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/christopher-buss/bedrock/claude-mdgit clone --depth 1 https://github.com/christopher-buss/bedrockWrote 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/christopher-buss/bedrock/claude-md)<a href="https://agentmods.dev/instructions/christopher-buss/bedrock/claude-md"><img src="https://agentmods.dev/badge/instructions/christopher-buss/bedrock/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 | $0.04293 | $0.04293 |
| Opus 5 | $0.02146 | $0.02146 |
| Sonnet 5 | $0.00859 | $0.00859 |
| Haiku 4.5 | $0.00429 | $0.00429 |
Grade A, and why
bedrock 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bedrock Project Context
What is Bedrock?
Infrastructure-as-Code deployment tool for Roblox, written in TypeScript. Modern replacement for Mantle (Rust-based tool no longer maintained).
Architecture
- Language: TypeScript (ES modules)
- Runtime: Bun
- Auth: Roblox Open Cloud APIs only (no ROBLOSECURITY)
- Toolchain: Vite+ (
vp packbuilds,vp testruns Vitest,vp runorchestrates tasks) - Lint: eslint from monorepo root only (
pnpm lint), no per-package lint scripts
Architecture Quick Reference
Pattern: FCIS (Functional Core, Imperative Shell) + Ports
┌─────────────────────────────────────────────────────┐
│ Shell │
│ (I/O, CLI commands, orchestration) │
│ │
│ ┌─────────────────────────────────────────────┐ │
│ │ Core │ │
│ │ (Pure functions, business logic, no I/O) │ │
│ └─────────────────────────────────────────────┘ │
│ │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ Port │ │ Port │ │ Port │ │
│ │ (State) │ │(OpenCloud)│ │ (Config) │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
└───────┼─────────────┼─────────────┼───────────────┘
│ │ │
┌────▼────┐ ┌─────▼────┐ ┌────▼─────┐
│ Adapter │ │ Adapter │ │ Adapter │
│ (Gist) │ │ (HTTP) │ │ (c12) │
└─────────┘ └──────────┘ └──────────┘
- Core: Pure functions, no side effects, easy to test
- Shell: Orchestrates I/O, calls core with data from adapters
- Ports: Interfaces defining what adapters must implement
- Adapters: Concrete implementations (Gist, Open Cloud HTTP, etc.)
Testing Requirements (NON-NEGOTIABLE)
Every line of production code must be written in response to a failing test.
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.
- 3d ago First seen · 381 lines · 4,293 tokens per session scan A 14aa17de25d1
bedrock CLAUDE.md is an instructions file published in the GitHub repository christopher-buss/bedrock (14 stars, last pushed yesterday), licensed MIT. It adds 4,293 tokens to every session, about $0.0215 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 2026-09-01.
Other instructions, from other repositories
turn-based-game-mcp typescript.instructions.md
TypeScript development patterns and best practices for the turn-based games platform.
lattice AGENTS.md
Instructions for plausibleventures/lattice, covering lattice — how to work in this repo, the eleven non-negotiables, layout, commands and house style.
wc3-map-ts-template AGENTS.md
AGENTS.md instructions for eiriksgata/wc3-map-ts-template, covering repository guidelines, project identity, project structure, build and run commands and kkwe lni and terrain editing.
wc3-map-ts-template copilot-instructions.md
Copilot instructions for eiriksgata/wc3-map-ts-template, covering warcraft iii typescript map development template, project architecture, @eiriksgata/wc3ts library reference, core api structure and documentation patterns.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.
Kokoro-Engine CLAUDE.md
Claude Code instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.