Architect-builder cross-vendor loop

A two-vendor loop that pairs Claude as architect with Codex as builder, using the repo itself as shared memory: the architect writes specs, the builder implements one item per iteration, and the architect reviews the diffs on the next pass.

prompt
→ Claude
Claude as architect, Codex as builder, the repo as shared memory — architect writes plan/spec files, builder implements one item per iteration, architect reviews diffs next pass.
claude-code

Implementation note

When to use: tasks where planning quality and implementation throughput are different problems — you want one model doing deliberate architecture and another grinding out code, with a review pass between them. How it works: Claude plays architect, Codex plays builder, and the repo itself is the shared memory. The architect writes plan and spec files into the repo; the builder implements one item per iteration from those specs; on the next pass the architect reviews the resulting diffs and updates the plan. Neither agent holds conversational state about the other — everything they know about each other's work lives in files and git history. Safety: the architect-reviews-diffs step is the built-in check — implementation drift gets caught on the next planning pass rather than accumulating silently. One item per builder iteration keeps changes bounded and attributable. Cap iterations on both sides and keep the spec files small enough that fresh-context reads stay reliable.

Source: DanMcInerney/architect-loop

More planning loops

loop-init, loop-audit, loop-cost CLI patterns

/ralphnew

Three starter CLI tools that turn loop design into a repeatable workflow: scaffold a loop with a goal, budget, and verify step; audit an existing loop design; and estimate cost before you run.

prompt
→ Claude
Starter CLI tools: `loop-init` scaffolds a loop (goal, budget, verify step), `loop-audit` reviews an existing loop design, `loop-cost` estimates spend before running.
planningmedium risk

Ralph the PRD backlog

The canonical Ralph loop: each iteration starts fresh, reads the PRD and guardrails, ships exactly one backlog item end-to-end, and records what it learned.

prompt
→ Claude
/loop start each iteration with fresh context: read PROMPT.md, prd.json, and .ralph/guardrails.md; pick the single highest-priority item in prd.json not marked done, implement it with tests, run the full check suite, commit and mark it done only if green; if blocked or a check fails twice the same way, append the lesson to .ralph/guardrails.md and move on; stop when every item is done or after 30 turns
planninghigh risk

Set agent continuation budget

/goalnew

Configure max turns before agent stops, preventing runaway loops and controlling execution cost.

prompt
→ Claude
/goal budget <n Set max continuation turns
planninglow risk