opencode-plugin-scaffold

A project starter and repair guide for OpenCode plugins, which are TypeScript extensions that add tools or hooks to OpenCode. It supports plugins published as npm packages and plugins kept locally for automatic discovery.

In plain words
What is it for?
Use it to create a new OpenCode plugin, prepare one for publishing to npm, set up a local auto-discovered plugin, or align an existing plugin with the expected structure.
Why use it?
It removes the need to work out the required files, naming, build setup, and configuration by hand. It can also bring an existing plugin project into line with OpenCode's conventions.

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/matthewye/opencode-toolbox/opencode-plugin-scaffold
Any agent
npx skills add MatthewYe/opencode-toolbox --skill opencode-plugin-scaffold
Clone the repo
git clone --depth 1 https://github.com/MatthewYe/opencode-toolbox

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 851 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 $0.00079 $0.00851
Opus 5 $0.00039 $0.00426
Sonnet 5 $0.00016 $0.00170
Haiku 4.5 $0.00008 $0.00085

Measured yesterday against content hash 47ccfb6820ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-plugin-scaffold 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/init.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/opencode-plugin-scaffold/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCode Plugin Scaffold

Create a new opencode plugin from scratch, or align an existing project with plugin conventions.

Architecture

An opencode plugin is a TypeScript module exporting an async function:

async (PluginInput) => hooks object

PluginInput includes: project, client, $ (BunShell), directory, worktree. Hooks are organized by domain — see references/hooks.md for the full catalog.

Two deployment modes:

npm local
Location Standalone dir, published to npm .opencode/plugins/ or ~/.config/opencode/plugins/
Install "plugin" in opencode.json Auto-discovered, no config needed
Build bun builddist/ Run .ts directly (Bun native)
Naming Prefix opencode-* No requirement
Deps Listed in package.json External deps go in .opencode/package.json

Workflow

Create from scratch

Run bash scripts/init.sh for interactive prompts (mode, name, path, publish). The script generates a complete scaffold with a working example tool.

If the script is unavailable, the agent can generate files manually — the script's gen_* shell functions serve as the canonical templates (read scripts/init.sh to find them). Key templates:

  • gen_package_json — package.json with correct deps and scripts
  • gen_tsconfig_json — tsconfig extending @tsconfig/node22
  • gen_index_ts_with_tool — entry with a working example tool (default for npm mode)
  • gen_index_ts_empty — minimal empty skeleton (used for local mode and --fix)

After scaffolding: bun install && bun run src/index.ts to verify the plugin loads.

Fix an existing project

Run bash scripts/init.sh --fix <path>. The script detects what's missing and adds only what's needed — it never overwrites existing files.

If running manually without the script, follow this detection order:

  1. package.json exists? — if not, generate one. If yes, ensure @opencode-ai/plugin in dependencies.
  2. tsconfig.json exists? — if not, generate one.
  3. Entry file (src/index.ts or index.ts) exists? — if not, generate empty skeleton.
  4. Entry file exports a Plugin function? — if not, warn and abort (don't overwrite user code).
  5. dist/ directory (npm mode only)? — hint about build setup if missing.

Read the full file on GitHub · 78 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 78 lines · 79 tokens per session scan A 47ccfb6820ce

Subscribe to this mod's changes

opencode-plugin-scaffold is a skill published in the GitHub repository MatthewYe/opencode-toolbox (5 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 851 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens