AGENTS

AGENTS is a command for coding agents from melandlabs/openloomi. It costs 0 tokens per session (96 once invoked), scanned A, original, Apache-2.0.

Instructions for the command-line subcommands of a software project. They define where argument parsing, configuration, setup, validation, scaffolding, and user-facing errors belong.

In plain words
What is it for?
Adding or changing CLI subcommands while preserving argument handling, exit behavior, error messages, templates, and delegation to the project's runtime components.
Why use it?
They keep command-line behavior consistent and prevent core benchmark logic from being placed in the wrong part of the codebase.

Command

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 commands/melandlabs/openloomi/agents
Clone the repo
git clone --depth 1 https://github.com/melandlabs/openloomi

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 AGENTS

README.md
[![agentmods](https://agentmods.dev/badge/commands/melandlabs/openloomi/agents.svg)](https://agentmods.dev/commands/melandlabs/openloomi/agents)
Your own site
<a href="https://agentmods.dev/commands/melandlabs/openloomi/agents"><img src="https://agentmods.dev/badge/commands/melandlabs/openloomi/agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 96 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00096
Opus 5 $0.00000 $0.00048
Sonnet 5 $0.00000 $0.00019
Haiku 4.5 $0.00000 $0.00010

Measured 4d ago against content hash bccf9f0ea417, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS 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 4d 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.

benchmark/continual-learning-bench/src/commands/AGENTS.md · 9 lines

What it actually says

AGENTS.md

CLI subcommands live here.

  • Keep argument parsing, config normalization, scaffolding, setup, validation, and friendly error reporting at this boundary.
  • Preserve argparse contracts, exit behavior, and user-facing error text unless a behavior change is approved.
  • Keep templates aligned with src/interface.py and src/registry.py.
  • Do not move benchmark execution logic into commands; delegate to runtime/, runs/, tasks, and systems.
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. 4d ago First seen · 9 lines · 0 tokens per session scan A bccf9f0ea417

Subscribe to this mod's changes

AGENTS is a command published in the GitHub repository melandlabs/openloomi (1,020 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 96 tokens. 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.