What is command-design?

A design standard for slash commands, which are commands users invoke directly by typing a name such as /command.

Use it when designing command names, arguments, completion messages, and confirmation points for irreversible or login-related actions.

It helps commands stay focused, predictable, understandable, and safe when they need authentication or user confirmation.

command-design — Command by peerjakobsen

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-design

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 554 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00554
Opus 5	$0.00000	$0.00277
Sonnet 5	$0.00000	$0.00111
Haiku 4.5	$0.00000	$0.00055

Measured 2d ago against content hash 9cddbaa65632, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-design 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-design.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command Design Principles

Context

Commands are slash commands that users invoke directly. Each command triggers a specific workflow. This standard defines how to design commands that are intuitive and reliable.

Design Principles

One Command, One Job

Each command should do one clear thing. Don't combine unrelated actions.

Good: /smartspender:sync nykredit -- syncs transactions from one bank Bad: /smartspender:sync-and-analyze -- combining two distinct workflows

Predictable Arguments

Users should be able to guess valid arguments.

Bank commands accept bank IDs: nykredit, danske-bank
Time commands accept months: january, 2026-01
Service commands accept service names: netflix, spotify
Use all as a special argument when applicable: /smartspender:sync all

Clear Feedback

Every command should report what it did when finished.

Good: "Synced 47 new transactions from Nykredit (Jan 15 - Feb 1)" Bad: "Done."

Human-in-the-Loop by Default

Any step that requires authentication or irreversible action should pause for user confirmation.

Required handoff points:

Bank login (MitID)
Service login (for cancellation)
Final cancellation confirmation
Any action that spends money or changes account settings

Graceful Failure

Commands should handle common failures explicitly:

No internet / bank site down: "Could not reach Nykredit netbank. Please check your connection."
Session expired: "Bank session has expired. Please log in again with MitID."
No new data: "No new transactions found since last sync (Jan 28)."
MCP not configured: "Google Sheets MCP is not configured. Run /smartspender:add-account first."

Command Naming Rules

Use verbs for actions: sync, analyze, cancel
Use nouns for views: overview, report, subscriptions
Keep names short -- one word when possible
Use hyphens for multi-word: add-account
Namespace: all commands use /smartspender: prefix

Workflow Design Checklist

Read the full file on GitHub · 62 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.

2d ago First seen · 62 lines · 0 tokens per session scan A 9cddbaa65632

Subscribe to this mod's changes

command-design is a command published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 554 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.

Building agents claude-code-plugin claude-code-plugins personal-finance

derive-tests

Turn documented intent into a test-coverage map — inventory the tests that exist today, derive use-case cases from the system docs, separate existing coverage from proposed tests and unverified gaps, mark each unit / guarded-live / manual, and recommend a green-before-merge CI gate.

phuryn/pm-skills · 55 tokens

command-design