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 agentmods add skills/mesutgulecen/ponscli/verifynpx skills add mesutgulecen/ponscli --skill verifygit clone --depth 1 https://github.com/mesutgulecen/ponscliWrote 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/mesutgulecen/ponscli/verify)<a href="https://agentmods.dev/skills/mesutgulecen/ponscli/verify"><img src="https://agentmods.dev/badge/skills/mesutgulecen/ponscli/verify.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00645 |
| Opus 5 | $0.00028 | $0.00322 |
| Sonnet 5 | $0.00011 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
verify 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying a change to ponscli
Four checks, in this order. Later ones are slower and depend on the earlier ones passing.
npm run typecheck
npm run lint
npm test
npm run build
Run them individually, not as one && chain: when the second fails you want the
first's output still on screen.
What each failure usually means here
typecheck: most often an ABI change. viem infers argument and return types
from the literal ABI, so adding a contract or regenerating one surfaces as a type
error at every call site that used the old shape. That is the check working.
lint: no-unnecessary-type-assertion fires a lot in this repo because the
generated ABIs are as const and already narrow. If you wrote as Address on
something coming out of addresses.ts, delete it.
npm test: the suite is offline. Every test drives the real command surface
through test/fakeChain.ts, a table of address + ABI + function → result. A test
that fails with every free endpoint failed is not a network problem: it means
the fixture is missing an answer for a call the code now makes. Add it to
answers, or to succeed if the call is a state-changing one whose arguments
the test cannot predict.
npm run build: rarely fails on its own. If it does after the others pass,
suspect a runtime-only import cycle.
The ABI gate
npm run abi:check
Fails when a committed ABI no longer matches its verified source. It is not
part of npm test on purpose: it reaches the network, and Blockscout's API is
a token bucket that a full sweep drains. Run it when you have touched
scripts/fetch-abis.mjs or suspect a redeployment, not on every change.
Before you claim something about the protocol
This project's standing rule is that protocol values come from the chain, not from contract source or from this document. The source's defaults are stale in several places that matter. If a change rests on a claim about how Pons behaves, verify it against mainnet state before writing it down:
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.
- 2d ago First seen · 66 lines · 55 tokens per session scan A fc0b674ab1ab
verify is a skill published in the GitHub repository mesutgulecen/ponscli (0 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 645 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.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
agent-uat
AI 에이전트가 마크다운 시나리오를 읽고 사용자와 인터랙티브하게 실행하여 WAIaaS 기능을 메인넷/테스트넷에서 검증하는 시스템이다.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
blockchain-expert
Expert-level blockchain, Web3, smart contracts, DeFi, and cryptocurrency development.
analyzing-ethereum-smart-contract-vulnerabilities
使用 Slither 和 Mythril 对 Solidity 智能合约进行静态分析和符号执行，在部署到以太坊主网之前检测重入攻击、整数溢出、访问控制缺陷和其他漏洞类型。.