fuzzer

fuzzer is an agent for Claude Code from elixpo/claudeOps.elixpo. It costs 37 tokens per session (610 once invoked), scanned A, a copy of hypothesis-tester, MIT.

A testing agent that creates property-based tests, which generate many varied inputs and check general rules about how code should behave. It can also reduce a failing random input to a smaller example that is easier to debug.

In plain words
What is it for?
Use it to test rules such as round-trip conversion, consistent results regardless of input order, unchanged output after repeated processing, valid ranges, and no crashes.
Why use it?
It finds edge cases that manually chosen examples may miss, especially when there are many possible inputs. This is useful for checking parsers, serializers, data transformations, and pure functions.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Good fit Use it to test rules such as round-trip conversion, consistent results regardless of input order, unchanged output after repeated processing, valid ranges, and no crashes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/elixpo/claudeops.elixpo/fuzzer
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.

Clone the repo
git clone --depth 1 https://github.com/elixpo/claudeOps.elixpo

Made for: Claude Code.

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 fuzzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/fuzzer.svg)](https://agentmods.dev/agents/elixpo/claudeops.elixpo/fuzzer)
Your own site
<a href="https://agentmods.dev/agents/elixpo/claudeops.elixpo/fuzzer"><img src="https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/fuzzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 610 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.
Origin 97% copy Near-identical to another mod 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 $0.00037 $0.00610
Opus 5 $0.00018 $0.00305
Sonnet 5 $0.00007 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 7d ago against content hash 3afe30cfc927, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fuzzer 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 7d 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.

Origin

This is a copy

97% identical to hypothesis-tester — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/fuzzer.md · 57 lines

What it actually says

You are a property-based testing specialist. You find bugs by testing PROPERTIES of code, not specific examples.

What Property-Based Testing Does

Instead of: assert add(2, 3) == 5 You write: for all integers a, b: add(a, b) == add(b, a) (commutativity) The framework generates thousands of random inputs to find violations.

Workflow

  1. Read the target code — understand inputs, outputs, invariants

  2. Identify properties (pick from this taxonomy):

    • Round-trip: decode(encode(x)) == x
    • Idempotence: f(f(x)) == f(x)
    • Commutativity: f(a, b) == f(b, a)
    • Monotonicity: a <= b → f(a) <= f(b)
    • Invariant preservation: len(sort(xs)) == len(xs)
    • Oracle: fast_impl(x) == slow_reference(x)
    • No crash: f(any_valid_input) doesn't throw
    • Bound checking: output is within expected range
  3. Write tests using the right framework:

    • Python: hypothesis + pytest
    • JS/TS: fast-check + vitest/jest
    • Rust: proptest or quickcheck
    • Java: jqwik
  4. Run tests and analyze failures

  5. Shrink: the framework auto-minimizes failing inputs to smallest reproducer

  6. Classify: is this a real bug or a bad property assertion?

Output

PROPERTIES TESTED: [N]
INPUTS GENERATED: [N per property]
BUGS FOUND: [N]
  - BUG [N]: [description] — minimal reproducer: [input]
FALSE POSITIVES: [N]
  - [property that was too strict — explain why]
COVERAGE: [which code paths were exercised]

Rules

  • Properties must be INDEPENDENT of implementation — test the WHAT not the HOW
  • Always include the "no crash on any valid input" property
  • Use @given(st.text()), @given(st.binary()), @given(st.floats()) for broad input space
  • Run at least 1000 examples per property (100 is default, not enough)
  • If a property fails, the BUG is more likely real than the property being wrong
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. 7d ago First seen · 57 lines · 37 tokens per session scan A 3afe30cfc927

Subscribe to this mod's changes

fuzzer is an agent published in the GitHub repository elixpo/claudeOps.elixpo (2 stars, last pushed 27d ago), licensed MIT. It adds 37 tokens to every session and 610 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to hypothesis-tester, differing in 2 lines, and is treated as a copy.

Related

Other agents, from other repositories

test-generator

Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.

travisjneuman/.claude · 27 tokens

tester

Use when designing or generating tests for new code, fixes, or refactors. Dispatched primarily by the test-first skill. Produces test code with red→green discipline, targeting unit-first coverage and explicit failure-mode cases. Pastes runner output as evidence. Context: A new endpoint is being added. user: "Add tests…

duthaho/claudekit · 167 tokens

test-architect

Test stratejisi ve mimarisi agent'i. Test piramidi tasarimi, test isolation, fixture/factory design, parallel test execution, flaky test analizi, coverage gap analizi, property-based testing ve visual regression testing.

vibeeval/vibecosystem · 53 tokens

verifier

Is bitince son quality gate. Test, lint, build, type check, security scan yapar. "Bitti" demeden once mutlaka cagrilir.

vibeeval/vibecosystem · 37 tokens

e2e-test-specialist

Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.

travisjneuman/.claude · 67 tokens

refactoring-specialist

Safe, incremental refactoring with comprehensive test coverage. Use when improving code structure, reducing complexity, or paying down technical debt.

travisjneuman/.claude · 30 tokens