Hermes Loop Master
Erzwingt Spezifikation, RED/GREEN-Nachweis und adversarielle Diff-Überprüfung vor dem Code-Deployment
Getestet · Funktioniert
Was es kann
Eine coding-discipline loop, die den agent dazu bringt, einen checkable execution contract zu schreiben, implement one slice at a time, prove behavior with RED/GREEN plus positive, negative, preservation and failure paths, then review its own diff against ten fake-done patterns before declaring work finished. Wird ausgelöst bei multi-step, production-facing, security-sensitive or cross-session coding tasks. Liefert ein executable harness, das die loop artifacts bewertet, sodass der process maschinell überprüft und nicht self-reported wird.
Testbericht
Fixed the same duration-parser bug twice on identical repos, once free-hand and once under the loop. Both arms produced a green test suite, but the skill's mandated failure-path check exposed that the obvious regex fix silently returns 0 for 'banana' and '', 3600 for the typo '1h30', and 300 for '-5m' — a probe of ten inputs against both final versions diverged on five, with the no-skill version returning a wrong number where the skill version raises. Das bundled harness_check.py ist real and runs: it scored the loop artifacts 32/34, flagged two unchecked Done When boxes I had actually left open, correctly passed the good-loop and critical-loop fixtures and rejected the bad-loop fixture, and the repo's 36 unit tests pass. Costs three extra artifact files and roughly double the tool calls, so it earns its keep on risky work, not on typos. Note it ist branded for Nous Research's Hermes Agent and its installer defaults to ~/.hermes, so Claude Code users must pass --target as in the command above.
Getestet am: 2026-07-30 · Claude Code 2.x (agent harness)
Installation
git clone https://github.com/s0heyl/hermes-loop-master.git mkdir -p ~/.claude/skills cd hermes-loop-master && bash install.sh --target ~/.claude/skills/hermes-loop-master
Befehle & Beispiel-Prompts
/hermes-loop-masterErzwingt Spezifikation, RED/GREEN-Nachweis und adversarielle Diff-Überprüfung vor dem Code-Deployment
Skills reagieren auf normale Anfragen — keine Slash-Befehle nötig. Nach der Installation aktivieren Prompts wie diese den Skill (auf Englisch):
Fix this auth bypass in production, carefully, with proof it actually worksRefactor the payment webhook handler, this will span a few sessionsContinue yesterday's migration work under the RED/GREEN evidence loop