claude-progress.txt harness pattern (Anthropic)
Anthropic's first-party file-as-memory harness for long-running agents: every fresh-context session recovers state from a progress file and the git log, does one unit of work, updates the file, commits, and exits.
Implementation note
When to use: agent work too long for one session — multi-day builds where context will be lost repeatedly and the question becomes how each new session knows where things stand. This is Anthropic's first-party answer. How it works: every fresh-context session begins by reading claude-progress.txt plus the git log to recover state, does one unit of work, updates the progress file, commits, and exits. An initializer session sets up the progress file; coder sessions then loop the pattern indefinitely. The progress file is curated state — what is done, what is next, what to watch for — while git history is the ground truth it points into. Safety: the discipline lives in the exit ritual: a session that fails to update the progress file before exiting strands the next one, so treat update-then-commit as non-negotiable. One unit of work per session keeps commits reviewable and recovery cheap when an iteration goes sideways.
Source: Anthropic Engineering ↗
More automation loops
Run workflows with dynamic sub-agents
Split a task into packets, run sub-agents in parallel, synthesize results, and verify completion.
Run agent turns until goal met
Agent executes repeated turns toward a condition, with a lightweight evaluator checking progress after each turn until the goal is reached.
Run agent until goal met
Queue agent turns with goal context until your objective is achieved, treating the goal as untrusted data.