What is vp-claude CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant. They define safe non-interactive shell commands and require using Beads, a task-tracking tool, for repository work.

Use them when operating on repositories that contain a CLAUDE.md file, especially for copying, moving, or removing files and managing work with Beads.

They reduce the chance that file commands hang for confirmation and keep implementation tasks recorded in the project's chosen tracker.

How voxpelli/vp-claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to voxpelli/vp-claude. 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/voxpelli/vp-claude/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/voxpelli/vp-claude

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/voxpelli/vp-claude/claude-md.svg)](https://agentmods.dev/instructions/voxpelli/vp-claude/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/voxpelli/vp-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/voxpelli/vp-claude/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 9,098 This file is loaded in full into every session.

When invoked 9,098 The same file — it is already loaded in full.

Security scan D 2 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	$0.09098	$0.09098
Opus 5	$0.04549	$0.04549
Sonnet 5	$0.01820	$0.01820
Haiku 4.5	$0.00910	$0.00910

Measured 8d ago against content hash e8433a83d5ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

vp-claude CLAUDE.md scanned grade D with 2 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

sgconfig.yml # ast-grep config — auto-discovers .ast-grep/rules/ (see .claude/rules/ast-grep-rules.md)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf directory # NOT: rm -r directory

CLAUDE.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 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.

Non-Interactive Shell Commands

ALWAYS use non-interactive flags with file operations to avoid hanging on confirmation prompts. cp, mv, and rm may be aliased to -i (interactive) mode, which hangs an agent indefinitely waiting for y/n input.

# Force overwrite without prompting
cp -f source dest           # NOT: cp source dest
mv -f source dest           # NOT: mv source dest
rm -f file                  # NOT: rm file

# For recursive operations
rm -rf directory            # NOT: rm -r directory
cp -rf source dest          # NOT: cp -r source dest

Others that may prompt: scp and ssh (use -o BatchMode=yes), apt-get (use -y), brew (use HOMEBREW_NO_AUTO_UPDATE=1).

Task Tracking

bd (beads) is this repo's tracker and bd ready is the work queue — use it rather than TodoWrite/TaskCreate or markdown TODO lists. Four things about it here are not obvious:

bd's git-hook integration was removed deliberately (2026-07-29): core.hooksPath no longer points at .beads/hooks. Those shims ran bd hooks run <name> on a 300 s timeout and exited non-zero on a bd panic, aborting the commit or push, while the JSONL auto-export they existed to drive had been broken since 2026-05-29. Do not re-arm it. Nothing syncs the store on a git operation now — export by hand.
.beads/ is gitignored — the issue history is NOT in this repo. A fresh clone carries no backlog. Treat the local Dolt database as a working copy, never as the record of truth. A committed snapshot lives at docs/design/bd-export-2026-07-29.jsonl (360 issues + 7 memories); refresh it with bd export --include-memories -o docs/design/bd-export-<date>.jsonl.
bd's write path is unreliable here. The Dolt invalid hash length: 19 panic recurred 2026-07-28, after the 1.1.2 upgrade meant to fix it. Reads survive panics that kill writes, so the store looks healthy while diverging. Verify every bd create / bd close with bd show <id> — see bd CLI quirks.
Migration to diarie is blocked, not merely unscheduled. Published [email protected] reads acceptance criteria only from a ## Acceptance Criteria heading, but this repo's bd records carry acceptance_criteria as a standalone field — so diarie migrate today silently drops it, exits 0, and passes diarie validate. The gate is a published diarie release with that fix.

Read the full file on GitHub · 418 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.

8d ago First seen · 418 lines · 9,098 tokens per session scan D e8433a83d5ac

Subscribe to this mod's changes

vp-claude CLAUDE.md is an instructions file published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 10d ago), licensed MIT. It adds 9,098 tokens to every session, about $0.0455 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Project management ai-generated basic-memory claude-code-agents claude-code-plugin claude-code-skills

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

vp-claude: Instructions file for Claude Code