aifed AGENTS.md

aifed AGENTS.md is an instructions file for Codex, OpenCode from ImitationGameLabs/aifed. It costs 639 tokens per session, scanned A, original, MIT.

An AGENTS.md guide containing project instructions for working on aifed, a Rust-based project. It describes the folders, common development tasks, testing in a scratch directory, and dependency management.

In plain words
What is it for?
Use it when modifying or testing ImitationGameLabs/aifed. It covers adding workspace members, using the command-line tool, testing in .playground/, and managing dependencies.
Why use it?
It gives coding agents project-specific rules and orientation instead of making them infer how the repository is organized. A scratch directory is a safe place for development experiments and manual checks.

Instructions file for CodexOpenCode

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

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/imitationgamelabs/aifed/agents-md
Clone the repo
git clone --depth 1 https://github.com/ImitationGameLabs/aifed

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 aifed AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/imitationgamelabs/aifed/agents-md.svg)](https://agentmods.dev/instructions/imitationgamelabs/aifed/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/imitationgamelabs/aifed/agents-md"><img src="https://agentmods.dev/badge/instructions/imitationgamelabs/aifed/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 639 This file is loaded in full into every session.
When invoked 639 The same file — it is already loaded in full.
Security scan A 0 findings. 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 5.1 $0.00639 $0.00639
Opus 5 $0.00319 $0.00319
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 5d ago against content hash 249aadbc28d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

aifed 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 5d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI Agent working guide. This document provides code structure and decision rules for AI agents.

Directory Structure

.
├── flake.nix                  # Flake entry point
├── crates/                    # Rust workspace members
├── docs/                      # Project documentation
│   ├── agent-action-wizards/ # Step-by-step guides for AI agents
│   └── reference/            # CLI command reference
└── nix/
      ├── common.nix              # Core config (crate paths, dependencies)
      ├── packages.nix            # Flake output packages
      ├── tarball.nix             # FHS-ready tarball for non-Nix distribution
      ├── checks.nix              # CI checks (clippy, fmt, audit, nextest)
      └── home-manager-modules/   # Home-manager modules for binary deployment

Common Tasks

Testing aifed in .playground/

Use .playground/ as the general scratch workspace for testing aifed during development. This includes CLI flows, edit behavior, LSP-driven operations, and other manual verification tasks.

cd .playground
../target/debug/aifed --skill
../target/debug/aifed <command>

The .playground/ directory is in .gitignore. The CLI test walkthrough provides example test cases, but .playground/ is not limited to that guide.

Dependency Management

When adding dependencies to any crate:

  1. Add to [workspace.dependencies] in root Cargo.toml
  2. Reference in crate's Cargo.toml with workspace = true

Example:

# Root Cargo.toml
[workspace.dependencies]
serde = { version = "1.0", features = ["derive"] }

# crates/my-app/Cargo.toml
[dependencies]
serde = { workspace = true }

Verification Checklist

After modifying Nix files:

  • nixfmt <nix file> - Format single file
  • nixfmt $(find nix/ -name "*.nix") flake.nix - Format all Nix files at once
  • statix check . - Static analysis (run from project root)

Read the full file on GitHub · 73 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. 5d ago First seen · 73 lines · 639 tokens per session scan A 249aadbc28d6

Subscribe to this mod's changes

aifed AGENTS.md is an instructions file published in the GitHub repository ImitationGameLabs/aifed (11 stars, last pushed 2mo ago), licensed MIT. It adds 639 tokens to every session, about $0.0032 per session on Opus 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 2026-08-30.