skill

A command for creating a new OpenCode skill folder with standard documentation and starter directories. A skill is reusable guidance for an agent working on a particular kind of task.

In plain words
What is it for?
Use it to scaffold SKILL.md, GOTCHAS.md, HISTORY.md, asset folders, and script folders for a named skill.
Why use it?
It provides a consistent starting structure so new skills are easier to write, understand, and maintain.

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/mazumba/opencode-dockerized/skill
Clone the repo
git clone --depth 1 https://github.com/mazumba/opencode-dockerized
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,007 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 $0.00022 $0.01007
Opus 5 $0.00011 $0.00504
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured yesterday against content hash 8bdeb686f8f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill 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.

.opencode/config/commands/skill.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a new OpenCode skill. Skill name: $1. Description hint: $2.

What to build

Create the following structure under .opencode/skills/$1/:

1. .opencode/skills/$1/SKILL.md

---
name: $1
description: <concise trigger-first description, ≤150 chars, starts with "Use when...">
---

# Skill: $1

## Overview

<2–3 sentences. What this domain IS. No step-by-step. Facts only.>

## File & Directory Map

| Path | Purpose |
|---|---|
| `SKILL.md` | This reference file |
| `GOTCHAS.md` | Known failure points and fixes |
| `HISTORY.md` | Append-only change log |
| `assets/` | Templates, static files, and output scaffolds (if any) |
| `scripts/` | Helper scripts and libraries the agent can run or compose (if any) |

## Key Facts

<Dense reference material. Patterns, constraints, naming rules, API shapes, config values.
Write what an agent needs to KNOW, not what it needs to DO.
Tables, code blocks, and bullet lists — no numbered instructions.>

## Configuration

<!-- Remove this section if the skill needs no per-user setup. -->
<!-- If the skill requires user-specific values (e.g. a Slack channel, an API endpoint),
     store them in config.json in this folder. On first run, check whether config.json
     exists; if not, ask the user for the required values and write the file.
     Example shape:
{
  "channel": "#deployments",
  "environment": "production"
}
-->

## Memory

<!-- Remove this section if the skill is stateless. -->
<!-- For skills that benefit from remembering past runs (standups, recaps, deploy logs),
     store data in an append-only file in this folder (e.g. history.log or runs.json).
     Read the last N entries at the start of each run so context carries across sessions. -->

## Cross-References

- Related skill: `other-skill-name` — brief reason

2. .opencode/skills/$1/GOTCHAS.md

# Gotchas

Every real mistake, wrong assumption, and edge case discovered while working in this domain.
Add an entry whenever something breaks unexpectedly. Also log it in HISTORY.md.

---

<!-- Add entries below as they are discovered. Format:

### <Short title>

**Symptom:** What you observe / what breaks
**Root cause:** Why it happens
**Fix:** What to do instead

-->

Read the full file on GitHub · 124 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 · 124 lines · 22 tokens per session scan A 8bdeb686f8f6

Subscribe to this mod's changes

skill is a command published in the GitHub repository mazumba/opencode-dockerized (5 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 1,007 once invoked, about $0.0001 per session on Opus 5. 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.