janus-datalog: Instructions file for Claude Code

CLAUDE.md

janus-datalog CLAUDE.md is an instructions file for Claude Code from wbrown/janus-datalog. It costs 19,173 tokens per session, scanned A, original, Apache-2.0.

Development instructions for Janus Datalog, including its complete test command and architectural rules. The test gate checks native Go code, example programs, and JavaScript/WebAssembly contracts.

In plain words
What is it for?
Running the full test suite or focused checks, compiling examples, verifying WebAssembly contracts, and implementing approved architectural changes.
Why use it?
They prevent developers from treating partial tests as sufficient and clarify which architectural decisions belong to the project owner.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is wbrown/janus-datalog's own configuration. It tells Claude Code how to work on janus-datalog 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 janus-datalog configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wbrown/janus-datalog. 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/wbrown/janus-datalog/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/wbrown/janus-datalog

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 janus-datalog CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wbrown/janus-datalog/claude-md.svg)](https://agentmods.dev/instructions/wbrown/janus-datalog/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wbrown/janus-datalog/claude-md"><img src="https://agentmods.dev/badge/instructions/wbrown/janus-datalog/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 19,173 This file is loaded in full into every session.
When invoked 19,173 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 5.1 $0.19173 $0.19173
Opus 5 $0.09586 $0.09586
Sonnet 5 $0.03835 $0.03835
Haiku 4.5 $0.01917 $0.01917

Measured 6d ago against content hash 56607ce9510d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

janus-datalog 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 6d 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 · 1,676 lines

How it starts

The opening of the file, as written. The whole thing — 1,676 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Test Commands

The standard gate is make test. It runs the native suite (go test -count=1 ./...), the examples/ compile check (make test-examples), and the js/wasm contracts (make test-wasm). Do not treat bare go test ./... as a full green — that skips both of the others.

make test                        # Full gate: native + examples + wasm (required)
make test-examples               # Compile-check examples/ under //go:build example
make test-wasm                   # js/wasm contracts only (needs node)
go test -v ./package -run Test   # Focused native iteration only

Every examples/ file is its own package main behind //go:build example, so go vet ./examples/ reports main redeclared and no ordinary build reaches them. test-examples vets each file separately; without it nothing compiles them at all.

Do NOT add -timeout to go test commands, or use -timeout 0. Use the default timeout. No exceptions.


Architectural Authority

The user owns all architectural decisions. Claude implements them.

Before making ANY of these decisions, ASK:

  • Introducing new patterns (globals, managers, abstractions)
  • Changing existing patterns (options → globals, Relations → Bindings)
  • Adding new cross-cutting concerns (configuration, logging, caching)
  • Deviating from established conventions for any reason

If you're unsure whether something is an "architectural decision":

  • Would it affect multiple files/packages?
  • Would it change how components interact?
  • Would it require other code to change to accommodate it?
  • Are you thinking "I'll ask forgiveness later"?

Then ASK first.

Red flags that indicate you're overstepping:

  • "This is just temporary/experimental"
  • "I'll refactor this later"
  • "It's faster to do it this way"
  • "It's simpler/easier this way" (when deviating from a plan or established pattern)
  • Making a choice between multiple valid approaches without consulting

Read the full file on GitHub · 1,676 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. 6d ago First seen · 1,676 lines · 19,173 tokens per session scan A 56607ce9510d

Subscribe to this mod's changes

janus-datalog CLAUDE.md is an instructions file published in the GitHub repository wbrown/janus-datalog (51 stars, last pushed 28d ago), licensed Apache-2.0. It adds 19,173 tokens to every session, about $0.0959 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

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 · 5,182 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens