- To regenerate the JavaScript SDK, run
./packages/sdk/js/script/build.ts. - ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE.
- The default branch in this repo is
dev. - Local
mainref may not exist; usedevororigin/devfor diffs. - Prefer automation: execute requested actions without confirmation unless blocked by missing info or safety/irreversibility.
- Keep things in one function unless composable or reusable
- Avoid
try/catchwhere possible - Avoid using the
anytype - Prefer single word variable names where possible
- Use Bun APIs when possible, like
Bun.file() - Rely on type inference when possible; avoid explicit type annotations or interfaces unless necessary for exports or clarity
- Prefer functional array methods (flatMap, filter, map) over for loops; use type guards on filter to maintain type inference downstream
Prefer single word names for variables and functions. Only use multiple words if necessary.
THIS RULE IS MANDATORY FOR AGENT WRITTEN CODE.
- Use single word names by default for new locals, params, and helper functions.
- Multi-word names are allowed only when a single word would be unclear or ambiguous.
- Do not introduce new camelCase compounds when a short single-word alternative is clear.
- Before finishing edits, review touched lines and shorten newly introduced identifiers where possible.
- Good short names to prefer:
pid,cfg,err,opts,dir,root,child,state,timeout. - Examples to avoid unless truly required:
inputPID,existingClient,connectTimeout,workerPath.
// Good
const foo = 1
function journal(dir: string) {}
// Bad
const fooBar = 1
function prepareJournal(dir: string) {}Reduce total variable count by inlining when a value is only used once.
// Good
const journal = await Bun.file(path.join(dir, "journal.json")).json()
// Bad
const journalPath = path.join(dir, "journal.json")
const journal = await Bun.file(journalPath).json()Avoid unnecessary destructuring. Use dot notation to preserve context.
// Good
obj.a
obj.b
// Bad
const { a, b } = objPrefer const over let. Use ternaries or early returns instead of reassignment.
// Good
const foo = condition ? 1 : 2
// Bad
let foo
if (condition) foo = 1
else foo = 2Avoid else statements. Prefer early returns.
// Good
function foo() {
if (condition) return 1
return 2
}
// Bad
function foo() {
if (condition) return 1
else return 2
}Use snake_case for field names so column names don't need to be redefined as strings.
// Good
const table = sqliteTable("session", {
id: text().primaryKey(),
project_id: text().notNull(),
created_at: integer().notNull(),
})
// Bad
const table = sqliteTable("session", {
id: text("id").primaryKey(),
projectID: text("project_id").notNull(),
createdAt: integer("created_at").notNull(),
})- Avoid mocks as much as possible
- Test actual implementation, do not duplicate logic into tests
- Tests cannot run from repo root (guard:
do-not-run-tests-from-root); run from package dirs likepackages/opencode.
- Always run
bun typecheckfrom package directories (e.g.,packages/opencode), nevertscdirectly.
You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session.
Any shell command containing curl or wget will be intercepted and blocked by the context-mode plugin. Do NOT retry.
Instead use:
context-mode_ctx_fetch_and_index(url, source)to fetch and index web pagescontext-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")to run HTTP calls in sandbox
Any shell command containing fetch('http, requests.get(, requests.post(, http.get(, or http.request( will be intercepted and blocked. Do NOT retry with shell.
Instead use:
context-mode_ctx_execute(language, code)to run HTTP calls in sandbox — only stdout enters context
Do NOT use any direct URL fetching tool. Use the sandbox equivalent. Instead use:
context-mode_ctx_fetch_and_index(url, source)thencontext-mode_ctx_search(queries)to query the indexed content
Shell is ONLY for: git, mkdir, rm, mv, cd, ls, npm install, pip install, and other short-output commands.
For everything else, use:
context-mode_ctx_batch_execute(commands, queries)— run multiple commands + search in ONE callcontext-mode_ctx_execute(language: "shell", code: "...")— run in sandbox, only stdout enters context
If you are reading a file to edit it → reading is correct (edit needs content in context).
If you are reading to analyze, explore, or summarize → use context-mode_ctx_execute_file(path, language, code) instead. Only your printed summary enters context.
Search results can flood context. Use context-mode_ctx_execute(language: "shell", code: "grep ...") to run searches in sandbox. Only your printed summary enters context.
- GATHER:
context-mode_ctx_batch_execute(commands, queries)— Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. - FOLLOW-UP:
context-mode_ctx_search(queries: ["q1", "q2", ...])— Query indexed content. Pass ALL questions as array in ONE call. - PROCESSING:
context-mode_ctx_execute(language, code)|context-mode_ctx_execute_file(path, language, code)— Sandbox execution. Only stdout enters context. - WEB:
context-mode_ctx_fetch_and_index(url, source)thencontext-mode_ctx_search(queries)— Fetch, chunk, index, query. Raw HTML never enters context. - INDEX:
context-mode_ctx_index(content, source)— Store content in FTS5 knowledge base for later search.
- Keep responses under 500 words.
- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
- When indexing content, use descriptive source labels so others can
search(source: "label")later.
| Command | Action |
|---|---|
ctx stats |
Call the stats MCP tool and display the full output verbatim |
ctx doctor |
Call the doctor MCP tool, run the returned shell command, display as checklist |
ctx upgrade |
Call the upgrade MCP tool, run the returned shell command, display as checklist |