sabba: Instructions file for Claude Code

CLAUDE.md

sabba CLAUDE.md is an instructions file for Claude Code from 8NobleTruths/sabba. It costs 712 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Sabba, a security tool that searches for bugs and reports them only after reproducing an exploit in a sandbox.

In plain words
What is it for?
Use them when working on Sabba, its vulnerability provers, security-agent design, or support for additional languages and smart contracts.
Why use it?
They explain where to start reading and how Sabba proves security problems, including its focus on memory safety in C and C++.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is 8NobleTruths/sabba's own configuration. It tells Claude Code how to work on sabba itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sabba configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 8NobleTruths/sabba. 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/8NobleTruths/sabba/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/8NobleTruths/sabba

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.

agentmods badge for sabba CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/8nobletruths/sabba/claude-md.svg)](https://agentmods.dev/instructions/8nobletruths/sabba/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/8nobletruths/sabba/claude-md"><img src="https://agentmods.dev/badge/instructions/8nobletruths/sabba/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 712 This file is loaded in full into every session.
When invoked 712 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 8d ago against content hash 5f3d77219b50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sabba 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 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.

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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sabba Agent

Sabba finds security bugs and proves each one by triggering it. A model proposes candidates, and an execution oracle runs an exploit in a sandbox and decides whether a security property broke. Nothing is reported unless the exploit reproduces. The pipeline that exists today targets C and C++ memory safety. The design extends the same discipline to any language and to smart contracts, Solidity first.

Where to start reading

  • docs/SABBA_AGENT_DESIGN.md: how the current C and C++ bug-finder fits together. The oracle is the anchor; every other part proposes candidates.
  • docs/PROVERS_MULTI_DOMAIN_DESIGN.md: how the oracle generalizes from one sanitizer pipeline into a registry of provers, one per vulnerability class and runtime. Covers managed languages, web applications, and Web3 and Solidity, where a finding is proven on an EVM fork by a fund-drain or solvency invariant. Read this before adding a prover for a new language or chain.
  • docs/WATER_LAYER_DESIGN.md: the design for the next layer, an agent that learns skills, keeps them as runnable code, runs without a frontier model, and can be rebuilt from a signed seed after deletion. Read this before working on anything under a future water/ package. Provers are skills the genome accumulates.

Layout

  • sabba/harness/oracle.py: the execution oracle, the shared verifier. Never fork it. It generalizes into the prover registry.
  • sabba/harness/agent.py, sabba/harness/orchestrator.py: the reasoning agent and driver.
  • sabba/harness/fuzz.py: the model writes a harness, the oracle proves the crash. This is the seed of the Water Layer's skill compiler.
  • sabba/harness/symbolic/synth.py: the Z3 synthesizer.
  • sabba/llm/: the model backend switch (OpenRouter, Anthropic, GLM). The Water Layer's Teacher and Resident both sit behind llm/base.py.
  • sabba/sandbox/: docker and local execution isolation. It grows environment builders per domain: a compile step, a fuzz harness, a seeded web container, an EVM fork.
  • sabba/memory.py, sabba/history.py: the seed of the Water Layer genome.
  • sabba/cli.py, sabba/repl.py, sabba/tui.py: the command line, the REPL, the TUI.

Read the full file on GitHub · 49 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. 8d ago First seen · 49 lines · 712 tokens per session scan A 5f3d77219b50

Subscribe to this mod's changes

sabba CLAUDE.md is an instructions file published in the GitHub repository 8NobleTruths/sabba (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 712 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

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

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

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

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