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. Cap the run at 25 iterations; leave remaining work for the next session.
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

Ship verified code, one stage per agent

Loop/ralph

Run a multi-stage software factory pipeline where each agent handles one task in a fresh context, anchored to mechanical gates and held-out test suites.

prompt
→ Claude
# AGENTS.md — read this first This is Software Bodega , a software factory: a pipeline that turns an idea into verified code with one human touch per stage. Where state lives — on disk, never in chat history: - factory/STATE.md — current stage + pointer. Single source of truth. - factory/BRIEF.md BLUEPRINT.md CONTRACT.md HANDOFF.md REVIEW.md GUIDE.md - factory/.planning/{spec,decompose,plan}.json — machine-checked artifacts - factory/.planning/gate-results/ — <gate>-<sha>.json verdicts - factory/tasks/ .md — one file per task - factory/progress.md factory/log.md — append-only diaries. Never rewrite. Rules that do not bend: 1. One agent per station. One task per fresh context window. No multi-agent chat. 2. Every gate anchors to something mechanical. LLM judges are fallbacks and must be a different model FAMILY than the author. 3. factory/tests/heldout/ is held out . Never read it, never reference it, never write to it. If you can see it, that is a bug — report it. 4. Repair loops cap at 2. Then resample N=3. Then PARK. Never loop forever. 5. Never weaken a test to make it pass. Never edit CONTRACT.md — it is signed. 6. git add
planninghigh riskclaude-code

Ralph Overnight Builds — Progressive Curriculum Entry

Loop/ralph

A graduated path to unattended Ralph runs: start with a single bounded task, add a PROMPT.md spec file, add verification, and only then remove the human from the loop for overnight builds.

prompt
→ Claude
Staged path from basic prompt → PROMPT.md spec → overnight Ralph run: start with a single bounded task, add a spec file, add verification, only then remove the human from the loop. Cap the run at 25 iterations; leave remaining work for the next session.
planningmedium riskclaude-code

Draft a sprint plan from the backlog

Loop/goallooprepo

Turn the open issue backlog into a proposed two-week sprint plan with estimates, a dependency ordering, and an explicit cut line, written as a document for the team to edit.

prompt
→ Claude
/goal SPRINT-PLAN.md contains a proposed 2-week plan — read all open issues labeled `ready`, estimate each as S/M/L based on the code it touches, order them by dependency and value, draw a cut line at a realistic capacity, and list what falls below it with reasons; make no changes to the issues themselves; stop after 6 turns
planninglow riskclaude-codecodex
1