HuGR_Tools CLAUDE.md

HuGR_Tools CLAUDE.md is an instructions file for coding agents from gmhelmold/HuGR_Tools. It costs 454 tokens per session, scanned A, original, MIT.

Repository working notes for AI coding agents in HuGR_Tools, a monorepo where many related Cloudflare Workers share code. A monorepo is one repository containing multiple projects; Cloudflare Workers are small programs that run on Cloudflare’s network.

In plain words
What is it for?
Use it when working on HuGR_Tools packages, especially authentication, provider credentials, CI tests, or Cloudflare Worker deployment.
Why use it?
It gives agents the project’s conventions for authentication, credentials, testing, and deployment. This reduces guesswork when changing or deploying one of the repository’s packages.

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/gmhelmold/hugr_tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/gmhelmold/HuGR_Tools

Wrote 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.

agentmods badge for HuGR_Tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gmhelmold/hugr_tools/claude-md.svg)](https://agentmods.dev/instructions/gmhelmold/hugr_tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gmhelmold/hugr_tools/claude-md"><img src="https://agentmods.dev/badge/instructions/gmhelmold/hugr_tools/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 454 This file is loaded in full into every session.
When invoked 454 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 $0.00454 $0.00454
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 4d ago against content hash 34ac3293a410, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

HuGR_Tools 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 4d 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.

CLAUDE.md · 18 lines

What it actually says

CLAUDE.md — repo working notes for AI agents

Monorepo of 37 MCP toolkit Cloudflare Workers on a shared @hugr/kernel. Remote: HumanGuardrail/HuGR_Tools.

Overview

  • Auth: pluggable IdentityProvider, fail-closed. The kernel resolves its mode strongest-first — RS256 → HMAC → remote introspection (packages/kernel/src/identity/hugr-auth.ts). A self-hoster needs only HUGR_INLINE_HMAC_SECRET (local HS256 verification, no network call). Scopes are derived server-side from the caller's plan, never read from the token.
  • BYOK: workers store no provider key; callers send provider creds as per-request headers; fail-closed.
  • CI: GitHub-hosted (ubuntu-latest); ci.yml runs the workspace test suite. Reference figures: 8,538 passed / 1,928 credential-gated skips / 0 failed.
  • Deploy: each package is a standard Cloudflare Worker — wrangler dev locally, or wrangler deploy --env <env> to your own account. The committed wrangler.toml values (account_id, introspect URL) are placeholders — fill in your own.

Conventions

  • Worker names come from each packages/<pkg>/wrangler.toml [env.<env>].name — NOT always hugr-<pkg>-<env> (the Datadog bundles are hugr-datadog-{logs,monitors,dashboards}-<env>). Never derive a worker name from the package name; read the toml.
  • Secrets never go in the repo or in chat. Real provider tokens live in GitHub Secrets / your machine, not committed.
  • zod is v4 across the workspace (v3→v4 gotchas: 1-arg z.record → 2-arg, .default({}).prefault({}), and z.unknown() object fields need explicit .optional()).
  • Use PRs (squash) off main; CI must be green.
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. 4d ago First seen · 18 lines · 454 tokens per session scan A 34ac3293a410

Subscribe to this mod's changes

HuGR_Tools CLAUDE.md is an instructions file published in the GitHub repository gmhelmold/HuGR_Tools (0 stars, last pushed 2mo ago), licensed MIT. It adds 454 tokens to every session, about $0.0023 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.