sxo AGENTS.md

A set of instructions for coding agents working on the SXO project, an ESM-only Node.js server-rendering framework that builds web pages from a pages folder.

In plain words
What is it for?
Use it when testing, formatting, building, or modifying SXO source code, routes, middleware, server code, and page files while following its Node.js, JSX, documentation, and change-size rules.
Why use it?
It explains the project’s commands, structure, coding rules, and files that must not be changed, helping agents make compatible edits safely.

Instructions file for CodexOpenCode

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/gc-victor/sxo/agents-md
Clone the repo
git clone --depth 1 https://github.com/gc-victor/sxo

Made for: Codex, OpenCode.

Per session 10,202 This file is loaded in full into every session.
When invoked 10,202 The same file — it is already loaded in full.
Security scan A 2 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.10202 $0.10202
Opus 5 $0.05101 $0.05101
Sonnet 5 $0.02040 $0.02040
Haiku 4.5 $0.01020 $0.01020

Measured yesterday against content hash 6d2f7823fe06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sxo AGENTS.md scanned grade A with 2 findings 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `pnpm run test:runtimes` expects: `curl`, `pnpm`, plus `bun` and `deno` installed for their sections.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

├── node.js # Node.js adapter (http, fs.watch, child_process)
AGENTS.md · 996 lines

How it starts

The opening of the file, as written. The whole thing — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Quick Start (TL;DR)

Commands:

  • pnpm test - run all tests
  • pnpm run test:file src/js/path/to/file.test.js - run single test file (dedicated script with NODE_ENV=test)
  • npm run check - lint with Biome
  • npm run format - format code
  • ./bin/sxo.js create|add|dev|build|start|clean|generate

Architecture: ESM-only Node 20+ SSR framework. Dual esbuild outputs (dist/client public, dist/server SSR bundles). Route discovery from pages/ dir, manifest at dist/server/routes.json. JSX via Rust/WASM transformer. Middleware in src/middleware.js.

Style: Small modules, ESM imports, JSDoc on exported utilities. No React patterns. Pages return full HTML docs (<html> + <head>). See .rules/jsx-standards.md for examples, .rules/jsdoc.md for docs, .rules/testing.instructions.md for tests.

Constraints: Only modify src/js/** unless directed. Never edit jsx-transformer/jsx_transformer.js, dist/**, or generated artifacts. No mega-refactors (>300 LOC / >3 files) without confirmation. Preserve AIDEV-* anchors.

Key Files: src/js/esbuild/ (build pipeline), src/js/server/ (dev/prod servers), src/js/config.js (resolution), src/js/cli/ (commands). Read full sections below for details.

Loaders: Custom esbuild server loaders can be configured via CLI flags (--loaders ".svg=file"), env (LOADERS='{"svg":"file"}'), or config file ({"loaders":{".svg":"file"}}). Format supports both .svg and svg notation (dot auto-added). Repeatable flags merge together; comma-separated values supported. Only propagated to dev/build commands. Follow standard config precedence: flags > file > env > defaults.


Special Error Pages (404/500)

Read the full file on GitHub · 996 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.

  1. yesterday First seen · 996 lines · 10,202 tokens per session scan A 6d2f7823fe06

Subscribe to this mod's changes

sxo AGENTS.md is an instructions file published in the GitHub repository gc-victor/sxo (51 stars, last pushed 1mo ago), licensed MIT. It adds 10,202 tokens to every session, about $0.0510 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.