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.
npx agentmods add skills/valtterimelkko/agent-workflow-skills/opencode-pluginnpx skills add valtterimelkko/agent-workflow-skills --skill opencode-plugingit clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skillsWrote 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.
[](https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/opencode-plugin)<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/opencode-plugin"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/opencode-plugin.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00120 | $0.05540 |
| Opus 5 | $0.00060 | $0.02770 |
| Sonnet 5 | $0.00024 | $0.01108 |
| Haiku 4.5 | $0.00012 | $0.00554 |
Grade A, and why
opencode-plugin scanned grade A 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `node:child_process`, `node:util`, `node:stream` How it starts
The opening of the file, as written. The whole thing — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenCode Plugin Development Guide
Complete guide for developing, installing, and troubleshooting plugins for the OpenCode CLI (opencode). Validated against OpenCode v1.14.20 and @opencode-ai/plugin v1.14.19.
Plugin Architecture
OpenCode plugins are ESM JavaScript modules that export an async function. The function receives a PluginInput and returns Promise<Hooks>. Plugins register custom tools, hook into the agent lifecycle, and modify behavior at runtime.
Plugin function called once at load time
-> returns Hooks object
-> hooks are called per-event during the session
Plugin File Structure
my-plugin/
├── package.json # Must have "type": "module", "main": "index.js"
└── index.js # The plugin code (ESM)
Minimal package.json:
{
"name": "my-opencode-plugin",
"version": "1.0.0",
"type": "module",
"main": "index.js",
"peerDependencies": {
"@opencode-ai/plugin": ">=1.14.0"
}
}
Minimal Plugin
export default async function MyPlugin(input) {
return {
// hooks go here
};
}
This is a valid plugin that does nothing. Every hook is optional.
The Plugin Function
PluginInput
The plugin function receives a single argument with these fields:
export default async function MyPlugin(input) {
input.client // OpenCode SDK client (for server API calls)
input.project // Project metadata object
input.directory // Project root directory (e.g., "~/my-project")
input.worktree // Project worktree root
input.serverUrl // URL object for the OpenCode server
input.$ // BunShell instance for running shell commands
input.experimental_workspace // Workspace registration API
}
Key fields you'll use most:
input.directory— the project root. Use this to derive project slugs, locate config files, resolve relative paths.input.$— BunShell for running commands. Usage:await $\git status`.cwd(dir).quiet().text()`input.client— OpenCode SDK client for making API calls to the running server.
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.
- 3d ago First seen · 729 lines · 120 tokens per session scan A 1e891f8ba142
opencode-plugin is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 5,540 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…