KohakuTerrarium: Instructions file for Claude Code

CLAUDE.md

KohakuTerrarium CLAUDE.md is an instructions file for Claude Code from Kohaku-Lab/KohakuTerrarium. It costs 12,787 tokens per session, scanned A, original, no licence file.

Claude Code instructions for the KohakuTerrarium project, covering its purpose, file layout, coding conventions, and style rules.

In plain words
What is it for?
Guiding code changes and reviews in the KohakuTerrarium repository.
Why use it?
They help Claude Code follow the project’s existing structure and coding expectations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Kohaku-Lab/KohakuTerrarium's own configuration. It tells Claude Code how to work on KohakuTerrarium itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything KohakuTerrarium configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kohaku-Lab/KohakuTerrarium. 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/Kohaku-Lab/KohakuTerrarium/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Kohaku-Lab/KohakuTerrarium

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.

agentmods badge for KohakuTerrarium CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kohaku-lab/kohakuterrarium/claude-md/github.svg)](https://agentmods.dev/instructions/kohaku-lab/kohakuterrarium/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kohaku-lab/kohakuterrarium/claude-md"><img src="https://agentmods.dev/badge/instructions/kohaku-lab/kohakuterrarium/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.

agentmods 80×15 button for KohakuTerrarium CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kohaku-lab/kohakuterrarium/claude-md"><img src="https://agentmods.dev/badge/instructions/kohaku-lab/kohakuterrarium/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12,787 This file is loaded in full into every session.
When invoked 12,787 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 unknown 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 5.1 $0.12787 $0.12787
Opus 5.5 $0.05115 $0.05115
Sonnet 5.5 $0.02557 $0.02557
Haiku 4.5 $0.01279 $0.01279

Measured 7d ago against content hash 5180c7cca598, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

KohakuTerrarium 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 7d 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 · 837 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 7d ago Changed · +15 lines · +521 tokens per session 5180c7cca598
  2. 8d ago Changed · +12 lines · +249 tokens per session 97f0952a5b60
  3. 9d ago Changed · +5 lines · +91 tokens per session e8802787a56b
  4. 17d ago Changed · +1 lines · +24 tokens per session d3fc8fabe900
  5. 2mo ago Changed · +44 lines · +623 tokens per session f21f5f903f9a
  6. 2mo ago First seen · 760 lines · 11,279 tokens per session scan A 3a1f7440f4b6

Subscribe to this mod's changes

KohakuTerrarium CLAUDE.md is an instructions file published in the GitHub repository Kohaku-Lab/KohakuTerrarium (543 stars, last pushed yesterday), with no licence file. It adds 12,787 tokens to every session, about $0.0511 per session on Opus 5.5. 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

KohakuTerrarium CLAUDE.md compared with instructions from other repositories

KohakuTerrarium CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
KohakuTerrarium CLAUDE.mdKohaku-Lab/KohakuTerrariumInstructions file543yesterdaynoneA12,787Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode