agentmods.dev

evolve-fuzz-probe

evolve-fuzz-probe is an agent for Claude Code from mickeyyaya/evolve-loop. It costs 18 tokens per session (338 once invoked), scanned A, original, Apache-2.0.

An automated agent that tests changed Go code with many generated inputs, a technique called fuzz testing. It focuses on parsers, decoders, and functions that turn external data into program values, then writes a results report.

In plain words
What is it for?
Use it after changing Go functions that read, parse, decode, or unmarshal input, especially when checking for crashes and test coverage changes.
Why use it?
It can expose crashes and unexpected input-handling problems that example-based tests may miss. The report records crashes and newly reached code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the evo plugin — 32 skills, 33 commands, 99 agents, 3 hooks shipped together

not rated 6repo +1 today A scan 18 tokens original Apache-2.0

Good fit Use it after changing Go functions that read, parse, decode, or unmarshal input, especially when checking for crashes and test coverage changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-fuzz-probe
View source ↗ mickeyyaya/evolve-loop mickeyyaya.github.io
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/mickeyyaya/evolve-loop

Made for: Claude Code.

Or install evo, the plugin that ships this one along with the rest of its 32 skills, 33 commands, 99 agents, 3 hooks.

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 evolve-fuzz-probe

README.md
[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe/github.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe)
Your own site
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe/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.

agentmods 80×15 button for evolve-fuzz-probe

Your own site · 80×15
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-fuzz-probe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 338 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 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 $0.00018 $0.00338
Opus 5.5 $0.00007 $0.00135
Sonnet 5.5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 1mo ago against content hash b7ba0a82cc01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evolve-fuzz-probe 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 1mo 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.

agents/evolve-fuzz-probe.md · 31 lines

What it actually says

Evolve Fuzz Probe Agent

You are the Fuzz Probe agent in the Evolve Loop. Your job is to run a short-budget Go-native fuzzing process on changed functions (especially parser, decoder, and unmarshal functions).

Workflow

  1. Identify fuzz targets:

    • Read the build-report.md to identify touched files and functions.
    • Scan for input-handling, parsing, decoding, or unmarshaling functions.

  2. Run Fuzzing:

    • Run Go-native fuzzing (go test -fuzz=. -fuzztime=60s) on the identified packages or functions.
    • If a crash occurs, write the crashers to the corpus and record details.

  3. Calculate Signals:

    • Record fuzz.crashers (number of unique crashes found) and fuzz.coverage_new (new coverage achieved).

  4. Emit Report:

    • Write the report fuzz-probe-report.md containing ## Target Functions, ## Fuzz Results, and ## Verdict sections.
    • Log the namespaced signals fuzz.crashers and fuzz.coverage_new using the standard format.
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. 1mo ago First seen · 31 lines · 18 tokens per session scan A b7ba0a82cc01

Subscribe to this mod's changes

evolve-fuzz-probe is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 338 once invoked, about $0.0001 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 2026-08-31.

Claude CodeGoLanguagesTestingai-agentsai-pipelineautonomous-codingclaude-code-plugincode-quality
Related

Other agents, from other repositories

peer-go-reviewer

Stage 1 peer code reviewer focused on idiomatic Go, error handling, and concurrency patterns.

hazarsozer/crucible-cc · 24 tokens

implementer-prompt

Implement one focused task in a Go codebase using strict test-driven development.

gopherguides/gopher-ai · 20 tokens

implementer

Executes a single plan task using TDD. Writes tests first, then production code, then refactors. Reports status with evidence.

greglas75/zuvo · 30 tokens

pre-commit-tester

Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…

skullninja/coco-workflow · 159 tokens

dnp-tdd-developer-hard

🔬 Deep TDD for complex .NET tasks: architectural decisions, ambiguous edge cases, high-risk refactoring. Writes both tests and production code with rigorous RED-GREEN-REFACTOR.

zdanovichnick/dotnet-pilot · 47 tokens

mobile-tester

Agent "mobile-tester" from akaszubski/autonomous-dev, covering mission, hard gate: appium mcp availability check, hard gate: environment security (sandbox only), hard gate: screenshot data safety and hard gate: 60-second timeout per test case.

akaszubski/autonomous-dev · 31 tokens