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/name0x0/hymarkx/claude-mdgit clone --depth 1 https://github.com/NAME0x0/HyMarkXWrote 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/name0x0/hymarkx/claude-md)<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>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 | $0.00553 | $0.00553 |
| Opus 5 | $0.00277 | $0.00277 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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.
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
- A document containing no HMX construct renders as CommonMark + GFM. Conformance suites are a CI gate.
- Only
@hymarkx/parserimports micromark / mdast / hast / unified. - Every AST node carries a real source span.
- No regex/string preprocessing of HMX syntax — tokenizer extensions only.
- Recoverable errors are
Diagnostics with stable codes and spans, never throws. - Trust mode is host-selected. No document construct can escalate it.
- Static documents emit zero HMX JavaScript.
- Syntax changes require an ADR +
SPEC.mdupdate before code. - TypeScript 7 strict, ESM only, no
anywithout justification. - 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.
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.
- 5d ago First seen · 46 lines · 553 tokens per session scan A cadb2b0aaf66
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.
Other instructions, from other repositories
hongdown AGENTS.md
AGENTS.md instructions for dahlia/hongdown, covering project architecture, initial setup, building, testing and website.
hongdown CLAUDE.md
Claude Code instructions for dahlia/hongdown, a project described as: A Markdown formatter that enforces Hong Minhee's Markdown style conventions.
goldmark AGENTS.md
AGENTS.md instructions for yuin/goldmark, covering instructions for agents, testing instructions, benchmark instructions, coding conventions and key point of commonmark spec.
markview CLAUDE.md
Instructions for paulhkang94/markview, covering markview — ai development guide, quick reference, architecture, mcp tools (for ai integration) and safety rules.
mdscript CLAUDE.md
Claude Code instructions for dean0x/mdscript, covering mds (markdown script), build and test, release, land the bump on main via pr (ci-gated), then and gotchas.
dingo CLAUDE.md
Claude Code instructions for MadAppGang/dingo, covering claude ai agent instructions - dingo project, 🚨🚨🚨 stop: read this before any implementation 🚨🚨🚨, the architectural principle (understand this first), why this rule exists and ✅ required approaches (the only correct ways).