claude-ai-dangerous: Instructions file for Claude Code

CLAUDE.md

claude-ai-dangerous CLAUDE.md is an instructions file for Claude Code from hlop3z/claude-ai-dangerous. It costs 1,850 tokens per session, scanned A, original, MIT.

Project instructions for a codebase whose work follows OpenSpec, a staged process for exploring, proposing, deciding, implementing, syncing, and closing changes. They also give priority to the project’s own engineering rules.

In plain words
What is it for?
Use them when working on this project’s changes, especially when deciding whether to build or adopt a dependency and when recording design decisions.
Why use it?
They make the required development process and rule precedence explicit, so changes are planned and reviewed before implementation.

Instructions file for Claude Code

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

This is hlop3z/claude-ai-dangerous's own configuration. It tells Claude Code how to work on claude-ai-dangerous 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 claude-ai-dangerous configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hlop3z/claude-ai-dangerous. 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/hlop3z/claude-ai-dangerous/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hlop3z/claude-ai-dangerous

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 claude-ai-dangerous CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hlop3z/claude-ai-dangerous/claude-md/github.svg)](https://agentmods.dev/instructions/hlop3z/claude-ai-dangerous/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hlop3z/claude-ai-dangerous/claude-md"><img src="https://agentmods.dev/badge/instructions/hlop3z/claude-ai-dangerous/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 claude-ai-dangerous CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hlop3z/claude-ai-dangerous/claude-md"><img src="https://agentmods.dev/badge/instructions/hlop3z/claude-ai-dangerous/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,850 This file is loaded in full into every session.
When invoked 1,850 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 $0.01850 $0.01850
Opus 5 $0.00925 $0.00925
Sonnet 5 $0.00370 $0.00370
Haiku 4.5 $0.00185 $0.00185

Measured 10d ago against content hash 0cdac5b6fe0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-ai-dangerous 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 · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to develop here

This project drives all work through OpenSpec, governed by a canon of engineering rules that is ours and comes first. Follow the pipeline — the rules apply themselves.

/opsx:explore   Think it through. Decompose (invariants, boundaries, ≥3 strategies). No code.
      ↓
/opsx:propose   Generate proposal.md (WHY/scope) + specs (abstract WHAT) + design.md (HOW).
      ↓
/ai:decide      Build-vs-adopt gate: per critical concern, Rent>Adopt>Extend>Fork>Build.
      ↓             Records each decision into design.md. Run before implementing.
/opsx:apply     Implement the tasks. Thin entry points; adapters isolate every dependency.
      ↓
/opsx:sync      Fold the change's delta specs into the main specs.
      ↓
/opsx:archive   Close out the completed change.

The canon comes first

.canon/ holds the rules this project lives by. It is ours — no external tool writes there. When an opsx command's instructions conflict with a rule in .canon/, the rule wins; say so rather than silently following the command. See .canon/README.md for the full precedence and ownership contract.

The rules (open the file when the trigger fires)

# Trigger In one line
1 explaining or changing architecture Draw it in Mermaid, in docs/architecture/, describing what is.
2 code touching any external system Pure core, ports and adapters at the boundary; dependencies point inward.
3 finishing any multi-file task Review the diff, split by intent, Conventional Commits, never co-author.
4 any branch merge A clean merge is not a correct one — you are the reviewer.
5 a merge just landed Delete what the merge superseded; git history is the history.
6 about to claim something is done Run the checks in .canon/checks.md; report what you couldn't run as unverified.
7 code sits beside an existing pattern Coherence beats minimal diff; consolidate duplicates, flag out-of-scope mess.
8 architecture or API changed Docs that contradict the code are defects — same change set, not later.
9 defining schemas, IDs, vocabularies Adopt the global standard: JSON Schema/OpenAPI/AsyncAPI; Wikidata/DOI/ORCID/LEI + UUID; Schema.org/RDF/ISO.
10 starting a system or bounded context Modular monolith on a kernel by default; DDD contexts, events between them, reads split from writes.
11 naming or registering system objects One grammar — kind:namespace.object_name, lowercase snake_case — in one kernel registry that every projection derives from.

Read the full file on GitHub · 112 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 · 112 lines · 1,850 tokens per session scan A 0cdac5b6fe0e

Subscribe to this mod's changes

claude-ai-dangerous CLAUDE.md is an instructions file published in the GitHub repository hlop3z/claude-ai-dangerous (2 stars, last pushed 25d ago), licensed MIT. It adds 1,850 tokens to every session, about $0.0093 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