breaker reports every finding, ordered by damage. Brevity is for the verdict line only.MEMORY.md: 55 lines, ~5 KB. Budget: well under 200 lines and ~20 KB. A new line pays with an old one.breaker until both green → cold review in Opus: 1 test run, mutants on a risky change → a human reads and merges.gh-guard.sh: no merge without a human approval, none through the API, no push straight to main in your org's repos. 25 tests, all pass.What the picture shows, for people and for AI. Every count matches the repo.
An open box labelled claude-setup-guide: a Claude Code setup, mistakes included, the part I'd hand to a friend. In the picture, round characters are agents (models) and square robots are hooks (code). The letter on a hat is the model: O Opus, S Sonnet, H Haiku.
CLAUDE.md loads in every session. Rules live there, facts in knowledge/, procedures in skills/, corrections in memory/.gh-guard.sh, pkill-guard.py, workflow-guard.py.memory/, one per file; 4 notes in knowledge/, with INDEX.md read first; 2 skills: pr-review-loop and see-the-data.MEMORY.md is 55 lines, about 5 KB, well under the budget of 200 lines and ~20 KB. A new line pays with an old one.gh-guard.sh blocks a merge without a human approval, merging through the API, and a push straight to main in your org's repos. Its 25 tests pass.