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 OpenLAIR/OpenSkill --skill evo-atheris-fuzz-drivergit clone --depth 1 https://github.com/OpenLAIR/OpenSkillWrote 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/openlair/openskill/evo-atheris-fuzz-driver)<a href="https://agentmods.dev/skills/openlair/openskill/evo-atheris-fuzz-driver"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-atheris-fuzz-driver/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/openlair/openskill/evo-atheris-fuzz-driver"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-atheris-fuzz-driver.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 | $0.00053 | $0.00396 |
| Opus 5 | $0.00026 | $0.00198 |
| Sonnet 5 | $0.00011 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
evo-atheris-fuzz-driver 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.
What it actually says
Atheris Fuzz Driver Generator
Generates fuzz.py harness files for Python libraries with proper Atheris instrumentation, FuzzedDataProvider usage, and exception handling.
Driver Design Principles
- Import target library inside
atheris.instrument_imports()context manager - Use
FuzzedDataProviderto generate structured typed inputs - Catch only expected exceptions (ValueError, TypeError, domain-specific errors)
- Guard with
if __name__ == "__main__":block - Use
atheris.Setup(sys.argv, TestOneInput)thenatheris.Fuzz()
Supported Libraries
- arrow: Date/time parsing, timestamp boundary testing
- black: Code formatting with Mode configuration
- ipython: Input transformation pipeline
- minisgl: JSON/msgpack parsing (lightweight targets)
- ujson: Differential fuzzing against stdlib json
Key Functions
generate_fuzz_driver(lib_path)- Generate and write fuzz.py for a libraryget_driver_template(lib_name)- Get driver source code for a libraryget_exception_handlers_for_lib(lib_name)- Get expected exceptions listcreate_fuzz_driver_file(lib_path, lib_name)- Write fuzz.py to disk
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-atheris-fuzz-driver/scripts')
from fuzz_driver import generate_fuzz_driver, create_fuzz_driver_file
generate_fuzz_driver('/app/arrow')
generate_fuzz_driver('/app/black')
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.
- yesterday First seen · 43 lines · 53 tokens per session scan A 2fbbc1f73c1f
evo-atheris-fuzz-driver is a skill published in the GitHub repository OpenLAIR/OpenSkill (90 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 396 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 2026-09-11.
Other skills, from other repositories
codex-autoresearch
Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
dos-self-improve
Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use dos-enforce-tune for policy knobs.
dos-witness-claim
Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.
dos-skillify
Convert an agent skill into a DOS-grounded variant by replacing self-certified claims with dos witness checks and emitting an additive copy plus report. Use when asked to make a skill DOS-aware or audit its self-checks.
experiment
Rules as hypotheses: falsifiable tests, confidence updates, graduate or kill. Triggers: experiment, hypothesis, prove, test rule, validate methodology, evidence.