A fact-checked knowledge base of Claude Code creator Boris Cherny's loop methodology, packaged as a runnable agent-loop skill you can drop straight into Claude Code.
Fact-checked knowledge base of Cherny's loop methodology for running Claude Code, shipped as a runnable `agent-loop` skill in `skill/agent-loop/`. Cap the run at 25 iterations; leave remaining work for the next session.
claude-code
Implementation note
When to use: you want to learn or standardize on loop practice from the source — Boris Cherny created Claude Code, and this packages his loop methodology in runnable form rather than as scattered posts. How it works: a fact-checked knowledge base of Cherny's methodology for running Claude Code in loops, shipped with a runnable agent-loop skill in skill/agent-loop/ that you can drop straight into Claude Code and invoke. The knowledge-base half explains the reasoning; the skill half executes the pattern, so the methodology and its implementation stay in sync. Safety: fact-checked is the notable attribute — loop advice attributed to Cherny circulates widely with varying accuracy, and this repo's stated purpose is verifying claims before packaging them. Still treat the skill like any third-party skill: read what it does before running it, and apply your own turn caps and branch discipline around it.
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.
# 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
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.
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.
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.
/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