hermes-mcp: Instructions file for Codex

AGENTS.md

hermes-mcp AGENTS.md is an instructions file for Codex, OpenCode from HarutuneDavisIBM/hermes-mcp. It costs 636 tokens per session, scanned A, original, MIT.

Project instructions for connecting to a Hermes MCP server that requires a browser session cookie for authentication. They explain the required cookie format and what to do when the session expires.

In plain words
What is it for?
Use them when configuring or troubleshooting access to this Hermes deployment. They provide the required environment variable and the browser steps for obtaining a replacement cookie.
Why use it?
They prevent agents from trying unsupported authentication methods and help identify an expired session when the server returns an HTML error instead of JSON.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is HarutuneDavisIBM/hermes-mcp's own configuration. It tells Codex and OpenCode how to work on hermes-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hermes-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HarutuneDavisIBM/hermes-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HarutuneDavisIBM/hermes-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/HarutuneDavisIBM/hermes-mcp

Made for: Codex, OpenCode.

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-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harutunedavisibm/hermes-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/harutunedavisibm/hermes-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/harutunedavisibm/hermes-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/harutunedavisibm/hermes-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hermes-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/harutunedavisibm/hermes-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/harutunedavisibm/hermes-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 636 This file is loaded in full into every session.
When invoked 636 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00636 $0.00636
Opus 5.5 $0.00254 $0.00254
Sonnet 5.5 $0.00127 $0.00127
Haiku 4.5 $0.00064 $0.00064

Measured 2mo ago against content hash 9efb83425f94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-mcp AGENTS.md scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This file provides instructions for AI agents (Bob, Copilot, etc.) working with this MCP server.

Authentication — the only method that works

This Hermes deployment authenticates exclusively via the AWSELBAuthSessionCookie-0 session cookie.

  • HERMES_TOKEN / x-amzn-oidc-data is not used by this deployment. Do not suggest it.
  • The only required env var is HERMES_COOKIE.

The correct value format is the full cookie name=value string:

AWSELBAuthSessionCookie-0=<value>

Include the AWSELBAuthSessionCookie-0= prefix — this is passed verbatim as the HTTP Cookie header.

When authentication fails

If any tool returns an HTML error page (Unexpected token '<'... or Search failed: Unexpected token) instead of JSON, the session cookie has expired. This is the only failure mode.

Do not attempt to use HERMES_TOKEN. Do not look for a x-amzn-oidc-data header. Just ask the user for a new cookie.

When asking for a new cookie, give these exact instructions:

  1. Go to https://hermes-sharepoint.hashicorp.services in your browser and make sure you're logged in
  2. Open DevTools (Cmd+Option+I) → Application tab → Cookies → select the site
  3. Find the cookie named AWSELBAuthSessionCookie-0
  4. Copy the Name=Value pair (e.g. AWSELBAuthSessionCookie-0=abc123...)
  5. Paste it here
  1. Use execute_command with a node one-liner to update ~/.bob/settings/mcp.json — this is safer than string search/replace because the cookie value is long and contains special characters that confuse diff tools:
node -e "
const fs = require('fs');
const path = '/Users/<username>/.bob/settings/mcp.json';
const config = JSON.parse(fs.readFileSync(path, 'utf8'));
config.mcpServers.hermes.env.HERMES_COOKIE = '<new-cookie-value>';
fs.writeFileSync(path, JSON.stringify(config, null, 2));
console.log('Done');
"
  1. Kill the old server process so it restarts with the new env:

Read the full file on GitHub · 69 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. 2mo ago First seen · 69 lines · 636 tokens per session scan A 9efb83425f94

Subscribe to this mod's changes

hermes-mcp AGENTS.md is an instructions file published in the GitHub repository HarutuneDavisIBM/hermes-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 636 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

hermes-mcp AGENTS.md compared with instructions from other repositories

hermes-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hermes-mcp AGENTS.mdHarutuneDavisIBM/hermes-mcpInstructions file02mo agoMITA636Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode