relay-shell AGENTS.md

relay-shell AGENTS.md is an instructions file for Codex, OpenCode from rmednitzer/relay-shell. It costs 1,490 tokens per session, scanned B, original, Apache-2.0.

A set of instructions for AI coding agents working in the relay-shell repository. The repository provides local shell and SSH operations through MCP, a standard that lets AI tools call external services, with auditing and execution limits.

In plain words
What is it for?
Guiding development and operations work on relay-shell, especially shell or SSH features, privileged actions, error handling, and auditability.
Why use it?
It gives agents the rules and project context needed to make safe, traceable changes. This helps prevent hidden execution paths, missing limits, and unclear failures.

Instructions file for CodexOpenCode

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 instructions/rmednitzer/relay-shell/agents-md
Clone the repo
git clone --depth 1 https://github.com/rmednitzer/relay-shell

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 relay-shell AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rmednitzer/relay-shell/agents-md.svg)](https://agentmods.dev/instructions/rmednitzer/relay-shell/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rmednitzer/relay-shell/agents-md"><img src="https://agentmods.dev/badge/instructions/rmednitzer/relay-shell/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,490 This file is loaded in full into every session.
When invoked 1,490 The same file — it is already loaded in full.
Security scan B 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 $0.01490 $0.01490
Opus 5 $0.00745 $0.00745
Sonnet 5 $0.00298 $0.00298
Haiku 4.5 $0.00149 $0.00149

Measured 3d ago against content hash 6f817aaaa8fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

relay-shell AGENTS.md scanned grade B 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

3. **Preserve capability.** Do not reduce shell/SSH/root/sudo viability unless explicitly requested.
AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repository is designed for AI-assisted operations and development. This file defines the required behavior for any coding/ops agent working in this repo.

1) Mission

relay-shell is an MCP server for high-capability local shell and SSH operations with strong auditability and bounded execution. The project goals are:

  1. Maximum useful operator capability (including privileged/root workflows when required)
  2. Reliable execution and error containment
  3. Audit-first observability
  4. Reasonable, explicit security controls without disabling core capability

2) Non-negotiable operating principles

  1. Never bypass auditability intentionally.
  2. Never introduce hidden execution paths. All tool paths must remain visible and auditable.
  3. Preserve capability. Do not reduce shell/SSH/root/sudo viability unless explicitly requested.
  4. Prefer explicit bounded behavior. Timeouts, output limits, and session caps must remain enforced.
  5. Fail closed where practical, fail safe everywhere else. Denials must be explicit; failures must not crash transport.

3) Trusted baseline references

Use these as decision anchors for changes:

4) Implementation standards

Reliability

  • Keep tool responses deterministic and bounded.
  • Do not allow uncaught exceptions to escape tool boundaries.
  • Preserve current behavior: return structured text errors instead of transport failures.
  • Add/adjust tests with any behavior change.

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 1,490 tokens per session scan B 6f817aaaa8fa

Subscribe to this mod's changes

relay-shell AGENTS.md is an instructions file published in the GitHub repository rmednitzer/relay-shell (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,490 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.