Borrowing it
Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/CLAUDE.mdgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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.
[](https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/claude-md)<a href="https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/claude-md"><img src="https://agentmods.dev/badge/instructions/noizu-labs-ml/noizupromptlingo/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.
<a href="https://agentmods.dev/instructions/noizu-labs-ml/noizupromptlingo/claude-md"><img src="https://agentmods.dev/badge/instructions/noizu-labs-ml/noizupromptlingo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03851 | $0.03851 |
| Opus 5.5 | $0.01540 | $0.01540 |
| Sonnet 5.5 | $0.00770 | $0.00770 |
| Haiku 4.5 | $0.00385 | $0.00385 |
Grade A, and why
NoizuPromptLingo 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 1mo 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.
This is a copy
95% identical to NoizuPromptLingo AGENTS.md — 100 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 360 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.
Session Initialization (MANDATORY — DO THIS FIRST)
BLOCKING REQUIREMENT: Before doing ANY work — before reading files, answering questions, or executing tasks — you MUST generate a session. No exceptions. This is the absolute first action in every conversation.
The $NPL_PROJECT environment variable MUST be set.
Single-Call Session Init
If the task is already clear from the user's first message, create a task session directly — no separate root session needed:
ToolSession.Generate(
agent="<agent-name>",
brief="<what this task does>",
task="<task-slug>",
project=$NPL_PROJECT
)
Save the returned UUID — it is both the root and task session ID for this conversation.
Deferred Task Session (exploratory/unclear intent)
If the user's intent is unclear and you need to explore first, create a root session:
ToolSession.Generate(
agent="Root",
brief="Session: <ISO8601 timestamp with ms>",
task="root",
project=$NPL_PROJECT
)
Then create child sessions as work items become clear:
ToolSession.Generate(
agent="<agent-name>",
brief="<what this task does>",
task="<task-slug>",
project=$NPL_PROJECT,
parent="<root-session-uuid>"
)
Sub-Agent Hierarchy
When spawning sub-agents, always pass the parent session UUID. Use root for top-level tasks, or the task session for sub-tasks within that scope.
Instructions Require Sessions
Instructions and Instructions.Create require a valid session UUID. You cannot use them without completing session initialization.
If the MCP server is unavailable or $NPL_PROJECT is not set, inform the user immediately and do not proceed until resolved.
Project Documentation (Agentic Reference)
Three documentation files provide a structured understanding of the codebase. Consult these before any task that requires knowledge of project structure, architecture, or data model. Each has a .summary.md companion for quick lookups.
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.
- 1mo ago Changed · +40 lines · +607 tokens per session 5a5c166c4b07
- 2mo ago Changed · +22 lines · +529 tokens per session 623bac71b1e2
- 2mo ago First seen · 298 lines · 2,715 tokens per session scan A 296033a8384b
NoizuPromptLingo CLAUDE.md is an instructions file published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 10d ago), licensed MIT. It adds 3,851 tokens to every session, about $0.0154 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to NoizuPromptLingo AGENTS.md, differing in 100 lines, and is treated as a copy.
NoizuPromptLingo CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| NoizuPromptLingo CLAUDE.mdnoizu-labs-ml/NoizuPromptLingo | Instructions file | 13 | 10d ago | MIT | A | 3,851 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |