relay-shell: Instructions file for Codex

AGENTS.md

relay-shell AGENTS.md is an instructions file for Codex, OpenCode from rmednitzer/relay-shell. It costs 2,284 tokens per session, scanned A, 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

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

This is rmednitzer/relay-shell's own configuration. It tells Codex and OpenCode how to work on relay-shell 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 relay-shell configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rmednitzer/relay-shell. 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/rmednitzer/relay-shell/main/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/github.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/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 relay-shell AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,284 This file is loaded in full into every session.
When invoked 2,284 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 $0.02284 $0.02284
Opus 5.5 $0.00914 $0.00914
Sonnet 5.5 $0.00457 $0.00457
Haiku 4.5 $0.00228 $0.00228

Measured 12d ago against content hash f7deb03a8f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

relay-shell 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 12d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent development guidance: relay-shell

Repository-specific workflow

MCP shell/SSH operator infrastructure. Read docs/runbook.md (especially its audit/review/validation sections), relevant docs/adr/, and SECURITY.md.

  • Preserve intentional scoped and privileged/root deployment modes, shell/SSH, sessions, transfers and forwarding. The executor has no internal sandbox. Do not silently remove capabilities or introduce a sandbox; changes to posture need explicit scope and design review.
  • Every execution path passes through the central audited runner. Preserve deny-first precedence across open/guarded/readonly modes, tier classification, confirmation-token binding/expiry/single-use semantics, redaction, timeout/output/session caps, and SSH host verification.
  • The default posture is open: with default settings no command is refused for what it does (ADR 0013, pinned by tests/test_notices.py). Do not add a default-on refusal, deny pattern or confirmation step; add opt-in controls instead. Risky admitted calls are answered with a [NOTICE ...] line and server_info.warnings lists permissive settings; both are information, are not written into the audit record, and must never be described as a boundary. A new permissive setting needs a matching entry in notices.config_warnings.
  • Classification regexes are heuristics, not a complete shell-language security boundary. Never claim that a permitted shell command or privileged client is contained by the classifier.
  • Audit arguments must be redacted; output bodies must not be logged, only length/hash. Preserve chain limitations, rotation continuity, off-host integrity requirements, and secret-prompt handling. Redaction is heuristic and must be tested with synthetic secrets.
  • Tool errors use existing bounded structured error helpers, not raw tracebacks or uncaught transport failures. Preserve cancellation and cleanup, close only owned sessions, and reconcile timeouts before retrying mutations.
  • Technical map: src/relay_shell/server.py registers tools; config, policy, broker, audit, redaction, patterns, sessions and sshpool define the principal boundaries. tests/test_server.py::_EXPECTED is the tool-registration contract.
  • Setup: python -m pip install -e ".[dev]". Run ruff check ., ruff format --check ., mypy, pytest -q. For classifier/redactor changes also run pytest -m fuzz -v; update PATTERNS_VERSION when required by the existing contract. Preserve CodeQL, dependency review, dependency audit and secret-scanning gates.
  • Use async I/O in tool paths; do not add requests/urllib3 blocking calls. Live shell/SSH smokes require explicit targets and bounded effects. Editing this repo does not authorize restarting or deploying its running service.

Read the full file on GitHub · 144 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. 12d ago Changed · +30 lines · +794 tokens per session scan B → A f7deb03a8f72
  2. 1mo 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 (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,284 tokens to every session, about $0.0091 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

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens