Hermes Adversary

The Hermes bridge comes from hermes-grok-bridge (https://github.com/shagghiesuperstar/hermes-grok-bridge): native Hermes API on :8642 over a private tailnet is primary; the SSH ask-relay MCP (ask/health) is the fallback. Credit Shagghie.

First conversation after importing Hermes Adversary: orient the owner, wire Hermes, ask setup questions one at a time, then start cross-model AR.

Use when adversarially reviewing code, plans, or pipelines and the independent reviewer must be Hermes (different model), not another Grok instance: package the AR methodology as an ask, relay it to Hermes, then triage findings.

Use when deciding between the native Hermes API (:8642) and the Hermes SSH ask-relay for putting Hermes inside Grok Bot.

Use when installing or wiring the Hermes SSH ask-relay connector so a Grok Bot can talk to a Hermes host over a private network.

Use when a connector ask to Hermes dies around ~120s (-32001): escape via host-local POST /v1/runs, and tell provider failure from host failure.

Use before shipping a vibe-coded site when you need a proven 14-attack security red team with separate test accounts, proof tables, and a one-pass fix.

Use before shipping a vibe-coded site when you need a 20-check performance audit across images, frontend, database/API, and network, with Lighthouse before/after.

Use when the user wants a backward adversarial audit of code, a plan, or a doc: line-by-line breakage, no skim, ranked critical to trivial.

Use before committing to a plan, architecture, launch, or strategy: assume it already failed and list why (Klein pre-mortem).

Use when exploring designs, attack variants, or plan options and mode collapse would hide better alternatives: generate a probability-weighted sample, then iterate on the strongest tails.

Use when designing or running AI code-review pipelines that must debounce bursts of commits, dedupe inference, cancel stale reviews, and stay tied to a commit SHA.

Use when choosing which agentic adversarial-review patterns to apply to a change, pipeline, or team process. Distills the IT Revolution pattern language with credit.