niuma-engine: Instructions file for Claude Code

CLAUDE.md

niuma-engine CLAUDE.md is an instructions file for Claude Code from Destined-at-Dawn/niuma-engine. It costs 1,512 tokens per session, scanned A, original, MIT.

Project instructions for niuma-engine that define required startup checks, file-protection steps, research expectations, and rules for reading and changing project files.

In plain words
What is it for?
Use them when working in niuma-engine to load the required project context, verify the agent branch and archives, follow protection procedures, and avoid blind file changes.
Why use it?
They give the agent project-specific operating rules, including checking memory and pending tasks and creating archives before modifications. This reduces accidental overwrites and keeps work aligned with the project’s history and safeguards.

Instructions file for Claude Code

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

This is Destined-at-Dawn/niuma-engine's own configuration. It tells Claude Code how to work on niuma-engine 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 niuma-engine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Destined-at-Dawn/niuma-engine. 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/Destined-at-Dawn/niuma-engine/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Destined-at-Dawn/niuma-engine

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 niuma-engine CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/destined-at-dawn/niuma-engine/claude-md/github.svg)](https://agentmods.dev/instructions/destined-at-dawn/niuma-engine/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/destined-at-dawn/niuma-engine/claude-md"><img src="https://agentmods.dev/badge/instructions/destined-at-dawn/niuma-engine/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 niuma-engine CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/destined-at-dawn/niuma-engine/claude-md"><img src="https://agentmods.dev/badge/instructions/destined-at-dawn/niuma-engine/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,512 This file is loaded in full into every session.
When invoked 1,512 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 $0.01512 $0.01512
Opus 5 $0.00756 $0.00756
Sonnet 5 $0.00302 $0.00302
Haiku 4.5 $0.00151 $0.00151

Measured 10d ago against content hash 2c69304c7a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

niuma-engine 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Startup Sequence (Every Conversation -- Mandatory)

Step Action When
1 Read .claude/rules/ directory Every conversation (Claude Code auto-loads)
2 Read memory/long-term.md First conversation / after corrections
3 Read memory/{today}.md First conversation of the day
4 Read EVOLUTION.md Match pending tasks -> execute first
5 R21 Three-Layer Protection: verify agent branch + archive ready + pre-modify archive Every conversation
6 Knowledge Hub: read cross-workspace lessons (last 7 days) Every conversation

Quick Mode: If the user message contains a specific trigger word you've defined, skip startup and process directly. High-risk operations still require reading long-term.md.


Project Rules

R21 -- Three-Layer File Protection (CRITICAL)

Before any file modification or deletion: archive -> agent/{date} branch -> daily zip snapshot. -> See .claude/rules/21-git-archive-ironlaw.md

Think Before Act

New problems require research before action. Never substitute "I think" for best practice. -> See .claude/rules/think-before-act.md

No Blind Overwrite (CRITICAL)

Read existing files before writing. Use Edit for partial changes, never Write without Read. -> See .claude/rules/no-blind-overwrite.md

Script Safety Check (CRITICAL)

Pipeline: write script -> safety check -> dry-run -> show -> confirm -> execute -> verify. Deletions must target specific files, never directories. -> See .claude/rules/script-safety-check.md

Evidence Layering

Every "pass" claim must carry a calibration label (coarse/medium/full-audit). -> See .claude/rules/10-engineering-laws.md Law 1

Anti-Illusion Audit

Abnormally good numbers are assumed fake until proven real. Run the five-question check. -> See .claude/rules/anti-illusion-audit.md

Negative Result Archiving

Dead ends must be archived. An unrecorded dead end will be retried by every subsequent conversation. -> See .claude/rules/negative-results.md

Read the full file on GitHub · 134 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 · 134 lines · 1,512 tokens per session scan A 2c69304c7a1c

Subscribe to this mod's changes

niuma-engine CLAUDE.md is an instructions file published in the GitHub repository Destined-at-Dawn/niuma-engine (4 stars, last pushed 29d ago), licensed MIT. It adds 1,512 tokens to every session, about $0.0076 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.

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

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

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