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.
npx agentmods add instructions/liutod/scream-code/agents-mdgit clone --depth 1 https://github.com/LIUTod/scream-codeWhat 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 | $0.18605 | $0.18605 |
| Opus 5 | $0.09302 | $0.09302 |
| Sonnet 5 | $0.03721 | $0.03721 |
| Haiku 4.5 | $0.01861 | $0.01861 |
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.
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
- Workspace Overview
- Code Quality & Style
- TUI Sanitization
- Testing Guidance
- Commands & Workflow
- TUI File Layout (apps/scream-code)
- Module Responsibilities (apps/scream-code)
- ScreamTUI Internal Sections (apps/scream-code)
- Where New Features Go (apps/scream-code)
- TUI Coding Conventions (apps/scream-code)
- How to Set Themes (apps/scream-code)
- MCP (apps/scream-code)
- Slash Commands (apps/scream-code)
- Agent-Core Mechanisms
- 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) |
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 · 890 lines · 18,605 tokens per session scan A 1c673add5465
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.
Other instructions, from other repositories
mini-swe-agent copilot-instructions.md
Instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
Octop AGENTS.md
Instructions for TencentCloud/Octop, covering agents.md, 1. collaboration principles, think before writing, simplicity first and surgical edits.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
hands-on-modern-rl AGENTS.md
AGENTS.md instructions for walkinglabs/hands-on-modern-rl, covering repository guidelines, project structure, commands, editing rules and tikz → svg workflow.