HyMarkX CLAUDE.md

HyMarkX CLAUDE.md is an instructions file for coding agents from NAME0x0/HyMarkX. It costs 553 tokens per session, scanned A, original, Apache-2.0.

A project instruction file that defines how an AI coding team should work on the HyMarkX software project. It records roles, design rules, security limits, and required documents.

In plain words
What is it for?
Use it to guide implementation, testing, reviews, architecture decisions, documentation, and changes to the project's syntax.
Why use it?
It gives the agents a shared source of truth, reducing inconsistent changes and decisions that break the project's rules.

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/name0x0/hymarkx/claude-md
Clone the repo
git clone --depth 1 https://github.com/NAME0x0/HyMarkX

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 HyMarkX CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/name0x0/hymarkx/claude-md.svg)](https://agentmods.dev/instructions/name0x0/hymarkx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/name0x0/hymarkx/claude-md"><img src="https://agentmods.dev/badge/instructions/name0x0/hymarkx/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 553 This file is loaded in full into every session.
When invoked 553 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 $0.00553 $0.00553
Opus 5 $0.00277 $0.00277
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured 5d ago against content hash cadb2b0aaf66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

HyMarkX 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 5d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HyMarkX — working agreement

Read these before acting; they are the source of truth, not this file: VISION.md · SPEC.md · ARCHITECTURE.md · SECURITY.md · ROADMAP.md · BACKLOG.md · CONTRIBUTING.md · docs/adr/

Roles

Claude orchestrates: spec, architecture, ADRs, task briefs, review, docs, acceptance. Codex implements: production code, tests, tooling — one narrowly scoped brief at a time. Claude reviews every diff hunk and runs the tests itself before accepting. Claude writes production code only for edits smaller than the delegation overhead.

Hard invariants

  1. A document containing no HMX construct renders as CommonMark + GFM. Conformance suites are a CI gate.
  2. Only @hymarkx/parser imports micromark / mdast / hast / unified.
  3. Every AST node carries a real source span.
  4. No regex/string preprocessing of HMX syntax — tokenizer extensions only.
  5. Recoverable errors are Diagnostics with stable codes and spans, never throws.
  6. Trust mode is host-selected. No document construct can escalate it.
  7. Static documents emit zero HMX JavaScript.
  8. Syntax changes require an ADR + SPEC.md update before code.
  9. TypeScript 7 strict, ESM only, no any without justification.
  10. HMX is not "MDX with more syntax" — reject features that make native HMX approach conventional-frontend verbosity.

Current state

Phases 0-7 complete: @hymarkx/{ast,parser,compiler,formatter,language-server,cli} compile Markdown plus HMX directives to styled, interactive HTML at 652/652 CommonMark conformance, with schema-validated components, frontmatter, scoped CSS, compile-time expressions, .hmx components, and component-local state on a 591-byte gzipped runtime. Tooling: hmx build/check/fmt/dev plus an LSP server and VS Code extension.

Interactivity is safe in document mode because expressions cannot reach a host object — the runtime is a security boundary and must never gain an escape hatch without an ADR.

Phase 8 complete: foreign components are framework-agnostic islands the compiler never executes. Phase 9 (hardening, fuzzing, security audit, 0.1 publish) is next.

Read the full file on GitHub · 46 lines

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. 5d ago First seen · 46 lines · 553 tokens per session scan A cadb2b0aaf66

Subscribe to this mod's changes

HyMarkX CLAUDE.md is an instructions file published in the GitHub repository NAME0x0/HyMarkX (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 553 tokens to every session, about $0.0028 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.