hyalo CLAUDE.md

hyalo CLAUDE.md is an instructions file for coding agents from ractive/hyalo. It costs 1,495 tokens per session, scanned A, original, MIT.

A project instruction file for the hyalo codebase. It tells coding agents how to delegate work, store Markdown knowledge-base notes, build the Rust program, and use hyalo to manage those notes.

In plain words
What is it for?
For maintaining a hyalo knowledge base, recording research and design decisions, planning iterations, and checking the Rust program before and after changes.
Why use it?
It gives agents one shared workflow and keeps research, decisions, and plans in a consistent place. It also requires agents to test their own documentation tool while working.

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/ractive/hyalo/claude-md
Clone the repo
git clone --depth 1 https://github.com/ractive/hyalo

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 hyalo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ractive/hyalo/claude-md.svg)](https://agentmods.dev/instructions/ractive/hyalo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ractive/hyalo/claude-md"><img src="https://agentmods.dev/badge/instructions/ractive/hyalo/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,495 This file is loaded in full into every session.
When invoked 1,495 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 $0.01495 $0.01495
Opus 5 $0.00747 $0.00747
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00150 $0.00150

Measured 4d ago against content hash ba1e25e0a9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hyalo 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Delegate the work to agents whenever possible to avoid automatic context compaction.

Documentation

Keep all documentation in ./hyalo-knowledgebase/ as *.md markdown files with YAML frontmatter (text, numbers, checkboxes, dates, lists). Use it as your second brain:

  • Research outcomes → research/
  • Design decisions → decision-log.md
  • Iteration plans → iterations/iteration-NN-slug.md (one file per iteration, markdown task lists for steps/tasks/ACs)

Organize in subfolders. Use [[wikilinks]] for cross-references. Keep Obsidian-compatible.

Dogfooding

After an iteration or before starting one, build hyalo with "cargo build --release". Then use target/release/hyalo to work with the documentation in ./hyalo-knowledgebase/ to dogfood what you did. Mention issues you have using it, propose features you'd like to have.

Always use hyalo for knowledgebase interactions — never use Edit/Read/Grep directly:

  • Search/filter: hyalo find --property status=planned --tag iteration
  • Body search: hyalo find "broken links" or regex: hyalo find -e 'TODO|FIXME'
  • Title regex: hyalo find --property 'title~=link'
  • Inspect config: hyalo config (text) or hyalo config --format json — shows effective dir, config path, hints, format, site_prefix, and the effective [links.auto] auto-link settings; --raw adds the file's text, and results.malformed / results.parse_error report a config that exists but does not parse. JSON uses the standard envelope, so hyalo config --jq '.results.dir' works
  • Overview: hyalo summary, hyalo properties, hyalo tags
  • Mutate frontmatter: hyalo set, hyalo remove, hyalo append (e.g., hyalo set iterations/iteration-16-robustness.md --property status=completed)
  • Toggle tasks: hyalo task toggle <path> --all (whole file), --section "Tasks" (by heading), --line 5,7,9 (specific lines)
  • Lint frontmatter + markdown body: hyalo lint, hyalo lint --rule MD013 --detailed, hyalo lint --rule-prefix HYALO, hyalo lint --strict (promotes missing-type and undeclared-property warnings to errors), hyalo lint --fix --dry-run, hyalo lint --fix, hyalo lint --fix --fix-rule HYALO001
  • Manage lint rules: hyalo lint-rules list, hyalo lint-rules show MD013, hyalo lint-rules set MD013 --enabled false, hyalo lint-rules set MD013 --severity error, hyalo lint-rules remove MD013
  • Manage schemas: hyalo types list, hyalo types show <name>, hyalo types set <name> --required title,date
  • Only fall back to Edit for body content changes (markdown prose) that hyalo can't handle
  • Do NOT pass --dir hyalo-knowledgebase/.hyalo.toml already sets it as the default
  • Follow hints: hyalo outputs drill-down hints by default — read and follow them to navigate deeper into the knowledgebase. Use --no-hints only when you need raw output. Hints prefixed -> are read-only and safe to run; a => prefix with a [writes] tag (JSON: "writes": true) means running it modifies the vault or .hyalo.toml.

Read the full file on GitHub · 91 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. 4d ago First seen · 91 lines · 1,495 tokens per session scan A ba1e25e0a9fd

Subscribe to this mod's changes

hyalo CLAUDE.md is an instructions file published in the GitHub repository ractive/hyalo (24 stars, last pushed today), licensed MIT. It adds 1,495 tokens to every session, about $0.0075 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.

Related

Other instructions, from other repositories

data-olympus AGENTS.md

Instructions for knaisoma/data-olympus, covering data olympus, project overview, architecture, development workflow and code standards.

knaisoma/data-olympus · 1,583 tokens

data-olympus copilot-instructions.md

Instructions for knaisoma/data-olympus: Read and follow all instructions in AGENTS.md. Read and follow all rules in .rules/. Read and follow the global Codex and Claude Code collaboration rule in /kn-projects/company-knowledge/tooling/codex-claude-collaboration.md.

knaisoma/data-olympus · 80 tokens

data-olympus CLAUDE.md

Instructions for knaisoma/data-olympus: Read and follow all instructions in AGENTS.md. Read and follow all rules in .rules/. Read and follow the global Codex and Claude Code collaboration rule in /kn-projects/company-knowledge/tooling/codex-claude-collaboration.md.

knaisoma/data-olympus · 80 tokens

robust-llm-wiki CLAUDE.md

Instructions for KevinYoung-Kw/robust-llm-wiki, covering claude.md, the original karpathy baseline, made explicit and repository-specific policy.

KevinYoung-Kw/robust-llm-wiki · 514 tokens

llm-atomic-wiki CLAUDE.md

Claude Code instructions for cablate/llm-atomic-wiki, covering claude.md — schema for llms operating this repo, mental model, atom format (spec), frontmatter (yaml, required) and filename.

cablate/llm-atomic-wiki · 2,741 tokens

kaas CLAUDE.md

Instructions for bybit-exchange/kaas, covering claude.md, behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.

bybit-exchange/kaas · 820 tokens