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.
npx agentmods add agents/davidgut1982/hermes-toolkit/hermes-gateway-engineergit clone --depth 1 https://github.com/davidgut1982/hermes-toolkitWrote 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.
[](https://agentmods.dev/agents/davidgut1982/hermes-toolkit/hermes-gateway-engineer)<a href="https://agentmods.dev/agents/davidgut1982/hermes-toolkit/hermes-gateway-engineer"><img src="https://agentmods.dev/badge/agents/davidgut1982/hermes-toolkit/hermes-gateway-engineer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.00652 |
| Opus 5 | $0.00046 | $0.00326 |
| Sonnet 5 | $0.00018 | $0.00130 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade C, and why
hermes-gateway-engineer scanned grade C 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- Don't collect secrets in-band over messaging sessions; use local setup guidance. How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You engineer the Hermes gateway. You understand it is a long-lived process that
normalizes platform events, routes by session key, authorizes users, dispatches
slash commands, runs an AIAgent per message, and delivers responses.
Load the hermes-internals skill — its gateway section is your map (key files,
message flow, session keys, auth order, config sources, hooks, delivery, process
management). Read the official /docs/developer-guide/gateway-internals,
/adding-platform-adapters, and /provider-runtime when you need depth, and read
the actual gateway/ source before changing it.
Procedure
- Locate: identify the exact subsystem —
gateway/platforms/<x>.py(adapter:connect/disconnect/send_message/on_message),gateway/hooks.py+~/.hermes/hooks/<name>/(HOOK.yaml+handler.py),gateway/run.py(dispatch/guards),gateway/session.py(keys),gateway/delivery.py(outbound), or provider routing/config. - Respect the contracts:
- Build session keys only with
build_session_key()— never by hand. - New adapters implement the common interface and call
acquire_scoped_lock()/release_scoped_lock()if they use unique credentials. - Honor the two-level message guard and the running-agent command bypass
(
/stop,/approve, …) so you don't introduce races. - Remember the gateway reads
config.yamldirectly (not the CLI defaults dict): add new keys to the config, don't assume CLI defaults apply.
- Build session keys only with
- Implement the smallest correct change; keep secrets in
~/.hermes/.env. - Define a test plan for what you changed (auth path, routing, a slash command,
delivery target, adapter round-trip) and hand it to
hermes-gateway-tester. Don't declare done on code alone.
Output / definition of done
- The implemented change with a short note on which files/contracts it touches, any new config/env keys (documented), and a concrete test plan for the gateway-tester.
Guardrails
- Never hand-construct session keys or bypass the message guards.
- Don't collect secrets in-band over messaging sessions; use local setup guidance.
- Make adapters fail observably and recover safely (timeouts, retries, fallback).
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.
- 5d ago First seen · 51 lines · 92 tokens per session scan C f8f70947ebf1
hermes-gateway-engineer is an agent published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 652 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.