scream-code AGENTS.md

A development guide for Scream Code, a monorepo—a single repository containing multiple related packages and applications. It describes package responsibilities, imports, testing, commands, and the terminal interface.

In plain words
What is it for?
It guides work on the agent runtime, language-model client, execution abstractions, Node.js SDK, terminal interface, themes, and related package tests.
Why use it?
It helps an agent understand where code belongs and how changes in one package relate to the rest of the workspace.

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/liutod/scream-code/agents-md
Clone the repo
git clone --depth 1 https://github.com/LIUTod/scream-code

Made for: Codex, OpenCode.

Per session 18,605 This file is loaded in full into every session.
When invoked 18,605 The same file — it is already loaded in full.
Security scan A 0 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 $0.18605 $0.18605
Opus 5 $0.09302 $0.09302
Sonnet 5 $0.03721 $0.03721
Haiku 4.5 $0.01861 $0.01861

Measured 2d ago against content hash 1c673add5465, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scream-code AGENTS.md scanned grade A with 0 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 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 890 lines

How it starts

The opening of the file, as written. The whole thing — 890 lines — stays where its author put it; the contents beside it link to each section on GitHub.

scream-code Development Guide

This guide covers the whole monorepo. Sections marked apps/scream-code are app-specific; the rest apply to all workspace packages.

Table of Contents

  1. Workspace Overview
  2. Code Quality & Style
  3. TUI Sanitization
  4. Testing Guidance
  5. Commands & Workflow
  6. TUI File Layout (apps/scream-code)
  7. Module Responsibilities (apps/scream-code)
  8. ScreamTUI Internal Sections (apps/scream-code)
  9. Where New Features Go (apps/scream-code)
  10. TUI Coding Conventions (apps/scream-code)
  11. How to Set Themes (apps/scream-code)
  12. MCP (apps/scream-code)
  13. Slash Commands (apps/scream-code)
  14. Agent-Core Mechanisms
  15. General Coding Requirements

Workspace Overview

Packages

Package Path Responsibility
agent-core packages/agent-core/ Agent runtime: turn loop, session, tools, MCP client, compaction, memory, goal/wolfpack
ltod packages/ltod/ Multi-provider LLM client with streaming support
jian packages/jian/ Execution environment abstractions (filesystem, process, sandbox)
node-sdk packages/node-sdk/ Node.js SDK (ScreamHarness, Session) consumed by the app
memory packages/memory/ Cross-session memory store and scoring
config packages/config/ Platform configuration, identity, model aliases
migration-legacy packages/migration-legacy/ Legacy data migration — deprecated, do not expand
apps/scream-code apps/scream-code/ CLI and terminal UI application (scream command)

Read the full file on GitHub · 890 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. 2d ago First seen · 890 lines · 18,605 tokens per session scan A 1c673add5465

Subscribe to this mod's changes

scream-code AGENTS.md is an instructions file published in the GitHub repository LIUTod/scream-code (135 stars, last pushed 2d ago), licensed MIT. It adds 18,605 tokens to every session, about $0.0930 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.