Metis-agent: Instructions file for Claude Code

CLAUDE.md

Metis-agent CLAUDE.md is an instructions file for Claude Code from l3gi0nXXXX/Metis-agent. It costs 1,435 tokens per session, scanned A, original, MIT.

A set of instructions for writing code in Cangjie, a programming language used by the Metis code-agent project.

In plain words
What is it for?
It covers defining and calling functions, declaring changeable or fixed variables, and using different integer and decimal-number types.
Why use it?
It gives developers the basic rules needed to understand and write Cangjie code in that project.

Instructions file for Claude Code

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

This is l3gi0nXXXX/Metis-agent's own configuration. It tells Claude Code how to work on Metis-agent 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 Metis-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to l3gi0nXXXX/Metis-agent. 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/l3gi0nXXXX/Metis-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/l3gi0nXXXX/Metis-agent

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 Metis-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/l3gi0nxxxx/metis-agent/claude-md/github.svg)](https://agentmods.dev/instructions/l3gi0nxxxx/metis-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/l3gi0nxxxx/metis-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/l3gi0nxxxx/metis-agent/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 Metis-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/l3gi0nxxxx/metis-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/l3gi0nxxxx/metis-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,435 This file is loaded in full into every session.
When invoked 1,435 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01435 $0.01435
Opus 5 $0.00718 $0.00718
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00144 $0.00144

Measured 10d ago against content hash 7c978eee66ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Metis-agent 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 · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This project implements the Metis code agent application, which is written in the Cangjie programming language.

Introduction of Cangjie

Cangjie is a recently introduced programming language. We briefly describe the syntax of Cangjie below.

Function definition

Use func to define a function, input parameter and return value may have type annotations. Some parameters may be named (indicated with ! sign). E.g.

func foo(a: Int64, b!: Int 64 = 0)

Function call

In function call, the positional parameters are passed in first, without specifying the parameters name. The named parameters follow in any order, where the parameter name must be specified. Parameter with default values need not be specified. E.g.

foo(3)
foo(3, b: 2)

Variable declaration

Variable declarations use either let or var. Variables declared using let are immutable (cannot be assigned after initialization). Variables declared using var can be assigner again within the function.

Number types

The primitive types for numbers include:

  • Signed integers: Int8, Int16, Int32, Int64, IntNative
  • Unsigned integers: UInt8, UInt16, UInt32, UInt64, UIntNative
  • Floating points: Float16, Float32, Float64(Float literals must have a ., e.g. 4 should be written as 4.0 to be Float type.)

Array and ArrayList

Arrays with fixed length are declared using Array<T>, where T is the type of elements in the array. Arrays with dynamic length are declared with ArrayList<T>. The use of ArrayList requires import std.collection.*.

HashMap and HashSet

HashMap represents mapping from keys to values using a hash table. HashSet represents a set of values. Hashable values include numbers and strings but not tuples, Array or ArrayList. Use of HashMap and HashSet requires import std.collection.*.

Sorting

Sorting on arrays requires import std.sort.*. The basic syntax is sort(arr).

Tuples

Tuple types are represented using (T1, T2, ..., TN), where T1 to TN can be any type. Tuples are immutable. Tuple values are represented using the parenthesis syntax as well. Elements of a tuple are accessed by array indexing with constant indices (e.g. t[0], t[1]).

Read the full file on GitHub · 176 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. 10d ago First seen · 176 lines · 1,435 tokens per session scan A 7c978eee66ae

Subscribe to this mod's changes

Metis-agent CLAUDE.md is an instructions file published in the GitHub repository l3gi0nXXXX/Metis-agent (129 stars, last pushed yesterday), licensed MIT. It adds 1,435 tokens to every session, about $0.0072 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 · 5,153 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens