Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/bendrucker/claude/claude-mdgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/claude-md)<a href="https://agentmods.dev/instructions/bendrucker/claude/claude-md"><img src="https://agentmods.dev/badge/instructions/bendrucker/claude/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 | $0.02121 | $0.02121 |
| Opus 5 | $0.01060 | $0.01060 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade A, and why
claude 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Plugin Marketplace
This repository contains my personal Claude Code configuration and a plugin marketplace (bendrucker) that allows others to install portions of my setup.
Structure
plugins/: Plugins providing language support, workflows, and integrations.claude-plugin/marketplace.json: Marketplace definition listing all available pluginsschemas/: JSON Schemas for Claude Code config formats. Upstream-backed ones (plugin,marketplace,settings) keep only our edits as an RFC 6902 overlay inschemas/overlays/, merged with the live upstream base in memory at validation time; the rest are hand-authoreduser/: User-level configuration, symlinked to~/.claudedocs/: Reference material too long to auto-inject, linked from the rule that needs it.claude/: Project-level configuration for this repository
Inventory
Answer any repo-wide "which X exists" question with bun run inventory [kind] before globbing or grepping plugins/, skills/, hooks/, or agents/. Rows carry each asset's path and scope, so the listing is where a Read or a narrowed grep starts. bun run inventory --help covers the kinds and flags.
User
The user/ directory contains user-level Claude Code configuration that gets symlinked to ~/.claude. This includes global instructions (CLAUDE.md), settings (plugins, permissions, sandbox), and hooks that apply across all projects. Symlinks and other system setup are managed by the claude topic in dotfiles.
Curation
Every customization (skill, hook, wordlist entry, agent, rule, permission) costs tokens on every session that touches it. Adding is cheap, accumulation is silent, and removal has no natural trigger. Before adding one, define how it gets removed: what evidence shows it's earning its cost, what evidence shows it isn't, and where that evidence surfaces. Detectors of model behavior need particular care: models drift and rules lose value, so pair detection with a path to evolve or retire.
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.
- yesterday Changed · +4 lines · +329 tokens per session 76c8da6f21f9
- 4d ago First seen · 74 lines · 1,792 tokens per session scan A 431e0f257fa7
claude CLAUDE.md is an instructions file published in the GitHub repository bendrucker/claude (16 stars, last pushed yesterday), licensed MIT. It adds 2,121 tokens to every session, about $0.0106 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
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.
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).