agent may not advance past an unticked item without recording the action in the plan file; arbitrary in-context-only plans are forbidden.

Consequences

Benefits

Plan survives context truncation and pause/resume.
Re-injecting unticked items keeps the model focused on what's left.
Human-readable trail for debugging and review.

Liabilities

Re-injection costs tokens every turn.
The agent may rewrite the file capriciously; needs guardrails on plan mutations.
Sandboxed VM cost (one VM per task) is non-trivial.

Known Uses

Manus (Monica.im) — Plan persisted as todo.md inside a per-task sandbox VM; remaining items re-injected each turn.
OpenManus — Open-source replica of Manus's loop.

Related Patterns

specialises → scratchpad — Scratchpad for the plan specifically.
alternative-to → spec-first-agent — Spec-first uses a human-authored spec; this is agent-authored.
complements → agent-resumption
uses → context-window-packing
uses → sandbox-isolation
complements → append-only-thought-stream