atheris

atheris is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 40 tokens per session (2,031 once invoked), scanned A, original, Apache-2.0.

A local fuzz-testing skill for Python code and Python native extensions using Atheris. Fuzz testing runs many automatically varied inputs against a target to find unexpected failures.

In plain words
What is it for?
Use it to create and run an Atheris test harness, measure code coverage, and replay saved crash cases.
Why use it?
It helps find crashes and other input-handling problems that ordinary test cases may miss, while recording inputs that reproduce failures.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin-fuzzing plugin — 12 skills shipped together

Good fit Use it to create and run an Atheris test harness, measure code coverage, and replay saved crash cases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/atheris
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.

Any agent
npx skills add OutlineDriven/odin-claude-plugin --skill atheris
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-fuzzing, the plugin that ships this one along with the rest of its 12 skills.

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 atheris

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/atheris.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/atheris)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/atheris"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/atheris.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high YARA Match · line 53
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
How audits are shown
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 $0.00040 $0.02031
Opus 5 $0.00020 $0.01015
Sonnet 5 $0.00008 $0.00406
Haiku 4.5 $0.00004 $0.00203

Measured 2d ago against content hash d4da46fd004c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

atheris 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 2d 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.

plugins/odin-fuzzing/skills/atheris/SKILL.md · 78 lines

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.

Atheris

Contract

Field Bound contract
Trigger User needs coverage-guided fuzzing for Python code or a Python native extension using Atheris.
Authority Reversible local: writes only the Atheris harness file, a corpus directory, and when required for dependency management pyproject.toml and uv.lock in the harness directory; rollback is deleting the harness file and corpus directory and restoring pyproject.toml and uv.lock to their pre-run state. No remote mutation. No source under test is mutated.
Side effect Local writes: a fuzz.py (or named) harness, a corpus/ directory of seed and crash artifacts, and a transient fuzzing process.
Done Atheris executes an instrumented target through a deterministic TestOneInput harness, reports coverage, and any saved crash artifact reproduces the same failure when replayed.

Inputs

  • Target: the Python function or module to fuzz, or the Python C extension to fuzz. Required.
  • Target kind: pure Python, or native C extension. Required; it selects the instrumentation and build path.
  • Expected exceptions: the exception types the target legitimately raises on bad input, so the harness catches them instead of crashing. Optional but recommended.
  • Seed corpus: initial input files for corpus/. Optional; Atheris can start empty.
  • Time/length budget: -max_total_time and -max_len values. Optional; defaults are libFuzzer defaults.
  • Sanitizers: whether AddressSanitizer and/or UndefinedBehaviorSanitizer are enabled. Optional; ASan is the default for native extensions.

Procedure

  1. Determine target kind. If the target is pure Python, follow the pure-Python path. If it is a C extension compiled from source, follow the native-extension path. Do not guess; ask the user when the kind is ambiguous. Done when: the target kind is determined as pure Python or native C extension.

  2. Install Atheris. If the harness directory is not already a uv project (no pyproject.toml present), run uv init --bare once. Then uv add atheris. Verify with python -c "import atheris; print(atheris.__version__)". Done when: Atheris is installed and importable.

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 78 lines · 40 tokens per session scan A d4da46fd004c

Subscribe to this mod's changes

atheris is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 2,031 once invoked, about $0.0002 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 2026-09-06.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens