FORMAT

FORMAT is a command for coding agents from tondevrel/scientific-agent-skills. It costs 0 tokens per session (552 once invoked), scanned A, original, MIT.

A formatting guide for slash-command files. It explains how Markdown files become commands and what their front matter and instruction sections should contain.

In plain words
What is it for?
Use it when creating command files with descriptions, optional argument hints, allowed tools, step-by-step instructions, capabilities, and examples.
Why use it?
It gives command authors a consistent file layout and naming scheme. This makes commands easier to discover, configure, and understand.

Command

Part of the scientific-agent-skills plugin — 55 skills, 2 commands, 1 MCP server shipped together

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/tondevrel/scientific-agent-skills/format
Clone the repo
git clone --depth 1 https://github.com/tondevrel/scientific-agent-skills

Or install scientific-agent-skills, the plugin that ships this one along with the rest of its 55 skills, 2 commands, 1 MCP server.

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 FORMAT

README.md
[![agentmods](https://agentmods.dev/badge/commands/tondevrel/scientific-agent-skills/format.svg)](https://agentmods.dev/commands/tondevrel/scientific-agent-skills/format)
Your own site
<a href="https://agentmods.dev/commands/tondevrel/scientific-agent-skills/format"><img src="https://agentmods.dev/badge/commands/tondevrel/scientific-agent-skills/format.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 552 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 5.1 $0.00000 $0.00552
Opus 5 $0.00000 $0.00276
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 5d ago against content hash e70a64f6066f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

FORMAT 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.

commands/FORMAT.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

commands/ Format Guide

This folder contains slash commands - user-invocable actions that users explicitly call via /command-name.

File Naming

  • Files must be .md (Markdown)
  • Filename becomes the command name: build-agent.md/build-agent
  • Use kebab-case: analyze-data.md, run-experiment.md

File Structure

Each command file has two parts:

1. YAML Frontmatter (Required)

---
description: Brief description shown in command autocomplete
argument-hint: [optional-argument-placeholder]
allowed-tools: [Read, Glob, Grep, Bash, Write, Edit, WebFetch]
---

Fields:

  • description (Required): One-line description of what the command does
  • argument-hint (Optional): Placeholder text for expected argument
  • allowed-tools (Optional): List of tools the command can use

2. Markdown Body

# Command Title

Brief explanation of what this command does.

## Arguments

The user invoked this command with: $ARGUMENTS

## Instructions

Step-by-step guide for the AI when this command is invoked:

1. First, do X
2. Then, do Y
3. Finally, do Z

## Capabilities

- Capability 1
- Capability 2

## Example Usage

\`\`\`
/command-name argument1
/command-name different argument
\`\`\`

Example Command

---
description: Analyze a scientific dataset and generate a report
argument-hint: [path-to-dataset]
allowed-tools: [Read, Glob, Grep, Bash, Write]
---

# Analyze Scientific Data

This command analyzes a dataset and generates a summary report.

## Arguments

The user invoked this command with: $ARGUMENTS

## Instructions

1. Read the skill file at `data-analysis/SKILL.md` for methodology
2. Load the dataset from the provided path
3. Generate statistical summary
4. Create visualization recommendations
5. Output a markdown report

## Example Usage

\`\`\`
/analyze-data ./experiments/results.csv
/analyze-data ./data/measurements.parquet
\`\`\`

Best Practices

  1. Keep descriptions concise - They appear in autocomplete
  2. Use $ARGUMENTS - This gets replaced with user's input
  3. Reference skills - Point to relevant SKILL.md files for detailed guidance
  4. Provide examples - Show 2-3 typical usage patterns
  5. Limit scope - One command = one focused action

Read the full file on GitHub · 102 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 · 102 lines · 0 tokens per session scan A e70a64f6066f

Subscribe to this mod's changes

FORMAT is a command published in the GitHub repository tondevrel/scientific-agent-skills (20 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 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.