refactor(init): tighten AGENTS guidance (#20422)

packages/opencode/src/command/index.ts

@@ -85,7 +85,7 @@ export namespace Command {
 
         commands[Default.INIT] = {
           name: Default.INIT,
-          description: "create/update AGENTS.md",
+          description: "guided AGENTS.md setup",
           source: "command",
           get template() {
             return PROMPT_INITIALIZE.replace("${path}", ctx.worktree)

packages/opencode/src/command/template/initialize.txt

@@ -1,10 +1,66 @@
-Please analyze this codebase and create an AGENTS.md file containing:
-1. Build/lint/test commands - especially for running a single test
-2. Code style guidelines including imports, formatting, types, naming conventions, error handling, etc.
+Create or update `AGENTS.md` for this repository.
 
-The file you create will be given to agentic coding agents (such as yourself) that operate in this repository. Make it about 150 lines long.
-If there are Cursor rules (in .cursor/rules/ or .cursorrules) or Copilot rules (in .github/copilot-instructions.md), make sure to include them.
-
-If there's already an AGENTS.md, improve it if it's located in ${path}
+The goal is a compact instruction file that helps future OpenCode sessions avoid mistakes and ramp up quickly. Every line should answer: "Would an agent likely miss this without help?" If not, leave it out.
 
+User-provided focus or constraints (honor these):
 $ARGUMENTS
+
+## How to investigate
+
+Read the highest-value sources first:
+- `README*`, root manifests, workspace config, lockfiles
+- build, test, lint, formatter, typecheck, and codegen config
+- CI workflows and pre-commit / task runner config
+- existing instruction files (`AGENTS.md`, `CLAUDE.md`, `.cursor/rules/`, `.cursorrules`, `.github/copilot-instructions.md`)
+- repo-local OpenCode config such as `opencode.json`
+
+If architecture is still unclear after reading config and docs, inspect a small number of representative code files to find the real entrypoints, package boundaries, and execution flow. Prefer reading the files that explain how the system is wired together over random leaf files.
+
+Prefer executable sources of truth over prose. If docs conflict with config or scripts, trust the executable source and only keep what you can verify.
+
+## What to extract
+
+Look for the highest-signal facts for an agent working in this repo:
+- exact developer commands, especially non-obvious ones
+- how to run a single test, a single package, or a focused verification step
+- required command order when it matters, such as `lint -> typecheck -> test`
+- monorepo or multi-package boundaries, ownership of major directories, and the real app/library entrypoints
+- framework or toolchain quirks: generated code, migrations, codegen, build artifacts, special env loading, dev servers, infra deploy flow
+- repo-specific style or workflow conventions that differ from defaults
+- testing quirks: fixtures, integration test prerequisites, snapshot workflows, required services, flaky or expensive suites
+- important constraints from existing instruction files worth preserving
+
+Good `AGENTS.md` content is usually hard-earned context that took reading multiple files to infer.
+
+## Questions
+
+Only ask the user questions if the repo cannot answer something important. Use the `question` tool for one short batch at most.
+
+Good questions:
+- undocumented team conventions
+- branch / PR / release expectations
+- missing setup or test prerequisites that are known but not written down
+
+Do not ask about anything the repo already makes clear.
+
+## Writing rules
+
+Include only high-signal, repo-specific guidance such as:
+- exact commands and shortcuts the agent would otherwise guess wrong
+- architecture notes that are not obvious from filenames
+- conventions that differ from language or framework defaults
+- setup requirements, environment quirks, and operational gotchas
+- references to existing instruction sources that matter
+
+Exclude:
+- generic software advice
+- long tutorials or exhaustive file trees
+- obvious language conventions
+- speculative claims or anything you could not verify
+- content better stored in another file referenced via `opencode.json` `instructions`
+
+When in doubt, omit.
+
+Prefer short sections and bullets. If the repo is simple, keep the file simple. If the repo is large, summarize the few structural facts that actually change how an agent should work.
+
+If `AGENTS.md` already exists at `${path}`, improve it in place rather than rewriting blindly. Preserve verified useful guidance, delete fluff or stale claims, and reconcile it with the current codebase.

packages/web/src/content/docs/rules.mdx

@@ -15,9 +15,17 @@ To create a new `AGENTS.md` file, you can run the `/init` command in opencode.
 You should commit your project's `AGENTS.md` file to Git.
 :::
 
-This will scan your project and all its contents to understand what the project is about and generate an `AGENTS.md` file with it. This helps opencode to navigate the project better.
+`/init` scans the important files in your repo, may ask a couple of targeted questions when the codebase cannot answer them, and then creates or updates `AGENTS.md` with concise project-specific guidance.
 
-If you have an existing `AGENTS.md` file, this will try to add to it.
+It focuses on the things future agent sessions are most likely to need:
+
+- build, lint, and test commands
+- command order and focused verification steps when they matter
+- architecture and repo structure that are not obvious from filenames alone
+- project-specific conventions, setup quirks, and operational gotchas
+- references to existing instruction sources like Cursor or Copilot rules
+
+If you already have an `AGENTS.md`, `/init` will improve it in place instead of blindly replacing it.
 
 ---
 

packages/web/src/content/docs/tui.mdx

@@ -153,7 +153,7 @@ Show the help dialog.
 
 ### init
 
-Create or update `AGENTS.md` file. [Learn more](/docs/rules).
+Guided setup for creating or updating `AGENTS.md`. [Learn more](/docs/rules).
 
 ```bash frame="none"
 /init