What is opencode-x AGENTS.md?

Repository instructions for OpenCode, including its JavaScript SDK, commands, package layout, technology choices, and testing rules.

Use them when changing OpenCode tools, sessions, agents, orchestration, providers, the terminal interface, database code, or SDK generation.

They prevent common setup and verification mistakes, such as running tests from the wrong directory or using the wrong type-checker.

opencode-x AGENTS.md — Instructions file by sdeonvacation

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 instructions/sdeonvacation/opencode-x/agents-md

Clone the repo

git clone --depth 1 https://github.com/sdeonvacation/opencode-x

Made for: Codex, OpenCode.

Per session 1,522 This file is loaded in full into every session.

When invoked 1,522 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.01522	$0.01522
Opus 5	$0.00761	$0.00761
Sonnet 5	$0.00304	$0.00304
Haiku 4.5	$0.00152	$0.00152

Measured 2d ago against content hash d964e7e54637, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

opencode-x AGENTS.md scanned grade C with 1 finding 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 2d ago.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf package

AGENTS.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Regenerate JS SDK: ./packages/sdk/js/script/build.ts
ALWAYS USE PARALLEL TOOLS WHEN APPLICABLE
Default branch: main. Use main or origin/main for diffs.
Prefer automation: execute without confirmation unless blocked by missing info or safety/irreversibility.
[CRITICAL] All changes must be upstream-rebase safe.
[CRITICAL] Do NOT break provider caching, app stability or performance.

Commands

bun install
bun run --cwd packages/opencode dev
bun --cwd packages/opencode run build
bun --cwd packages/opencode test --timeout 30000
bun --cwd packages/opencode test test/tool/task.test.ts
bun --cwd packages/opencode typecheck        # tsgo, never tsc
./packages/sdk/js/script/build.ts
bun --cwd packages/opencode db <drizzle-kit-cmd>

bun test from repo root always fails (guard). Run from packages/opencode.

Structure

packages/opencode/src/
  tool/           # bash, read, edit, task, registry
  session/        # lifecycle, prompt, compaction, checkpoint
  agent/          # definitions + routing
  orchestration/  # task spawning, model resolver
  cli/cmd/tui/    # @opentui Solid-based TUI
  provider/       # AI wrappers (Anthropic, OpenAI, etc.)
  storage/        # SQLite via Drizzle
  effect/         # Effect-ts (InstanceState, run-service)
  config/         # config loading
  lsp/            # LSP integration
  mcp/            # MCP protocol
  skill/          # skill loading
  test/           # mirrors src/, fixture/ has tmpdir() helper

Tech Stack

Style

Single-word names default. Multi-word only when ambiguous. Prefer: pid, cfg, err, opts, dir, root, child, state, timeout.
Inline values used once: await Bun.file(path.join(dir, "x.json")).json() not const p = path.join(...); await Bun.file(p).json()
Dot notation over destructuring: obj.a not const { a } = obj
const over let. Ternaries/early returns over reassignment.
No else. Early returns only.
No try/catch where avoidable. No any.
Functional array methods (flatMap, filter, map) over for loops; type guards on filter.
Type inference preferred; explicit types only for exports.
Use Bun APIs (Bun.file()) when possible.
Drizzle schemas: snake_case fields, no string column name args.

Read the full file on GitHub · 118 lines

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.

2d ago First seen · 118 lines · 1,522 tokens per session scan C d964e7e54637

Subscribe to this mod's changes

opencode-x AGENTS.md is an instructions file published in the GitHub repository sdeonvacation/opencode-x (91 stars, last pushed 5d ago), licensed MIT. It adds 1,522 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Databases Languages Testing

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

opencode-x AGENTS.md