Borrowing it
Nothing to install: this file belongs to ndif-team/skills. 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/ndif-team/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/ndif-team/skillsWrote 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/ndif-team/skills/claude-md)<a href="https://agentmods.dev/instructions/ndif-team/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ndif-team/skills/claude-md.svg" alt="Measured on agentmods" 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 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
skills 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This repository contains agent skills for neural network interpretability using NNsight. Skills are packaged for both Claude Code (via .claude-plugin/) and OpenAI Codex (via .codex/skills/).
Architecture
Skills follow the Agent Skills Specification:
- Skill files:
plugins/nnsight/skills/<skill-name>/SKILL.md- Markdown files with YAML frontmatter (name,description) containing technique documentation and code examples - Claude Code plugin:
plugins/nnsight/.claude-plugin/plugin.json- Plugin metadata - Marketplace config:
.claude-plugin/marketplace.json- Declares available plugins - Codex symlinks:
.codex/skills/- Symlinks to skill directories for Codex compatibility
Each skill is a self-contained guide for a specific interpretability technique: nnsight-basics, logit-lens, activation-patching, attribution-patching, causal-tracing, and model-steering.
Adding a New Skill
- Create
plugins/nnsight/skills/<skill-name>/SKILL.mdwith:--- name: skill-name description: When to use this skill (appears in agent selection). --- - Add technique documentation with Python code examples using NNsight patterns
- Create symlink:
cd .codex/skills && ln -s ../../plugins/nnsight/skills/<skill-name> .
NNsight Patterns Used Across Skills
All skills use consistent NNsight patterns:
LanguageModel("model-name", device_map="auto", dispatch=True)for loadingmodel.trace(prompt)context for interventions.save()to persist values outside tracetracer.invoke(prompt)for batched processingmodel.transformer.h[layer].output[0]for GPT-2 hidden states (adjust path for other architectures)remote=Truefor NDIF remote execution on large models
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.
- 6d ago First seen · 41 lines · 469 tokens per session scan A 3f9354d71b98
skills CLAUDE.md is an instructions file published in the GitHub repository ndif-team/skills (11 stars, last pushed 2d ago), licensed MIT. It adds 469 tokens to every session, about $0.0023 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.
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.
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.
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).
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).
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.
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.