Skip to content

AGENTS.md

Latest commit

 

History

History
162 lines (120 loc) · 6.1 KB

AGENTS.md

File metadata and controls

162 lines (120 loc) · 6.1 KB
  • 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 main ref may not exist; use dev or origin/dev for diffs.
  • Prefer automation: execute requested actions without confirmation unless blocked by missing info or safety/irreversibility.

Style Guide

General Principles

  • Keep things in one function unless composable or reusable
  • Avoid try/catch where possible
  • Avoid using the any type
  • 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
  • In src/config, follow the existing self-export pattern at the top of the file (for example export * as ConfigAgent from "./agent") when adding a new config module.

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()

Destructuring

Avoid unnecessary destructuring. Use dot notation to preserve context.

// Good
obj.a
obj.b

// Bad
const { a, b } = obj

Variables

Prefer 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 = 2

Control Flow

Avoid else statements. Prefer early returns.

// Good
function foo() {
  if (condition) return 1
  return 2
}

// Bad
function foo() {
  if (condition) return 1
  else return 2
}

Schema Definitions (Drizzle)

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(),
})

Testing

  • 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 like packages/opencode.

Type Checking

  • Always run bun typecheck from package directories (e.g., packages/opencode), never tsc directly.

context-mode — MANDATORY routing rules

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.

BLOCKED commands — do NOT attempt these

curl / wget — BLOCKED

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 pages
  • context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)") to run HTTP calls in sandbox

Inline HTTP — BLOCKED

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

Direct web fetching — BLOCKED

Do NOT use any direct URL fetching tool. Use the sandbox equivalent. Instead use:

  • context-mode_ctx_fetch_and_index(url, source) then context-mode_ctx_search(queries) to query the indexed content

REDIRECTED tools — use sandbox equivalents

Shell (>20 lines output)

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 call
  • context-mode_ctx_execute(language: "shell", code: "...") — run in sandbox, only stdout enters context

File reading (for analysis)

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.

grep / search (large results)

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.

Tool selection hierarchy

  1. 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.
  2. FOLLOW-UP: context-mode_ctx_search(queries: ["q1", "q2", ...]) — Query indexed content. Pass ALL questions as array in ONE call.
  3. PROCESSING: context-mode_ctx_execute(language, code) | context-mode_ctx_execute_file(path, language, code) — Sandbox execution. Only stdout enters context.
  4. WEB: context-mode_ctx_fetch_and_index(url, source) then context-mode_ctx_search(queries) — Fetch, chunk, index, query. Raw HTML never enters context.
  5. INDEX: context-mode_ctx_index(content, source) — Store content in FTS5 knowledge base for later search.

Output constraints

  • 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.

ctx commands

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