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 skills add aaronjmars/aeon-agent --skill investigation-reportgit clone --depth 1 https://github.com/aaronjmars/aeon-agentWrote 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/aaronjmars/aeon-agent/investigation-report)<a href="https://agentmods.dev/skills/aaronjmars/aeon-agent/investigation-report"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/investigation-report/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/skills/aaronjmars/aeon-agent/investigation-report"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/investigation-report.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 | $0.00052 | $0.07986 |
| Opus 5 | $0.00026 | $0.03993 |
| Sonnet 5 | $0.00010 | $0.01597 |
| Haiku 4.5 | $0.00005 | $0.00799 |
Grade A, and why
investigation-report scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -m 10 -s -X POST "$RPC" -H "Content-Type: application/json" -d '{ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -m 10 -s -X POST "${BASE_RPC_URL:-https://mainnet.base.org}" -H "Content-Type: application/json" \ This is a copy
100% identical to investigation-report — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
${var} — Base subject to investigate, plus optional flags:
<token-address> [--checks=rug,contract,deployer,holders,honeypot,lp] [--depth=quick|deep]. The first token is the subject contract address (0x…, required).--checks=is a comma-list selecting which analyzers to run (default = all six).--depth=isquick(the old rug-scan fast path — minimal reads) ordeep(full standalone logic of each selected check; default). If the subject address is empty, logREPORT_NO_TARGETand exit cleanly (no notify).Examples:
0xToken→ all six checks, deep report.0xToken --checks=honeypot→ only the honeypot simulation (reproduces the standalone honeypot-check exactly, incl. itsHONEYPOT_*end-states).0xToken --checks=rug,lp --depth=quick→ rug verdict + LP-lock, fast path.0xToken --checks=contract,deployer,holders --depth=deep→ structural audit + deployer entity intel + full concentration.
The "tell me everything about this token" skill. Instead of running six checks by hand, this composes them into one structured report behind a selector: rug risk, contract audit (verification / owner powers / proxy), deployer trace (who shipped it and their history), holder concentration (whale risk), honeypot (can you actually sell?), and LP lock (can the team pull liquidity?) — with a one-line summary on top.
Designed to degrade gracefully: each selected section runs independently, so a section that needs a key (or returns nothing) is marked unavailable without aborting the rest. Selecting a single check makes the composite behave as that one analyzer — same steps, same thresholds, same notify format, same status codes.
Config
- Subject = the first token of
${var}(validate:0x+ 40 hex). Chain = Base (chainid=8453, explorerbasescan.org). - Etherscan v2 unified API (
https://api.etherscan.io/v2/api?chainid=8453&…) — used by therug,contract,deployer,holderschecks. Works keyless at a lower rate limit. - Base RPC (
${BASE_RPC_URL:-https://mainnet.base.org}) — used byhoneypot,lp, and theeth_call/eth_getLogs/eth_getStorageAt/eth_getCodereads inside the other checks. Keyless; any standard JSON-RPC endpoint works. - Secrets (all optional):
ETHERSCAN_API_KEY(a.k.a.BASESCAN_API_KEY— same Etherscan v2 key) — appended to the Etherscan URL as&apikey=…via./secretcurl's{ETHERSCAN_API_KEY}placeholder (never a bare$SECRETon the line, never a header). Raises the rate limit and unlocks verified source, full deployer history, and the holder list. Used byrug,contract,deployer,holders.BASE_RPC_URL— overrides the default public Base RPC. Used by every RPC read; primary forhoneypotandlp.
- Preamble (run once, before dispatch): read
memory/MEMORY.mdand the last ~2–3 days ofmemory/logs/so a repeat investigation can note what changed since last time and avoid re-reporting the same signal. Parse${var}→ subject address,--checks(default all six),--depth(defaultdeep).
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.
- 5d ago First seen · 405 lines · 52 tokens per session scan A ea458a1bf6dd
investigation-report is a skill published in the GitHub repository aaronjmars/aeon-agent (11 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 7,986 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). It is 100% identical to investigation-report, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.