SkillProof tested Claude skills

Hermes Loop Master

Gennemtvinger spec, RØD/GRØN bevis og adversarial diff-gennemgang før kode sendes

Af s0heyl · s0heyl/hermes-loop-master

Testet · Virker ★ 8.8/10

Hermes Loop Master — Gennemtvinger spec, RØD/GRØN bevis og adversarial diff-gennemgang før kode sendes

Hvad det gør

En coding-discipline loop that makes the agent write a checkable execution contract, 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. Udløses ved multi-step, production-facing, security-sensitive or cross-session coding tasks. Ships an executable harness that scores the loop artifacts, so the process is machine-checked rather than self-reported.

Testrapport

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. The bundled harness_check.py is 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 is 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.

Testet: 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

Kommandoer og eksempelprompter

  • /hermes-loop-masterGennemtvinger spec, RØD/GRØN bevis og adversarial diff-gennemgang før kode sendes

Skills udløses af almindelige forespørgsler — ingen kommandoer at huske. Efter installationen aktiverer prompter som disse skillen (på engelsk):

  • Fix this auth bypass in production, carefully, with proof it actually works
  • Refactor the payment webhook handler, this will span a few sessions
  • Continue yesterday's migration work under the RED/GREEN evidence loop

Læs hele rapporten →