atheris

atheris is a skill for Claude Code, Codex from OutlineDriven/outline-driven-development. It costs 62 tokens per session (1,920 once invoked), scanned A, original, Apache-2.0.

A setup for Atheris, a Python tool that tests code with many automatically varied inputs, including Python native extensions.

In plain words
What is it for?
Use it to create a fuzzing harness, seed corpus, sanitizer configuration for native code, and reproducible crash artifacts.
Why use it?
It helps reveal crashes and unexpected behavior that ordinary example-based tests may miss. Saved failures can be replayed to reproduce the same problem.

Skill for Claude CodeCodex

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 skills/outlinedriven/outline-driven-development/atheris
Any agent
npx skills add OutlineDriven/outline-driven-development --skill atheris
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/outline-driven-development

Made for: Claude Code, Codex.

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/outline-driven-development/atheris.svg)](https://agentmods.dev/skills/outlinedriven/outline-driven-development/atheris)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/atheris"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/atheris.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,920 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00062 $0.01920
Opus 5 $0.00031 $0.00960
Sonnet 5 $0.00012 $0.00384
Haiku 4.5 $0.00006 $0.00192

Measured yesterday against content hash 18e7afae2e02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 yesterday.

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.

.devin/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 Write the Atheris harness file, a corpus directory, the local fuzzing process, and when required for dependency management, create or modify pyproject.toml and uv.lock in the harness directory. Roll back by deleting the harness file and corpus directory and restoring pyproject.toml and uv.lock to their pre-run state; 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.

  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__)".

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. yesterday First seen · 78 lines · 62 tokens per session scan A 18e7afae2e02

Subscribe to this mod's changes

atheris is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,920 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

run-helix-tests

Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.

dotnet/maui · 45 tokens

nw-fp-clojure

Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.

nWave-ai/nWave · 25 tokens

test-generator

Generate test templates for unit tests, integration tests, and UI tests using Swift Testing and XCTest. Use when adding tests to iOS/macOS apps.

rshankras/claude-code-apple-skills · 33 tokens

test-driven-generation

Generate implementation code that passes existing unit tests. Use when the user provides test files (Python pytest/unittest, Java JUnit/TestNG) and asks Claude to implement the code to make those tests pass. Supports full TDD workflow - analyzing tests, generating implementation, running tests, debugging failures, and…

ArabelaTso/Skills-4-SE · 71 tokens

browserless-test

Creates Vaadin Browserless server-side unit tests for Vaadin views covering navigation, component interactions, form validation, grid operations, and notifications. Use when the user asks to "write Browserless tests", "write Vaadin UI unit tests", "unit test a Vaadin view without a browser", "create view tests with…

AI-Unified-Process/marketplace · 104 tokens

smoke-test-ml-pipeline

Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real data/ source and predicts on a disjoint portion that deliberately carries no pre-history buffer. The assertion is structural — the number of predictions must equal…

probabl-ai/skills · 486 tokens