write-command

Guidance for writing OpenCode command files, including their metadata, layout, steps, tool choices, and constraints.

In plain words
What is it for?
It is for creating, reviewing, and structuring commands used by OpenCode.
Why use it?
It helps keep command files consistent and makes their instructions easier to follow and maintain.

Skill for Claude CodeCodex

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 skills/developer239/michals-opencode-cookbook/write-command
Any agent
npx skills add developer239/michals-opencode-cookbook --skill write-command
Clone the repo
git clone --depth 1 https://github.com/developer239/michals-opencode-cookbook

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown 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 $0.00028 $0.03484
Opus 5 $0.00014 $0.01742
Sonnet 5 $0.00006 $0.00697
Haiku 4.5 $0.00003 $0.00348

Measured yesterday against content hash 20c0bfad374a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

write-command scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

**Hard rule:** Do not run any code analysis until this step is fully completed.
src/skills/write-command/SKILL.md · 439 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 439 lines · 28 tokens per session scan B 20c0bfad374a

Subscribe to this mod's changes

write-command is a skill published in the GitHub repository developer239/michals-opencode-cookbook (1 stars, last pushed 1mo ago), with no licence file. It adds 28 tokens to every session and 3,484 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

ultracite

Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or reviewing JS/TS code in a project that uses Ultracite — to…

agustinusnathaniel/nextarter-tailwind · 142 tokens

next-upgrade

Upgrade Next.js to the latest version following official migration guides and codemods.

agustinusnathaniel/nextarter-tailwind · 19 tokens

regenerate-api

Regenerate the AppointMe frontend API client (orval/TanStack Query hooks + TypeScript schemas) after the backend OpenAPI surface changes. Use this whenever backend endpoints, request/response DTOs, or other contract-affecting types are added, removed, or modified — e.g. after editing files under src/AppointMe.Api…

bravodev-hub/appointme · 136 tokens

verify

Build, launch, and drive the AppointMe stack to verify a change end-to-end at its runtime surface.

bravodev-hub/appointme · 25 tokens

add-notification-feature

Adds Firebase Cloud Messaging (FCM) push notifications to one app under apps/{app}/: device token, foreground/background/terminated handling, topic subscriptions, tap-to-open-a-page routing, and image (rich) notifications. FCM only — no CleverTap.

abhinav503/flutter-agentic · 0 tokens

connect-firebase

Connects one app under apps/{app}/ to a Firebase project. Follow every step in the guide below. Notes on how this skill splits the work.

abhinav503/flutter-agentic · 0 tokens