Orchestrator
Creates the isolated harness branch, dispatches Builder and Reviewer agents across phases, and drives until the deliverable is complete, partial, or blocked. Never writes code. Never pauses mid-run for opinions.
Fram Loop for Claude Code and Codex
01
Ralph made the loop useful: deterministic feedback keeps the agent moving. Fram makes it reviewable: Builder writes; a separate read-only Reviewer scores with numeric thresholds and file:line evidence. Red→Green commits, baseline filtering, and adaptive recovery keep the loop moving until the goal is complete or progress is impossible.
02
A two-agent autonomous loop for features, refactors, migrations, library design, performance projects, and large cleanups. Kick it off with a spec and plan; review the finished PR, not per-phase progress.
Creates the isolated harness branch, dispatches Builder and Reviewer agents across phases, and drives until the deliverable is complete, partial, or blocked. Never writes code. Never pauses mid-run for opinions.
Receives the spec, plan slice, git history, prior carry-forward, and key files. Writes code, commits source and tests, and never grades its own work.
Reads the actual code, exercises the running deliverable, runs the checks, and scores the rubric with evidence. Read-only by tooling and by doctrine.
Branch template
fram/<source>-<feature>-<sha>Cut from your branch tip. Phase work, recovery, and run-state artifacts all land there. Your source branch stays untouched until the PR is ready to inspect.
Re-walk the spec section by section. Drive the deliverable in production-shape, end-to-end. Scan for new secrets and supply-chain hooks. Compare the full suite, lint, and typecheck against the Phase 0 baseline. Only after those checks pass does the loop push the harness branch and open the PR.
complete — goal met, end-to-end verified, PR opened. partial — locally verified, push failed, local handoff written. blocked — the spec, environment, or dependency prevents progress. No arbitrary fix-round cap.
03
One command adds the skill to Claude Code or Codex. Use it when the work is bigger than one agent run and you want the final feature, not an MVP with constant status checks.
Autonomous coding loop
A two-agent autonomous coding loop by Andrei Clodius. First reference run: 5 phases, 17 commits, 98 tests, no human intervention after kickoff.