poc-generator

poc-generator is an agent for coding agents from asyncswap/skills. It costs 55 tokens per session (312 once invoked), scanned A, original, MIT.

An agent that creates Foundry proof-of-concept tests for serious Solidity security findings. Foundry is a toolkit for building and running Ethereum smart-contract tests.

In plain words
What is it for?
Generating attack contracts, test setup, control cases, assertions, and a verdict for high- and critical-severity findings.
Why use it?
It turns suspected vulnerabilities into runnable tests, helping determine whether an attack really works or is blocked.

Agent

Part of the solidity-language-server plugin — 5 skills, 3 agents shipped together

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 agents/asyncswap/skills/poc-generator
Clone the repo
git clone --depth 1 https://github.com/asyncswap/skills

Or install solidity-language-server, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

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 poc-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/asyncswap/skills/poc-generator.svg)](https://agentmods.dev/agents/asyncswap/skills/poc-generator)
Your own site
<a href="https://agentmods.dev/agents/asyncswap/skills/poc-generator"><img src="https://agentmods.dev/badge/agents/asyncswap/skills/poc-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00055 $0.00312
Opus 5 $0.00028 $0.00156
Sonnet 5 $0.00011 $0.00062
Haiku 4.5 $0.00006 $0.00031

Measured 3d ago against content hash 3b86a232356c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poc-generator 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 3d 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.

plugins/solidity-language-server/agents/poc-generator.md · 33 lines

What it actually says

POC Generator Agent

You are a POC generator agent for Solidity smart contract security findings. Run the poc-generator skill for the target file(s) and findings provided in your prompt.

Follow the full skill instructions from the poc-generator skill definition.

Rules:

  • Search test/ for existing test base (SetupHook, BaseTest, etc.) and REUSE it
  • Search test/ for existing POC/reentrancy tests -- do not duplicate
  • Always include a control test (fair parameters, no exploit)
  • Use percentage-based assertions: assertLt(received, available * 80 / 100)
  • Emit log_named_uint for intermediate values
  • Run with: forge test --match-path test/.t.sol --no-cache -vvv

Output:

  1. The test file path and contents
  2. Forge output (pass/fail per test)
  3. Verdict per finding: CONFIRMED / MITIGATED / PARTIALLY CONFIRMED / INVALID
  4. Quantitative impact (% of tokens drained, balances before/after)
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. 3d ago First seen · 33 lines · 55 tokens per session scan A 3b86a232356c

Subscribe to this mod's changes

poc-generator is an agent published in the GitHub repository asyncswap/skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 312 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 2026-08-31.

Related

Other agents, from other repositories

copilot

Agent "copilot" from mareurs/codescout, covering github copilot, one-time setup, register codescout as an mcp server, enable agent skills and add workflow skills.

mareurs/codescout · 0 tokens

cursor

Agent "cursor" from mareurs/codescout, covering cursor, one-time setup, register codescout as an mcp server, add workflow skills and add the code-reviewer agent.

mareurs/codescout · 0 tokens

claude-code

Agent "claude-code" from mareurs/codescout, covering claude code, one-time setup, 1. install the binary, binary is at target/release/codescout and optionally copy it somewhere on your path.

mareurs/codescout · 0 tokens

codebase-onboarding

Produce a structured onboarding report for a codebase. Use when a developer asks "help me understand this project", "onboard me", "what does this codebase do", "give me an overview", or needs to get up to speed on an unfamiliar codebase. Analyzes architecture, key modules, entry points, data flow, and conventions.

jrollin/cartog · 76 tokens

refactoring-scout

Comprehensive pre-flight analysis before a refactoring. Use when a developer wants a full blast radius report before changing a symbol, module, or file — not for quick one-off queries like "what calls X?" (the cartog skill handles those). Triggers: "is it safe to change X?", "what breaks if I rename X?", "blast radius…

jrollin/cartog · 122 tokens

security-reviewer

Review Solidity contracts for security vulnerabilities, incentive design, and OpenZeppelin best practices.

protokol/solidity-typescript-hardhat-template · 16 tokens