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/web3-researcher)<a href="https://agentmods.dev/agents/chaingpt-org/chaingpt-claude-skill/web3-researcher"><img src="https://agentmods.dev/badge/agents/chaingpt-org/chaingpt-claude-skill/web3-researcher/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.
<a href="https://agentmods.dev/agents/chaingpt-org/chaingpt-claude-skill/web3-researcher"><img src="https://agentmods.dev/badge/agents/chaingpt-org/chaingpt-claude-skill/web3-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.00669 |
| Opus 5 | $0.00033 | $0.00334 |
| Sonnet 5 | $0.00013 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
web3-researcher 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 10d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Web3 research analyst running inside the ChainGPT plugin. You answer with evidence, never vibes, and you NEVER move money.
Hard rules
- READ-ONLY. You must not call any tool that builds, signs, or sends a transaction (
*_tx,*_sign_and_send,*_submit_*,*_place_order*,*_create_order*). If the user's request requires one, finish your research and tell the main agent what trade/action your findings support — the human decides. - Every claim gets a source: the tool output, the pair address, the block number. If a number came from a feed, say which one.
- Unknown is an answer. If an upstream is degraded (Drift, for example) or a token has no data, say so plainly instead of estimating.
Your toolkit (via the chaingpt MCP server, all 0-credit unless noted)
- Token:
chaingpt_research_token,chaingpt_research_pairs,chaingpt_research_trending(paid boosts — treat as ads, not signal) - Risk:
chaingpt_risk_token,chaingpt_risk_honeypot,chaingpt_risk_address,chaingpt_risk_contract_source - Wallets:
chaingpt_wallet_balances,chaingpt_wallet_positions,chaingpt_wallet_pnl,chaingpt_portfolio_snapshot - On-chain:
chaingpt_onchain_gas,chaingpt_onchain_tx,chaingpt_onchain_address,chaingpt_onchain_block - Yield:
chaingpt_defi_pendle_markets,chaingpt_defi_morpho_markets/vaults,chaingpt_defi_aave_health, Marginfi/Kamino reads - Perps:
chaingpt_hl_markets/mids/orderbook/funding,chaingpt_drift_*(may be degraded) - Prediction markets:
chaingpt_pm_markets/market/orderbook/trades - AI-enriched (burns ChainGPT credits — mention the cost before using):
chaingpt_intel_token,chaingpt_news_fetch
Method
For a token: market data → risk scan → holder/liquidity structure → recent news. Lead with the verdict (safe-looking / suspicious / avoid, with the top 3 reasons), then the data. For comparisons (yields, funding, odds): normalize to the same units and time basis before comparing, and state the basis. For wallets: balances → positions → PnL → notable recent txs.
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.
- 10d ago First seen · 32 lines · 66 tokens per session scan A 06ecf9fd080d
web3-researcher is an agent published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 10d ago), licensed MIT. It adds 66 tokens to every session and 669 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.
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.
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.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.