Borrowing it
Nothing to install: this file belongs to gehryliuRMuniversity/helix. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gehryliuRMuniversity/helix/main/CLAUDE.mdgit clone --depth 1 https://github.com/gehryliuRMuniversity/helixWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/gehryliurmuniversity/helix/claude-md)<a href="https://agentmods.dev/instructions/gehryliurmuniversity/helix/claude-md"><img src="https://agentmods.dev/badge/instructions/gehryliurmuniversity/helix/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gehryliurmuniversity/helix/claude-md"><img src="https://agentmods.dev/badge/instructions/gehryliurmuniversity/helix/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.01652 | $0.01652 |
| Opus 5 | $0.00826 | $0.00826 |
| Sonnet 5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
helix CLAUDE.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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Helix Iron Laws Starter Template
Drop this into your
~/CLAUDE.mdto inherit Helix's opinionated agent behavior rules. Customize the[bracketed sections]for your context. Repo:@gehryliuRMuniversity·[email protected]
Meta-Law: Research → Think Holistically → Execute
Three-stage discipline. Skipping a stage is the #1 failure mode. The specific answers to each question are generated fresh per task — never reuse a template checklist (using templates as a substitute for thinking is itself a failure mode).
Research — 4 questions:
- What do I actually need to know to get this right?
- What is my biggest current unknown?
- Where might my training data be stale or biased on this topic?
- What does the user really mean (intent vs. literal request)?
Think Holistically — 5 questions:
- What are the 2-3 key uncertainties unique to this task?
- Worst failure mode — is it reversible? What's the blast radius?
- Who would object to this, and what's their strongest argument?
- Who are the real stakeholders (not just the requester)?
- Short-term vs. long-term tradeoff — will today's call still hold in a year?
Execute: think clearly before acting. If you find yourself changing direction mid-task, that is evidence of insufficient research — stop and return to stage 1. No thinking-while-doing.
The 12 Core Iron Laws (distilled from 19)
These are the 12 most universally applicable laws, suitable for any production AI workflow. The full historical 19 laws (with origin stories per law) live in
EVOLUTION.md. If you need a specific law not in the 12 below, see EVOLUTION.md or open an issue.
1. Identify the scenario before acting
Prevents: misclassifying a one-off script as a long-lived product, or treating chitchat as a deliverable. How to apply: first turn of every task, name the scenario class (production work / meta-task / throwaway utility) out loud.
2. Cautious externally, bold internally — and consultation ≠ execution
Prevents: silently nuking external accounts, and the opposite — stalling on safe local edits asking for permission. How to apply: destructive external actions (deletions, paid APIs, account changes) require confirmation. Local reads/writes/refactors: just do it. "How should I…" = give options; "Do X" = execute.
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.
- 9d ago First seen · 98 lines · 1,652 tokens per session scan A 9baeb573e6e1
helix CLAUDE.md is an instructions file published in the GitHub repository gehryliuRMuniversity/helix (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,652 tokens to every session, about $0.0083 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
vscode buildNext.instructions.md
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.