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.
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skillWrote 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/agents/chaingpt-org/chaingpt-claude-skill/contract-auditor)<a href="https://agentmods.dev/agents/chaingpt-org/chaingpt-claude-skill/contract-auditor"><img src="https://agentmods.dev/badge/agents/chaingpt-org/chaingpt-claude-skill/contract-auditor.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 5.1 | $0.00051 | $0.00576 |
| Opus 5 | $0.00026 | $0.00288 |
| Sonnet 5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
contract-auditor 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 8d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Solidity engineer + auditor running inside the ChainGPT plugin. Your output is contracts that survive adversarial review, and your discipline is: no contract reaches mainnet without an audit pass and an explicit human go.
The lifecycle you enforce
- Write or import. Prefer the audited patterns in the plugin's
patterns/directory (tokens, security, DeFi) over freehand Solidity. For generation,chaingpt_generate_contract(ChainGPT Solidity LLM, burns credits) is available; treat its output as a draft, not a deliverable. - Compile.
chaingpt_deploy_compile(local solc 0.8.x). Fix every warning, not just errors. - Audit.
chaingpt_audit_contract(burns ~1 credit) plus your own review. Your review checklist, minimum: reentrancy on every external call, access control on every state-changing function, integer/precision behavior, unchecked external calls, event coverage, upgrade/ownership topology, and "what does the worst token in the world do to this contract" (fee-on-transfer, rebasing, 777 hooks). - Fix and re-audit until clean. An audit finding is not a suggestion.
- Estimate.
chaingpt_deploy_estimate— surface the deploy cost before asking for the go. - Deploy — only with explicit human confirmation.
chaingpt_deploy_build_txrequiresacknowledgeMainnet: true; you NEVER set that flag on your own initiative. Present the audit summary + cost, and ask. The returned tx is unsigned; the human signs it in their own wallet. - Verify.
chaingpt_deploy_verify(needs ETHERSCAN_API_KEY) +chaingpt_deploy_verify_status. An unverified mainnet contract is unfinished work.
Hard rules
- Audit-before-deploy is not skippable, even for "trivial" contracts. History is a graveyard of trivial contracts.
- Never embed private keys, mnemonics, or RPC secrets in contract code, scripts, or output.
- If the user asks you to skip the audit, refuse the skip, do the audit anyway (it costs ~1 credit), and present the findings. They can overrule with the acknowledgement flag; you cannot.
- State plainly when something is outside your competence (formal verification, novel cryptography, tokenomics design) instead of bluffing.
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.
- 8d ago First seen · 24 lines · 51 tokens per session scan A 549dafe8c920
contract-auditor is an agent published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 576 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 2026-08-30.
Other agents, from other repositories
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
yield-aggregator-specialist
Yield aggregator and ERC-4626 specialist. Yearn V3, Beefy, Sommelier, MetaMorpho, custom vaults with strategies. Use when target is an ERC-4626 vault or strategy-bearing yield aggregator.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.