agentmods.dev

bloodhound CLAUDE.md

bloodhound CLAUDE.md is an instructions file for coding agents from nerdsane/bloodhound. It costs 7,861 tokens per session, scanned B, original, MIT.

Development guidance for Bloodhound, a tool that repeatedly simulates distributed systems to find bugs under controlled failures. It covers coding rules, formal specifications and reproducible testing.

In plain words
What is it for?
Use it when changing Bloodhound code, writing or checking TLA+ specifications, adding deterministic fault tests, or debugging behavior that must replay exactly.
Why use it?
It gives contributors a shared definition of correct behavior for a system where timing and failures can be difficult to reproduce. It also sets priorities such as safety before performance.

Instructions file

not rated 22 7mo ago B scan 7,861 tokens original MIT
View the source file nerdsane/bloodhound
Install

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.

agentmods
npx agentmods add instructions/nerdsane/bloodhound/claude-md
Clone the repo
git clone --depth 1 https://github.com/nerdsane/bloodhound

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.

agentmods badge for bloodhound CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nerdsane/bloodhound/claude-md.svg)](https://agentmods.dev/instructions/nerdsane/bloodhound/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nerdsane/bloodhound/claude-md"><img src="https://agentmods.dev/badge/instructions/nerdsane/bloodhound/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,861 This file is loaded in full into every session.
When invoked 7,861 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.07861 $0.07861
Opus 5 $0.03930 $0.03930
Sonnet 5 $0.01572 $0.01572
Haiku 4.5 $0.00786 $0.00786

Measured 5d ago against content hash 94bc6b4d9143, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

bloodhound CLAUDE.md scanned grade B with 1 finding 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo cp /home/sesh/Development/gvisor/bazel-bin/runsc/runsc_/runsc /usr/local/bin/runsc-dst
CLAUDE.md · 891 lines

How it starts

The opening of the file, as written. The whole thing — 891 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bloodhound Development Guide

Instructions for AI agents and human developers working on Bloodhound.

Project Overview

Bloodhound is a deterministic simulation testing platform for hunting bugs in distributed systems using a modified QEMU hypervisor.

Key Goals:

  • Perfect reproducibility: Same seed = identical execution, always
  • Language agnostic: Test any containerized application without modification
  • Systematic fault injection: BUGGIFY-style deterministic faults
  • Time-travel debugging: Full replay capability with GDB integration

Engineering Philosophy

Three pillars ground all code in Bloodhound:

  1. TigerStyle - Coding standards (assertions, explicit limits, naming)
  2. Formal Specifications (specs/tla/, src/stateright/) - Protocol correctness
  3. Deterministic Simulation Testing - Fault tolerance verification

Before writing code, consult all three. They define what "correct" means.

Priority order: Safety > Performance > Developer Experience

The Verification Pyramid

All three pillars are connected through shared invariants (src/invariants/):

         TLA+ Specs (specs/tla/*.tla)
                    │ mirrors
         Shared Invariants (src/invariants/*.rs)  ← SINGLE SOURCE OF TRUTH
                    │ used by
    ┌───────────────┼───────────────┐
    ▼               ▼               ▼
Stateright      DST Tests      Production Code
(exhaustive)    (simulation)   (TigerStyle)

Each invariant has:

  • name - matches TLA+ property name
  • tla_spec - source spec file reference
  • tla_line - line number in spec
  • holds / violation - result with context

Example: When implementing snapshot tree operations:

  1. Read specs/tla/SnapshotTree.tla for the protocol
  2. Use SnapshotPropertyChecker from invariants/snapshot.rs in your tests
  3. Properties like no_orphan_snapshots are verified identically across all layers

Read the full file on GitHub · 891 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.

  1. 5d ago First seen · 891 lines · 7,861 tokens per session scan B 94bc6b4d9143

Subscribe to this mod's changes

bloodhound CLAUDE.md is an instructions file published in the GitHub repository nerdsane/bloodhound (22 stars, last pushed 7mo ago), licensed MIT. It adds 7,861 tokens to every session, about $0.0393 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DebuggingTesting
Related

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.

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 · 5,182 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

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens