ceos/opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: add v2 configuration reference

Browse source
This commit is contained in:
Dax Raad 2026-07-06 20:09:08 -04:00
commit bd947658bb
10 changed files with 1601 additions and 483 deletions
Download patch file Download diff file Expand all files Collapse all files

452
packages/core/src/plugin/skill/customize-opencode.md
View file

@ -1,452 +0,0 @@
<!--
Built-in skill. Name and description are registered in code at
packages/core/src/plugin/skill.ts
and CUSTOMIZE_OPENCODE_SKILL_DESCRIPTION). The body below becomes the
skill's content.
-->
# Customizing opencode
opencode validates its own config strictly and refuses to start when a field
is wrong. The shapes below cover the common surface area, but they are a
**summary, not the source of truth**.
## Full schema reference
The authoritative list of every config option — with field types, enums,
defaults, and descriptions — lives in the published JSON Schema:
**<https://opencode.ai/config.json>**
If a field is not documented in this skill, or you need to confirm an exact
shape before writing config, **fetch that URL and read the schema directly**
rather than guessing. opencode hard-fails on invalid config, so the cost of a
wrong shape is a broken startup.
Independently, every `opencode.json` should declare
`"$schema": "https://opencode.ai/config.json"` so the user's editor catches
mistakes as they type.
## Applying changes
Config is loaded once when opencode starts and is not hot-reloaded. After
saving changes to `opencode.json`, an agent file, a skill, a plugin, or any
other config-time file, **tell the user to quit and restart opencode** for
the changes to take effect. The running session will keep using the
already-loaded config until then.
## Where files live
| Scope | Path |
| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
| Project config | `./opencode.json`, `./opencode.jsonc`, or `.opencode/opencode.json` (opencode walks up from the cwd to the worktree root) |
| Global config | `~/.config/opencode/opencode.json` (NOT `~/.opencode/`) |
| Project agents | `.opencode/agent/<name>.md` or `.opencode/agents/<name>.md` |
| Global agents | `~/.config/opencode/agent(s)/<name>.md` |
| Project commands | `.opencode/command/<name>.md` or `.opencode/commands/<name>.md` |
| Global commands | `~/.config/opencode/command(s)/<name>.md` |
| Project skills | `.opencode/skill(s)/<name>/SKILL.md` |
| Global skills | `~/.config/opencode/skill(s)/<name>/SKILL.md` |
| External skills (auto-loaded) | `~/.claude/skills/<name>/SKILL.md`, `~/.agents/skills/<name>/SKILL.md` |
Configs from each scope are deep-merged. Project overrides global. Unknown
top-level keys in `opencode.json` are rejected with `ConfigInvalidError`.
## opencode.json
Every field is optional.
```json
{
"$schema": "https://opencode.ai/config.json",
"username": "string",
"model": "provider/model-id",
"small_model": "provider/model-id",
"default_agent": "agent-name",
"shell": "/bin/zsh",
"logLevel": "DEBUG" | "INFO" | "WARN" | "ERROR",
"share": "manual" | "auto" | "disabled",
"autoupdate": true | false | "notify",
"snapshot": true,
"instructions": ["AGENTS.md", "docs/style.md"],
"skills": {
"paths": [".opencode/skills", "/abs/path/to/skills"],
"urls": ["https://example.com/.well-known/skills/"]
},
"references": {
"docs": {
"path": "../docs",
"description": "Use for product behavior and documentation conventions"
},
"sdk": {
"repository": "owner/sdk",
"branch": "main",
"description": "Use for SDK implementation details",
"hidden": true
}
},
"agent": {
"my-agent": {
"model": "anthropic/claude-sonnet-4-6",
"mode": "subagent",
"description": "...",
"permission": { "edit": "deny" }
}
},
"command": {
"deploy": { "description": "...", "template": "..." }
},
"provider": {
"anthropic": { "options": { "apiKey": "..." } }
},
"disabled_providers": ["openai"],
"enabled_providers": ["anthropic"],
"mcp": {
"playwright": {
"type": "local",
"command": ["npx", "-y", "@playwright/mcp"],
"enabled": true,
"env": {}
},
"remote-thing": {
"type": "remote",
"url": "https://...",
"headers": { "Authorization": "Bearer ..." }
}
},
"plugin": [
"opencode-gemini-auth",
"opencode-foo@1.2.3",
"./local-plugin.ts",
["opencode-bar", { "option": "value" }]
],
"permission": {
"edit": "deny",
"bash": { "git *": "allow", "*": "ask" }
},
"formatter": false,
"lsp": false,
"experimental": {
"primary_tools": ["edit"],
"mcp_timeout": 30000
},
"tool_output": { "max_lines": 200, "max_bytes": 8192 },
"compaction": { "auto": true, "tail_turns": 15 }
}
```
Shape notes worth being explicit about:
- `model` always carries a provider prefix: `"anthropic/claude-sonnet-4-6"`.
- `skills` is an object with `paths` and/or `urls`, not an array.
- `references` is an object keyed by alias. Each value is a local path, Git repository, or string shorthand.
- `agent` is an object keyed by agent name, not an array.
- `command` is an object keyed by command name, not an array.
- `plugin` is an array of strings or `[name, options]` tuples, not an object.
- `mcp[name].command` is an array of strings, never a single string. `type` is required.
- `permission` is either a string action or an object keyed by tool name.
## Skills
opencode's skill loader scans for `**/SKILL.md` inside skill directories. The
file is named `SKILL.md` exactly, and lives in its own folder named after the
skill:
```
.opencode/skills/my-skill/SKILL.md
```
Frontmatter:
```markdown
---
name: my-skill
description: One sentence covering what this skill does AND when to trigger it. Front-load the literal keywords or filenames the user is likely to say.
---
# My Skill
(skill body in markdown: instructions, examples, references)
```
- `name` is required, lowercase hyphen-separated, up to 64 chars, and matches the folder name.
- `description` is effectively required: skills without one are filtered out and never surfaced to the model. Cover both _what_ the skill does and _when_ to use it. Write in third person ("Use when...", not "I help with..."). Front-load concrete trigger keywords and filenames; gate with "Use ONLY when..." if the skill should stay quiet on adjacent topics.
- Optional: `license`, `compatibility`, `metadata` (string-string map).
Register skills from non-default locations via `skills.paths` (scanned
recursively for `**/SKILL.md`) and `skills.urls` (each URL serves a list of
skills).
## References
References make local directories and Git repositories outside the active
project available as supporting context. Configure them under `references`,
keyed by the alias used in `@` autocomplete:
```json
{
"references": {
"docs": {
"path": "../product-docs",
"description": "Use for product behavior and terminology"
},
"effect": {
"repository": "Effect-TS/effect",
"branch": "main",
"description": "Use for Effect implementation details"
}
}
}
```
Local `path` values may be relative to the declaring config, absolute, or use
`~/`. Git `repository` values accept Git URLs, host/path references, and GitHub
`owner/repo` shorthand; `branch` is optional. Both forms support optional
`description` and `hidden` fields.
- Only references with a `description` are advertised to agents in system context.
- `hidden: true` removes a reference from TUI `@` autocomplete only. It remains available to agents and by direct path.
- Reference directories are automatically allowed through the external-directory boundary; normal read/edit/tool permissions still apply.
- String shorthand is supported: use `"docs": "../docs"` for local paths or `"effect": "Effect-TS/effect"` for Git repositories.
## Agents
Two ways to define an agent. Use the file form for anything non-trivial.
### Inline (in `opencode.json`)
```json
{
"agent": {
"my-reviewer": {
"description": "Reviews PRs for style violations.",
"mode": "subagent",
"model": "anthropic/claude-sonnet-4-6",
"permission": { "edit": "deny", "bash": "ask" },
"prompt": "You are a strict PR reviewer..."
}
}
}
```
### File
```
.opencode/agent/my-reviewer.md OR .opencode/agents/my-reviewer.md
```
```markdown
---
description: Reviews PRs for style violations.
mode: subagent
model: anthropic/claude-sonnet-4-6
permission:
edit: deny
bash: ask
---
You are a strict PR reviewer. Focus on...
```
The file body becomes the agent's `prompt`. Do not also put `prompt:` in the
frontmatter.
`mode` is one of `"primary"`, `"subagent"`, `"all"`.
Allowed top-level frontmatter fields: `name, model, variant, description, mode,
hidden, color, steps, options, permission, disable, temperature, top_p`. Any
unknown field is silently routed into `options`.
To disable a built-in agent: `agent: { build: { disable: true } }`, or in a
file, `disable: true` in frontmatter.
`default_agent` must point to a non-hidden, primary-mode agent.
### Built-in agents
opencode ships with `build`, `plan`, `general`, `explore`. Hidden internal agents:
`compaction`, `title`, `summary`. To override a built-in's fields, define the
same key in `agent: { <name>: { ... } }`.
## Commands
opencode's command loader scans for `**/*.md` inside command directories. The
file is named after the command, and lives directly inside the `command` folder:
```
.opencode/command/deploy.md
```
Frontmatter:
```markdown
---
description: One sentence describing what the command does.
agent: build
model: anthropic/claude-sonnet-4-6
---
(command body in markdown: the prompt opencode runs, with $ARGUMENTS for the user's input)
```
- `template` is the command body — everything below the frontmatter — and is required: it is the prompt opencode runs when the command is invoked. Do not also put a `template:` key in the frontmatter.
- `$ARGUMENTS` is replaced with everything the user typed after the command; `$1`, `$2`, … pull individual positional arguments.
- Optional: `description`, `agent`, `model`, `variant`, `subtask`.
## Plugins
`plugin:` is an array. Each entry is one of:
```json
"plugin": [
"opencode-gemini-auth", // npm spec, latest
"opencode-foo@1.2.3", // npm spec, pinned
"./local-plugin.ts", // file path, relative to the declaring config
"file:///abs/path/plugin.js", // file URL
["opencode-bar", { "key": "val" }] // tuple form with options
]
```
Auto-discovered plugins (no config entry needed): any `*.ts` or `*.js` file in
`.opencode/plugin/` or `.opencode/plugins/`.
A plugin module exports `default` (or any named export) of type
`Plugin = (input: PluginInput, options?) => Promise<Hooks>`. The export is a
function, not a plain object literal, and the function returns an object
(return `{}` if there is nothing to register).
```ts
import type { Plugin } from "@opencode-ai/plugin"
export default (async ({ client, project, directory, $ }) => {
return {
config: (cfg) => {
// cfg is the live merged config; mutate fields here.
},
"tool.execute.before": async (input, output) => {
// mutate output.args before the tool runs
},
}
}) satisfies Plugin
```
Hook surface (mutate `output` in place; return `void`):
- `event(input)`: every bus event
- `config(cfg)`: once on init with the merged config
- `chat.message`, `chat.params`, `chat.headers`
- `tool.execute.before`, `tool.execute.after`
- `tool.definition`
- `command.execute.before`
- `shell.env`
- `permission.ask`
- `experimental.chat.messages.transform`, `experimental.chat.system.transform`,
`experimental.session.compacting`, `experimental.compaction.autocontinue`,
`experimental.text.complete`
Special object-shaped (not callbacks): `tool: { my_tool: { ... } }`,
`auth: { ... }`, `provider: { ... }`.
## MCP servers
`mcp:` is an object keyed by server name. Each server is discriminated by
`type`:
```json
{
"mcp": {
"playwright": {
"type": "local",
"command": ["npx", "-y", "@playwright/mcp"],
"enabled": true,
"env": { "BROWSER": "chromium" }
},
"github": {
"type": "remote",
"url": "https://...",
"enabled": true,
"headers": { "Authorization": "Bearer {env:GITHUB_TOKEN}" }
},
"old-server": { "enabled": false }
}
}
```
`command` is an array of strings. `type` is required. Use `enabled: false` to
disable a server inherited from a parent config. String values such as header
tokens support `{env:VAR}` interpolation (and `{file:path}`); the shell-style
`${VAR}` is not substituted.
## Permissions
```json
"permission": {
"edit": "deny",
"bash": { "git *": "allow", "rm *": "deny", "*": "ask" },
"external_directory": { "~/secrets/**": "deny", "*": "allow" }
}
```
Actions: `"allow"`, `"ask"`, `"deny"`.
Per-tool value forms: `"allow"` shorthand (treated as `{"*": "allow"}`), or an
object `{ pattern: action }`. Within an object, **insertion order matters**.
opencode evaluates the LAST matching rule, so put broad rules first and narrow
rules last.
`permission: "allow"` (a string at the top level) is shorthand for "allow
everything" and is rarely what the user wants.
Known permission keys: `read, edit, glob, grep, list, bash, task,
external_directory, todowrite, question, webfetch, websearch, lsp, doom_loop,
skill`. Some of these (`todowrite,
question, webfetch, websearch, doom_loop`) only accept a flat
action, not a per-pattern object.
`external_directory` patterns are filesystem paths (use `~/`, absolute paths,
or globs like `~/projects/**`).
Per-agent `permission:` overrides top-level `permission:`. Plan Mode lives on
the `plan` agent's permission ruleset (`edit: deny *`).
## Escape hatches
When a user's config is broken and opencode won't start, these env vars help:
- `OPENCODE_DISABLE_PROJECT_CONFIG=1`: skip the project's local `opencode.json`
and start from globals only. Run from the project directory, opencode loads,
the user edits the broken file, then they restart without the flag.
- `OPENCODE_CONFIG=/path/to/file.json`: load an additional explicit config.
- `OPENCODE_CONFIG_CONTENT='{"$schema":"https://opencode.ai/config.json"}'`:
inject inline JSON as a final local-scope merge.
- `OPENCODE_DISABLE_DEFAULT_PLUGINS=1`: skip default plugins.
- `OPENCODE_PURE=1`: skip external plugins entirely.
- `OPENCODE_DISABLE_EXTERNAL_SKILLS=1`,
`OPENCODE_DISABLE_CLAUDE_CODE_SKILLS=1`: skip the external skill scans under
`~/.claude/` and `~/.agents/`.
## When proposing edits
- Validate against the schema before writing. If you are unsure of a field's
exact shape, or the field is not covered in this skill, fetch
`https://opencode.ai/config.json` and read the schema rather than guessing.
- Preserve `$schema` and any existing fields the user did not ask to change.
- For agent, command, skill, and plugin definitions, prefer creating new files
in the correct location over inlining everything in `opencode.json`.
- If the user's existing config is malformed, point them at the env-var escape
hatches above so they can edit from inside opencode without breaking their
session.
- After saving any config change, remind the user to quit and restart opencode
— running sessions keep using the already-loaded config.

112
packages/core/src/plugin/skill/opencode.md Normal file
View file

@ -0,0 +1,112 @@
# OpenCode
Use this guide as the starting point for work involving OpenCode itself. It
covers the core concepts needed to configure and customize OpenCode, extend it
with plugins, and build integrations with the OpenCode SDK, clients, and API.
Full documentation is available at <https://opencode.mintlify.site/>. Consult
it when this overview does not contain enough detail for the task.
## Configuration
OpenCode configuration uses JSON or JSONC. Include the published schema so the
user's editor can validate fields and provide autocomplete:
```jsonc
{
"$schema": "https://opencode.ai/config.json"
}
```
Global configuration lives at `~/.config/opencode/opencode.json(c)` and applies
to every project for that user. Project configuration can live in any directory
as `opencode.json(c)` or `.opencode/opencode.json(c)`, including nested packages
in a monorepo.
When OpenCode starts, it searches upward from the current directory for project
configuration and merges the files it finds with the global configuration.
Common configuration fields include `model`, `default_agent`, `permissions`,
`agents`, `commands`, `plugins`, `providers`, `mcp`, `skills`, `instructions`,
`references`, `formatter`, and `lsp`.
Do not guess field names or shapes. Use
<https://opencode.ai/config.json> as the source of truth and preserve unrelated
settings when editing an existing file.
See the [full configuration guide](https://opencode.mintlify.site/config) for
every field, examples, config locations, and links to dedicated feature guides.
## Service
OpenCode uses a client-server architecture. Interfaces such as the TUI connect
to a background OpenCode service, which owns sessions, configuration, plugins,
permissions, and tool execution.
Configuration and related files are typically watched and reloaded while the
service is running. If a change does not appear, restart the service:
```sh
opencode2 service restart
```
Check its status after restarting:
```sh
opencode2 service status
```
## API
OpenCode exposes an HTTP API from its server. The API is described by an
OpenAPI document available from the running server at `/openapi.json`.
Use OpenCode's built-in `api` command for local requests. It discovers the same
background server used by the TUI, starts it when necessary, and applies the
server's authentication headers automatically.
Call an endpoint with an HTTP method and path:
```sh
opencode2 api get /api/health
```
Pass a request body with `--data` or `-d`, and additional headers with
`--header` or `-H`:
```sh
opencode2 api post /api/example --data '{"key":"value"}'
opencode2 api get /api/example --header 'X-Example:value'
```
Request bodies default to `Content-Type: application/json`. When OpenCode is
connected to an explicit server instead of its managed background service, use
the same configured server and authentication context rather than constructing
an unauthenticated request separately.
See the [full API reference](https://opencode.mintlify.site/api) for available
endpoints, parameters, request bodies, and response schemas. The
raw [OpenAPI specification](https://opencode.mintlify.site/openapi.json) is also
available for code generation and other tooling.
## Troubleshooting
OpenCode runs a client and a background server. Start by determining whether a
problem belongs to the client, the shared server, or one project.
- Check the service with `opencode2 service status` and verify the API with
`opencode2 api get /api/health`.
- Inspect `~/.local/share/opencode/log/opencode.log`. Filter `role=cli` for
client startup and `role=server` for sessions, providers, plugins,
permissions, and tools.
- Run one reproduction with `OPENCODE_LOG_LEVEL=DEBUG` when normal logs are not
sufficient.
- Do not delete or edit the database, service registration, or service config
while diagnosing a problem. Back up persistent data before inspecting it
with external tools.
- Redact API keys, authorization headers, prompts, file contents, and other
sensitive data before sharing diagnostics.
See the [full troubleshooting guide](https://opencode.mintlify.site/troubleshooting)
for service lifecycle commands, API inspection, log locations, explicit server
connections, issue-reporting details, and local development paths.