command-format

A documentation standard for structuring command files in Markdown, a plain-text format with headings and tables.

In plain words
What is it for?
It helps document slash commands with sections for invocation, arguments, step-by-step behavior, and the result shown to the user.
Why use it?
It gives commands a predictable layout, making their triggers, inputs, workflow, and output easier for an agent to follow.

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/peerjakobsen/smartspender/command-format
Clone the repo
git clone --depth 1 https://github.com/peerjakobsen/smartspender
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 780 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 $0.00780
Opus 5 $0.00000 $0.00390
Sonnet 5 $0.00000 $0.00156
Haiku 4.5 $0.00000 $0.00078

Measured 2d ago against content hash 76ef28f4b6dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-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 2d 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.

agent-os/standards/commands/command-format.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command File Format

Context

All command files follow a consistent markdown structure so Claude can execute them reliably. This standard defines the required and optional sections.

Required Structure

# /smartspender:[command]

## Trigger
How the user invokes this command (slash command and natural language alternatives).

## Arguments
What arguments the command accepts and their valid values.

## Workflow
Step-by-step instructions for Claude to follow.

## Output
What the user sees when the command completes.

Section Guidelines

Title

  • Format: # /smartspender:[command]
  • Include the full namespaced command name

Trigger

  • The primary slash command: /smartspender:sync [bank]
  • Natural language alternatives: "sync my transactions", "download Nykredit data"
  • List 2-3 natural language phrases users might say

Arguments

  • Use a table for structured argument documentation:
| Argument | Required | Values | Default |
|----------|----------|--------|---------|
| bank | yes | nykredit, danske-bank, nordea, all | - |
| period | no | 1m, 3m, 6m, 1y | 3m |

Workflow

  • Numbered steps that Claude follows in order
  • Mark human-in-the-loop steps clearly: [USER ACTION]
  • Reference specific bank adapters or skills by path: "Load banks/nykredit/BANK.md"
  • Include error handling inline: "If no CSV downloads within 10 seconds, report timeout"

Output

  • Show the exact format of the success message
  • Include an example with realistic data
  • List possible error messages

Optional Sections

Prerequisites

What must be true before this command can run (e.g., "Google Sheets MCP must be configured").

Side Effects

What changes this command makes (e.g., "Writes to Transactions sheet, logs to Action Log").

Related Commands

Other commands the user might want to run after this one.

Example Command File

# /smartspender:sync

## Trigger
- `/smartspender:sync [bank]`
- "sync my transactions"
- "download transactions from Nykredit"

## Arguments

| Argument | Required | Values | Default |
|----------|----------|--------|---------|
| bank | yes | nykredit, danske-bank, nordea, all | - |

## Prerequisites
- Google Sheets MCP configured
- Bank account added via /smartspender:add-account

## Workflow
1. Identify target bank from argument
2. Load bank adapter: `banks/{bank}/BANK.md`
3. Open bank netbank URL in browser
4. Announce: "Please log in with MitID. Let me know when you're logged in."
5. **[USER ACTION]**: User completes MitID login
6. **[USER ACTION]**: User confirms login complete
7. Navigate to export page (per bank adapter)
8. Execute export automation (per bank adapter)
9. Wait for CSV download
10. Parse CSV using `banks/{bank}/export-format.md`
11. Normalize to common transaction schema (per `skills/transaction-schema.md`)
12. Connect to Google Sheets via MCP
13. Deduplicate against existing data by tx_hash
14. Append new transactions to "Transactions" sheet
15. Log sync event to "Action Log" sheet

## Output
"Synced {count} new transactions from {bank} ({date_range})"

Example: "Synced 47 new transactions from Nykredit (Jan 15 - Feb 1)"

## Side Effects
- Writes to "Transactions" sheet
- Writes to "Action Log" sheet

Read the full file on GitHub · 114 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. 2d ago First seen · 114 lines · 0 tokens per session scan A 76ef28f4b6dd

Subscribe to this mod's changes

command-format is a command published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 780 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 2026-08-31.