Pre-code system configuration for any AI agent. Detects model, applies token optimization, estimates input tokens, compresses context, calculates real-time savings (to the token), and tracks cost delta before coding starts. Works with all 11 models. Agent runs this BEFORE writing code—saves 75-95% tokens + cost on every project. Triggers: "before i code", "set up token optimization", "configure system", "what model am i", "estimate tokens", "how much will this save", "show me savings", "pre-code checklist", "token tracker", "cost me to code this"

2026-07-012

a2a-router

executiveusa/pauli-hermes-agent

Publish agent capabilities and accept Agent2Agent task requests through the local HTTP receiver.

2026-07-012

browser-smoke-check

executiveusa/pauli-hermes-agent

Verify that a Vercel deployment URL displays a real page instead of a 404, auth wall, blank shell, or error page.

2026-07-012

github-webhook-trigger

executiveusa/pauli-hermes-agent

Verify and normalize GitHub webhook payloads for deployment automation. Use when a GitHub push, deployment_status, or workflow_run event arrives.

2026-07-012

no-code-repair-loop

executiveusa/pauli-hermes-agent

Iterate deployment visibility failures using only no-code-safe actions and stop when source-code changes are required.

2026-07-012

repo-inventory

executiveusa/pauli-hermes-agent

Inventory GitHub repositories and Vercel projects, then map repos to deployments for a visibility sweep.

2026-07-012

ワンクリックで任意のスキルを実行

name	memory-routing-policy
description	Policy for deciding what enters memory, what stays transient, and what must be redacted.