agentmods.dev

hermes-webtop: Instructions file for Codex

AGENTS.md

hermes-webtop AGENTS.md is an instructions file for Codex, OpenCode from gitricko/hermes-webtop. It costs 2,830 tokens per session, scanned C, original, MIT.

Repository instructions for agents working on the Hermes Webtop project, including its structure, startup procedures, required checks, and staged migration work. An agent is a coding tool that performs tasks in a repository.

In plain words
What is it for?
Use it to orient an agent, find important files, load required tools, follow migration phases, and verify builds, containers, and health checks.
Why use it?
It gives agents project-specific boundaries and verification rules, reducing incorrect edits and unsupported claims about completed work.

Instructions file for CodexOpenCode

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

This is gitricko/hermes-webtop's own configuration. It tells Codex and OpenCode how to work on hermes-webtop 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-webtop configures →

not rated 28repo 4d ago C scan 2,830 tokens original MIT
View source ↗ gitricko/hermes-webtop
Reuse

Borrowing it

Nothing to install: this file belongs to gitricko/hermes-webtop. 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/gitricko/hermes-webtop/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gitricko/hermes-webtop

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-webtop AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gitricko/hermes-webtop/agents-md/github.svg)](https://agentmods.dev/instructions/gitricko/hermes-webtop/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gitricko/hermes-webtop/agents-md"><img src="https://agentmods.dev/badge/instructions/gitricko/hermes-webtop/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-webtop AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gitricko/hermes-webtop/agents-md"><img src="https://agentmods.dev/badge/instructions/gitricko/hermes-webtop/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,830 This file is loaded in full into every session.
When invoked 2,830 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02830 $0.02830
Opus 5.5 $0.01132 $0.01132
Sonnet 5.5 $0.00566 $0.00566
Haiku 4.5 $0.00283 $0.00283

Measured 1mo ago against content hash ed0c586cdab5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

hermes-webtop AGENTS.md 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 1mo 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

| `git push` → "Invalid username or token" / "No anonymous write access" | Codespaces' `GH_TOKEN`/credential helper is not a usable git credential | Extract `GITHUB_TOKEN` from the VS Code server process and use `git con
AGENTS.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Webtop — Agent Guidelines

Quickstart

  1. Load these skills first (via skill_view):

    • karpathy-coding-guidelines — surgical minimal diffs, verify with real output
    • docker-test-shell — clean-container integration tests
    • codespace-gh-auth — GitHub token for this Codespace
    • ci-lint-check / ci-log-capture — CI validation + log preservation
    • mnemon-recall / mnemon_remember — session memory

  2. Always verify with real output before claiming success:

    • CI runs, builds, test Docker images, self-check health — always check exit codes and artifact logs
    • If a tool call fails, say so plainly; do not fabricate results

  3. Phase-based work — never jump phases:

    • Phase 1: ModelRelay → 9Router (port 7352) — ✅ DONE
    • Phase 2: PI branch fix + dependency bumps — ✅ DONE
    • Phase 3: .agents/skills port — ✅ DONE

Project Structure (key paths)

Path Purpose
docker/Dockerfile Multi-stage build; ARGs: PI_VERSION, NINEROUTER_VERSION, OMNIROUTE_VERSION, NODE_VERSION, etc.
docker/start-ninerouter.sh 9Router launch + health poll (/api/health, 300s) + inline config
docker/9router-config.sh Deleted — config logic inlined into start-ninerouter.sh
docker/self-check.sh Validates all services; probes /v1/models for 9Router (not just /)
docker/pi-settings.json Pi install config — git:github.com/gitricko/pi-failover@main
docker/pi-models.json Provider chain 9router / omniroute
.agents/skills/ Repo-portable skills (ci-lint-check, ci-log-capture, docker-test-shell)
~/.hermes/skills/minions/ Global minions skills (do NOT edit these)
~/.hermes/memories Mnemon graph — persist insights across sessions

Core Procedures

9Router Migration (Phase 1)

Root Cause Pattern: /config/.9router/ state dir didn't exist at boot → EACCES on jwt-secret/model-catalog → every stateful endpoint (login, combos, models) returned 500.

Read the full file on GitHub · 202 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. 1mo ago First seen · 202 lines · 2,830 tokens per session scan C ed0c586cdab5

Subscribe to this mod's changes

hermes-webtop AGENTS.md is an instructions file published in the GitHub repository gitricko/hermes-webtop (28 stars, last pushed 4d ago), licensed MIT. It adds 2,830 tokens to every session, about $0.0113 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.

Building agentsProject management
Related

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

hermes-webtop AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hermes-webtop AGENTS.mdgitricko/hermes-webtopInstructions file284d agoMITC2,830Codex, 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