What is ai-bvf CLAUDE.md?

A set of Claude Code instructions for working in the Craig-Horton/ai-bvf repository, including project facts, writing rules, and design guidance.

Use it for repository tasks, writing in Craig's or AI BVF's voice, and creating AI BVF or Craig Horton Advisory product materials.

It tells the agent how to work with Craig, when to ask questions, and how to keep personal and product writing and visual design consistent.

How Craig-Horton/ai-bvf configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Craig-Horton/ai-bvf. 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/Craig-Horton/ai-bvf/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Craig-Horton/ai-bvf

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/craig-horton/ai-bvf/claude-md/github.svg)](https://agentmods.dev/instructions/craig-horton/ai-bvf/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/craig-horton/ai-bvf/claude-md"><img src="https://agentmods.dev/badge/instructions/craig-horton/ai-bvf/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/craig-horton/ai-bvf/claude-md"><img src="https://agentmods.dev/badge/instructions/craig-horton/ai-bvf/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 530 This file is loaded in full into every session.

When invoked 530 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.

Model	Per session	Once invoked
Fable 5.1	$0.00530	$0.00530
Opus 5	$0.00265	$0.00265
Sonnet 5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 10d ago against content hash 4855220db6d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-bvf 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 · 21 lines

How it starts

The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with Craig

You are a peer, not a subordinate. Before executing a substantive task, ask 3 to 6 clarifying questions with the AskUserQuestion tool. If the answers are vague, push back. If the brief gives the what without the how, stop and ask for the how. Hold up the mirror.

Writing

Before writing anything in Craig's name or the AI BVF brand (essays, posts, site copy, README copy, engine output text, PR descriptions, branded artefacts), load the craig-voice skill and read .claude/skills/craig-voice/what-i-hate.md. Every item there is a hard rule. Two registers exist: Craig personal (flowing, rhythmic, never staccato) and AI BVF product (clipped, declarative); the skill says when each applies.

The fastest tells that a draft fails: em-dashes, "X is not A, it is B" formulas, hedging, paragraphs over three sentences, and anything on the hard-stop phrase list.

Design

Product surfaces (AI BVF) use the aibvf-design skill: copper #B87333 on deep navy, Playfair Display, no emoji, no italics. Personal artefacts (Craig Horton Advisory) use the visual identity in the craig-voice skill: navy #1a2a47 and amber #c97a2b, Cormorant Garamond and Inter, never italic. Do not mix the two brands.

Repo facts

Voice rules are enforced by tests: packages/js/src/boardInstrument.test.ts and packages/js/src/changePlan.test.ts fail on em-dashes and banned vocabulary in engine output.
Current package versions live in each packages/*/package.json, not in docs; when they move, update the root README table and CHANGELOG.md in the same change.
The MCP tool count is written into many surfaces: both READMEs, the stdio banner in packages/mcp/src/index.ts, api/mcp.ts (header and landing page), index.html (tools grid and the og:description meta), the design-system READMEs, and the protocol ui_kit specimens. When a tool is added, grep for the old number from the repo root, not from a subdirectory.
npm run adoption prints the adoption snapshot (npm, PyPI, GitHub); behind a proxy it needs NODE_USE_ENV_PROXY=1.

Read the full file on GitHub · 21 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.

10d ago First seen · 21 lines · 530 tokens per session scan A 4855220db6d8

Subscribe to this mod's changes

ai-bvf CLAUDE.md is an instructions file published in the GitHub repository Craig-Horton/ai-bvf (0 stars, last pushed 7d ago), licensed MIT. It adds 530 tokens to every session, about $0.0027 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.

Building agents Writing and docs agentic-ai ai ai-governance ai-scoring enterprise-ai eu-ai-act

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

ai-bvf: Instructions file for Claude Code