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/lestrrat-go/helium/claude-mdgit clone --depth 1 https://github.com/lestrrat-go/heliumWrote 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/lestrrat-go/helium/claude-md)<a href="https://agentmods.dev/instructions/lestrrat-go/helium/claude-md"><img src="https://agentmods.dev/badge/instructions/lestrrat-go/helium/claude-md.svg" alt="Measured on agentmods" 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 | $0.05225 | $0.05225 |
| Opus 5 | $0.02612 | $0.02612 |
| Sonnet 5 | $0.01045 | $0.01045 |
| Haiku 4.5 | $0.00522 | $0.00522 |
Grade A, and why
helium 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 6d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helium
XML toolkit for Go covering XML parsing, SAX2-style streaming, XPath 3.1, XInclude, XSD, Relax NG, and Schematron. Started as a libxml2-style port to Go and grew broader native Go APIs and features along the way.
XPath 3.1 — XSD Version
The xpath3 package targets XSD 1.1 only. This means +INF is a valid lexical form for xs:double and xs:float, and
xs:dateTimeStamp is a recognized type. QT3 tests with dependency type="xsd-version" value="1.0" are skipped.
XSD — Version Toggle
The xsd package defaults to XSD 1.0 and treats 1.1 as opt-in via Compiler.Version(xsd.Version11) (or a
vc:minVersion="1.1" hint on the root <xs:schema> when no explicit version is set). The resolved version is frozen
onto the compiled Schema so the Validator applies the same semantics. 1.0 stays the default so existing behavior and
goldens are unchanged.
resolveVersion (compile.go) resolves in order: a forced Compiler.Version() (always wins) → a
vc:minVersion="1.1"-or-higher hint on the root → a configured Compiler.DefaultVersion(v) (the opt-in fallback for a
schema silent on version) → Version10. DefaultVersion never overrides a forced version or a vc hint — it only
chooses the fallback. The STANDALONE default stays Version10; DefaultVersion lets an embedding layer opt its schemas
into 1.1 by default while still honoring an explicit version.
Validator.SkipDatatypeIntegrityChecks(true) suppresses the document-wide datatype-integrity walks in
validateDocument (cfg.skipDatatypeIntegrity): the xs:ID/xs:IDREF/xs:IDREFS uniqueness+referential-integrity walk
(version-INDEPENDENT — runs in both 1.0 and 1.1) and the XSD 1.1-only xs:ENTITY/xs:ENTITIES walk; content-model, type,
and xs:key/unique/keyref identity-constraint validation are unaffected. It is for callers that validate an
element/subtree as a fragment and enforce document-scope ID/IDREF integrity themselves (xslt3). In 1.0 it suppresses the
ID/IDREF walk (the ENTITY walk never runs there).
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.
- 6d ago First seen · 242 lines · 5,225 tokens per session scan A 43018c7bf8f6
helium CLAUDE.md is an instructions file published in the GitHub repository lestrrat-go/helium (61 stars, last pushed 2d ago), licensed MIT. It adds 5,225 tokens to every session, about $0.0261 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
dingtalk-workspace-cli AGENTS.md
AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
agentcat-go-sdk CLAUDE.md
Claude Code instructions for agentcathq/agentcat-go-sdk, covering claude.md, what this is, build & test commands, module layout and architecture.
oastools GEMINI.md
Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.
claw-code-go CLAUDE.md
Claude Code instructions for SocialGouv/claw-code-go, covering claw-code-go and downstream consumer: iterion.