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.
npx skills add OutlineDriven/outline-driven-development --skill atherisgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/skills/outlinedriven/outline-driven-development/atheris)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/atheris"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/atheris/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/skills/outlinedriven/outline-driven-development/atheris"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/atheris.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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.
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 | $0.00042 | $0.02041 |
| Opus 5.5 | $0.00017 | $0.00816 |
| Sonnet 5.5 | $0.00008 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
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 22d 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 — 79 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_timeand-max_lenvalues. Optional; defaults are libFuzzer defaults. - Sanitizers: whether AddressSanitizer and/or UndefinedBehaviorSanitizer are enabled. Optional; ASan is the default for native extensions.
Procedure
-
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.
-
Install Atheris. If the harness directory is not already a uv project (no
pyproject.tomlpresent), runuv init --bareonce. Thenuv add atheris. Verify withpython -c "import atheris; print(atheris.__version__)". Done when: Atheris is installed and importable.
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.
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.
- 22d ago Changed · +2 tokens per session 95383c5ca6a6
- 1mo ago Changed · +1 lines c9f0e963fe82
- 1mo ago Changed · -22 tokens per session d4da46fd004c
- 1mo ago First seen · 78 lines · 62 tokens per session scan A 18e7afae2e02
atheris is a skill published in the GitHub repository OutlineDriven/outline-driven-development (53 stars, last pushed 22d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,041 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
521-frameworks-micronaut-testing-unit-tests
Use when you need to write unit tests for Micronaut applications — Mockito-first with @ExtendWith(MockitoExtension.class), @MicronautTest with @MockBean, HttpClient @Client(/) assertions, @Property overrides, @ParameterizedTest, and Test vs IT naming. For framework-agnostic Java use @131-java-testing-unit-testing.…
rn-testing
Testing React Native: Jest with jest-expo / react-native preset, React Testing Library Native, native module mocking, hook testing. Optional sections for Detox (native automation) and Maestro (declarative YAML e2e). Use this skill to: Configure Jest preset based on workflow. Write component tests with…
dotnet-testing
Skill "dotnet-testing" from AratKruglik/claude-sdlc, covering .net testing patterns (stack-agnostic), test framework: xunit, nuget packages for a test project, xunit fundamentals and parameterised tests — [theory].
dotnet-nunit
Write, run, or repair .NET tests that use NUnit. Use when a repo uses NUnit, [Test], [TestCase], [TestFixture], or NUnit3TestAdapter for VSTest or Microsoft.Testing.Platform execution.
rn-write-tests
Use to write tests for an Expo + RN app: Jest + React Native Testing Library for unit/integration (components, hooks, queries, mutations) and Maestro for end-to-end flows (sign-in, navigation, forms). Sets up the testing stack on first call (jest-expo preset, RNTL, jest config) and writes a focused test next to the…