hermes

hermes is a skill for Claude Code, Codex from appletechie/perfect-goal. It costs 131 tokens per session (3,267 once invoked), scanned A, original, MIT.

A reference guide for working with the Hermes agent platform, a Python-based system for running AI agents and plugins. It covers the codebase, plugin structure, known version-history issues, and deployment procedures.

In plain words
What is it for?
Use it when editing or debugging Hermes code, creating Hermes plugins, investigating the version 15-to-16 merge regression, or planning fleet deployments.
Why use it?
It helps developers avoid known integration and deployment mistakes when changing Hermes or operating its agent fleet.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/appletechie/perfect-goal/hermes
Any agent
npx skills add appletechie/perfect-goal --skill hermes
Clone the repo
git clone --depth 1 https://github.com/appletechie/perfect-goal

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hermes

README.md
[![agentmods](https://agentmods.dev/badge/skills/appletechie/perfect-goal/hermes.svg)](https://agentmods.dev/skills/appletechie/perfect-goal/hermes)
Your own site
<a href="https://agentmods.dev/skills/appletechie/perfect-goal/hermes"><img src="https://agentmods.dev/badge/skills/appletechie/perfect-goal/hermes.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00131 $0.03267
Opus 5 $0.00066 $0.01633
Sonnet 5 $0.00026 $0.00653
Haiku 4.5 $0.00013 $0.00327

Measured 5d ago against content hash c60ef0aec0fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hermes scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

ssh dokploy-root 'curl -X POST -H "Authorization: Bearer $DOKPLOY_API_KEY" \
skills/hermes/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes — Working Knowledge

Hermes is a Python-based AI agent platform forked from NousResearch/hermes-agent and operated as enduru-mc-v<NN> releases. This skill compresses the high-leverage knowledge for working in and deploying hermes — codebase layout, plugin authoring, the v15→v16 upstream-merge regression chain, the fleet deploy flow, and the traps that cost real engineering time when missed.

If you're filing a multi-step goal involving hermes, invoke /perfect-goal after reading this skill. The two compose: this skill gives you the facts, perfect-goal gives you the output shape.


Codebase layout

The canonical repo is hermes-agent-enduru (fork of NousResearch/hermes-agent). Customer pins live in enduru-agent-infra/Dockerfile.v2. Operator fleet builds from /srv/hermes-fleet-repo on dokploy-root.

hermes-agent-enduru/
├── hermes_cli/                # CLI entry (`python -m hermes_cli.main`)
│   ├── main.py
│   └── plugins.py             # CLI-side plugin route system (see 37268d0bfd)
├── gateway/                   # Long-running gateway (WS RPC + REST)
│   ├── run.py                 # GatewayRunner — includes spawn_subprocess_agent (restored v16.3 / d2072fb484)
│   ├── api_server.py          # FastAPI routes; voice-realtime WS endpoint here
│   ├── mc_worker.py           # Pulls + executes MC tasks; the operator/customer task surface
│   ├── mc_routes.py           # MC-facing REST routes (transcript reader at L~120 reads JSON in v16.1+, was SQLite in upstream)
│   └── voice_realtime/        # Browser/Discord/Meet realtime voice (browser_bridge.py + amalia_session.py)
├── plugins/                   # First-class plugins
│   ├── <name>/
│   │   ├── plugin.yaml        # Declaration — name, version, kind, platforms, provides_tools
│   │   └── __init__.py        # Implementation — register(ctx) entry point
│   └── agent_manifest/        # Posts profile manifest → MC every 60s (see L~47 _profile_agent_id)
├── plugins-dist/              # Built/bundled MC plugin artifacts
├── scripts/                   # Build + release scripts
└── pyproject.toml             # MUST include plugins/**/plugin.yaml in package-data (28be8f2527 v16.1 fix)

Read the full file on GitHub · 201 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 201 lines · 131 tokens per session scan A c60ef0aec0fa

Subscribe to this mod's changes

hermes is a skill published in the GitHub repository appletechie/perfect-goal (2 stars, last pushed 3mo ago), licensed MIT. It adds 131 tokens to every session and 3,267 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens