What is human-native-knowledge-skills CLAUDE.md?

Repository instructions for agents making changes to a collection of reusable skills, rather than using those skills in another project.

Use them when editing this skills repository, preparing changes, or reviewing work before opening a pull request.

They explain which interfaces and documents must remain stable and how changes must be versioned and checked.

How seongjaeryu/human-native-knowledge-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to seongjaeryu/human-native-knowledge-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/seongjaeryu/human-native-knowledge-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/seongjaeryu/human-native-knowledge-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/seongjaeryu/human-native-knowledge-skills/claude-md/github.svg)](https://agentmods.dev/instructions/seongjaeryu/human-native-knowledge-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/seongjaeryu/human-native-knowledge-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/seongjaeryu/human-native-knowledge-skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/seongjaeryu/human-native-knowledge-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/seongjaeryu/human-native-knowledge-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 763 This file is loaded in full into every session.

When invoked 763 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00763	$0.00763
Opus 5	$0.00381	$0.00381
Sonnet 5	$0.00153	$0.00153
Haiku 4.5	$0.00076	$0.00076

Measured 10d ago against content hash 32c42184bf00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

human-native-knowledge-skills 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 10d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on this repository — instructions for AI agents

Boundary first. If you are here to consume the skill — to install it into a target project — this file is not for you: read llm.txt and follow orchestrator.md. This file is only for agents (and their human partners) making changes to this repository itself.

What this repository is to you

Every document here is load-bearing. The skill documents are not prose — they are instructions that shape agent behavior in every project this skill is installed into. A wrong sentence here becomes a wrong action in someone else's repository. Treat specification text with the care you would give production code.

Non-negotiable rules

Frozen interfaces stay frozen. The interfaces marked "Frozen interface" in skill/02, 03, 07, 08, 09, 10 (card fields, identifier schemes, command shapes, the frontmatter grammar, the environment contract) change only with a version increment of the owning document, a recorded reason (per skill/06), and a passing core-audit. No silent edits, ever.
Derive or delete. Every rule you add must state which degree of understanding it serves (first or nth — core/philosophy.md §10). A rule that serves neither does not belong here, however clever.
Never restate the core. Cite core/philosophy.md by anchor; restating it is an audit failure (D2 in core/audit.md).
Honesty of the record. No invented metrics, no aspirational claims written as facts, no "should work" — this repository's README publishes only measured results, and your pull request must too. "It works" is not evidence; command output is.
Zero dependency is absolute. scripts/hnk.mjs uses Node builtins only. A pull request adding a package dependency will be closed regardless of its other merits.
examples/ is generated, not edited. It is the output of a real install run. To change it, change what generates it and re-run the install; hand-edits break the claim the directory exists to make.
Domain adaptations belong elsewhere. A variant of this skill for a specific stack, company, or workflow belongs in its own repository that points at this one — not in core. Keeping core small is a feature.

Read the full file on GitHub · 56 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.

10d ago First seen · 56 lines · 763 tokens per session scan A 32c42184bf00

Subscribe to this mod's changes

human-native-knowledge-skills CLAUDE.md is an instructions file published in the GitHub repository seongjaeryu/human-native-knowledge-skills (5 stars, last pushed 20d ago), licensed MIT. It adds 763 tokens to every session, about $0.0038 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.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

human-native-knowledge-skills: Instructions file for Claude Code