helix CLAUDE.md

Claude Code instructions for developing Helix, a private system for running teams of AI agents on dedicated computer environments.

In plain words
What is it for?
Keeping Claude Code work on the helixml/helix project within its development guidelines.
Why use it?
They define the project’s communication, development, Git, and file-handling rules in one place.

Instructions file

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/helixml/helix/claude-md
Clone the repo
git clone --depth 1 https://github.com/helixml/helix
Per session 14,463 This file is loaded in full into every session.
When invoked 14,463 The same file — it is already loaded in full.
Security scan E 4 findings. Scan, not verified.
Origin unknown 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 $0.14463 $0.14463
Opus 5 $0.07232 $0.07232
Sonnet 5 $0.02893 $0.02893
Haiku 4.5 $0.01446 $0.01446

Measured yesterday against content hash 7771d98e2eb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

helix CLAUDE.md scanned grade E with 4 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

**ALWAYS use the Drone MCP tools** (`drone_build_info`, `drone_fetch_logs`, `drone_search_logs`, `drone_tail_logs`, `drone_read_logs`) when they are available. Do NOT try to extract credentials from `.env` files or use r

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get update && sudo apt-get install -y gcc libc6-dev

Recursive force deletehighDestructive command

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

- **NEVER** `rm -rf *` or `rm -rf .*` in a git repo

Makes network callslowCapability

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

- When using `curl` or the browser to test, always use `http://localhost:8080`, never `http://api:8080`.
CLAUDE.md · 812 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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 · 812 lines · 14,463 tokens per session scan E 7771d98e2eb2

Subscribe to this mod's changes

helix CLAUDE.md is an instructions file published in the GitHub repository helixml/helix (803 stars, last pushed 2d ago), with no licence file. It adds 14,463 tokens to every session, about $0.0723 per session on Opus 5. A static security scan graded it E with 4 findings (harvests environment variables, asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.