AGENTS

A repository guide for the command modules used by Prime-Silo’s command-line interface. It defines which documentation belongs in the commands folder and how parent and child documentation fit together.

In plain words
What is it for?
Use it when changing commands, command help, command discovery, or the command tree. It also guides updates to related documentation and local AGENTS.md files.
Why use it?
It helps developers keep command behavior, help text, command discovery, and related documentation aligned. It prevents implementation details from being scattered across the wrong documentation files.

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/binary16labs/prime-silo/agents
Clone the repo
git clone --depth 1 https://github.com/binary16labs/prime-silo
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 5,844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.05844
Opus 5 $0.00000 $0.02922
Sonnet 5 $0.00000 $0.01169
Haiku 4.5 $0.00000 $0.00584

Measured yesterday against content hash 158530dee560, 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 yesterday.

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.

Origin

This is a copy

88% identical to AGENTS — 148 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/AGENTS.md · 513 lines

How it starts

The opening of the file, as written. The whole thing — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Purpose

commands/ contains CLI command modules used by space.

Keep this file scoped to command-module behavior and help metadata. Repo-wide CLI surface and top-level command names still belong in /AGENTS.md.

This is one of the five core docs. It owns the command-tree contract for commands/. If command-specific helper subtrees later grow their own AGENTS.md files, those local docs should own the implementation detail while this file stays focused on the command surface and conventions.

Documentation is top priority for this area. After any change to command discovery, command behavior, command help, or the command tree under commands/, update this file and the matching supplemental docs under app/L0/_all/mod/_core/documentation/docs/ in the same session before finishing.

Documentation Hierarchy

/commands/AGENTS.md stays the command-tree doc for top-level command behavior. Command-family or helper subtrees with their own local contracts should add child AGENTS.md files.

Current child docs:

  • commands/lib/supervisor/AGENTS.md

If that happens:

  • the parent command doc should own the command-family surface and cross-command conventions
  • the child doc should own the concrete subcommand or helper contract
  • update both docs when the surfaced CLI behavior and the helper boundary change together

How To Document Command Child Docs

Future command-family docs should keep the same section spine:

  • Purpose
  • Ownership
  • Command Surface or Helper Contract
  • Arguments, Output, And State Changes
  • Development Guidance

Required coverage:

  • which command files or helpers are owned
  • which subcommands, flags, environment variables, or schema entries are part of the public CLI contract
  • what the command prints and what files or runtime state it mutates
  • which shared server or helper libraries it must delegate to instead of re-implementing logic
  • which help text and examples must stay synchronized with the code

A child doc is justified only when a command family has enough behavior or helper ownership that this file would otherwise become vague or bloated.

Read the full file on GitHub · 513 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. yesterday First seen · 513 lines · 0 tokens per session scan A 158530dee560

Subscribe to this mod's changes

AGENTS is a command published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,844 tokens. A static security scan graded it A with 0 findings. It is 88% identical to AGENTS, differing in 148 lines, and is treated as a copy.