jailed-agents: Instructions file for Codex

AGENTS.md

jailed-agents AGENTS.md is an instructions file for Codex, OpenCode from andersonjoseph/jailed-agents. It costs 1,494 tokens per session, scanned A, original, MIT.

Development instructions for jailed-agents, a project that packages coding agents with restricted access. They cover commands for formatting, checking, building, and testing Nix code.

In plain words
What is it for?
Formatting Nix files, running checks, building packages, entering the development shell, and testing agent configurations.
Why use it?
They give coding agents consistent project commands and explain how to verify sandbox restrictions.

Instructions file for CodexOpenCode

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

This is andersonjoseph/jailed-agents's own configuration. It tells Codex and OpenCode how to work on jailed-agents 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 jailed-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andersonjoseph/jailed-agents. 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/andersonjoseph/jailed-agents/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/andersonjoseph/jailed-agents

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 jailed-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andersonjoseph/jailed-agents/agents-md.svg)](https://agentmods.dev/instructions/andersonjoseph/jailed-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/andersonjoseph/jailed-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/andersonjoseph/jailed-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,494 This file is loaded in full into every session.
When invoked 1,494 The same file — it is already loaded in full.
Security scan A 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 $0.01494 $0.01494
Opus 5 $0.00747 $0.00747
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00149 $0.00149

Measured 8d ago against content hash d4a01f9b3cf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jailed-agents AGENTS.md scanned grade A 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Example: `commonPkgs = with pkgs; [ bashInteractive curl wget jq git ];`
AGENTS.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidelines for agentic coding assistants working on jailed-agents.

Development Commands

Formatting

nixfmt

Format all Nix files using nixfmt.

Linting

nix shell nixpkgs#statix -c statix check

Check for Nix code style issues.

Building

nix build .#<package>

Build any package from flake outputs. Use llm-agents.packages.${system}.<agent> pattern for package access.

Testing

No external tests. Create a test flake that imports this repository, build the agent config, and verify sandbox constraints:

{
  inputs.jailed-agents.url = "path:/path/to/jailed-agents";
  outputs = { jailed-agents, ... }: {
    packages.x86_64-linux.default = jailed-agents.lib.x86_64-linux.makeJailedOpencode {};
  };
}

Development Shell

nix develop

Enter dev shell with nixd, nixfmt, statix, and jailed agents.

Code Style Guidelines

Nix Formatting

  • Use nixfmt for all Nix files (automatically applied via nix fmt)
  • 2-space indentation for nested structures
  • Keep line length reasonable (~100 characters, but not strictly enforced)
  • Use trailing commas in multi-line lists and attribute sets

Function Definitions

  • Use camelCase for function names (e.g., makeJailedAgent, makeJailedCrush)
  • Define parameters with ? [] pattern for defaults (e.g., extraPkgs ? [])
  • Align parameters on new lines for multi-argument functions:
makeJailedAgent = {
  name,
  pkg,
  configPaths,
  extraPkgs ? [],
  baseJailOptions ? commonJailOptions,
  basePackages ? commonPkgs,
}: ...

Imports and Scope

  • Use with pkgs; for package imports when building package lists
  • Use with jail.combinators; when using jail combinators
  • Avoid mixing with statements in the same scope
  • Use inherit for passing multiple attributes vertically:
makeJailedAgent {
  inherit
    name
    pkg
    extraPkgs
    baseJailOptions
    ;
  configPaths = ["~/.config/app"];
};

Lists and Attributes

  • Place list items on separate lines with proper indentation and trailing commas
  • Example: commonPkgs = with pkgs; [ bashInteractive curl wget jq git ];
  • Add empty lines between logical sections in let-bindings (e.g., between commonPkgs and commonJailOptions)
  • Use trailing semicolon for multi-line inherit blocks

Read the full file on GitHub · 173 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. 8d ago First seen · 173 lines · 1,494 tokens per session scan A d4a01f9b3cf0

Subscribe to this mod's changes

jailed-agents AGENTS.md is an instructions file published in the GitHub repository andersonjoseph/jailed-agents (113 stars, last pushed today), licensed MIT. It adds 1,494 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens