syzkaller is an automated fuzzer that generates kernel activity and uses code coverage to find bugs in operating-system kernels. It is used by kernel developers and security researchers to test Linux and other supported kernels for vulnerabilities and failures. The catalogue add-ons help coding agents operate or use syzkaller.
Borrowing it
Nothing to install: this file belongs to google/syzkaller. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/google/syzkaller/master/GEMINI.mdgit clone --depth 1 https://github.com/google/syzkallerWrote 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/google/syzkaller/gemini-md)<a href="https://agentmods.dev/instructions/google/syzkaller/gemini-md"><img src="https://agentmods.dev/badge/instructions/google/syzkaller/gemini-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/google/syzkaller/gemini-md"><img src="https://agentmods.dev/badge/instructions/google/syzkaller/gemini-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01239 | $0.01239 |
| Opus 5.5 | $0.00496 | $0.00496 |
| Sonnet 5.5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
syzkaller GEMINI.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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
syzkaller - Context for Gemini
Project Overview
syzkaller is an unsupervised, coverage-guided kernel fuzzer. It is a hybrid
system consisting of a Go-based manager (running on a host) and a C++
executor (running inside the target VM).
- Primary Language: Go (Manager, Tools), C++ (Executor).
- Architecture:
syz-manager: Orchestrates the fuzzing process, manages corpus, and monitors VMs.syz-executor: Runs inside the VM, executes test programs via syscalls, and collects coverage.syz-ci,syz-hub,dashboard: Infrastructure for continuous fuzzing and reporting.
Building and Testing
Prefer to use the syz-env Docker container to build the compontents and run
tests. There's a ./tools/syz-env script that will start a container and run
the given command inside it.
Some reference commands:
- Build everything:
CI=true ./tools/syz-env make. - Run a linter:
CI=true ./tools/syz-env make lint. - Run a test:
CI=true ./tools/syz-env go test ./package -run TestName. - Formatter:
CI=true ./tools/syz-env make format(runsgofmt,clang-format, etc).
Note the CI=true part - otherwise the commands may not run in your environment.
When running tests (especially in ./prog and ./pkg/csource) prefer to run
individual tests you have affected, otherwise it may take a lot of time. Some
packages also offer a -short flag to run a lighter version of tests.
It may be necessary to first run CI=true ./tools/syz-env make descriptions to
pre-build descriptions for the sys/* targets. It may be necessary for all
tests that eventually use prog.Target or targets.Target.
Key Directories
syz-manager/: Entry point for the main fuzzing manager.executor/: C++ source code for the test program executor.pkg/: Core Go libraries:pkg/ipc: IPC mechanism between manager and executor.pkg/fuzzer: Fuzzing logic.pkg/manager: Manager logic library.
sys/: System call descriptions (essential for the fuzzer to know how to call the kernel).sys/linux/: Linux-specific descriptions (.txtand.const).
tools/: Helper utilities (syz-repro,syz-mutate, etc.).docs/: Extensive documentation on setup, internals, and contribution.
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 · 75 lines · 1,239 tokens per session scan A 8d6ea9fd4cce
syzkaller GEMINI.md is an instructions file published in the GitHub repository google/syzkaller (6,383 stars, last pushed today), licensed Apache-2.0. It adds 1,239 tokens to every session, about $0.0050 per session on Opus 5.5. 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 2026-10-26.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.