Skip to content
Agentmart
Submit a tool

investigation-report

One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot…

Skill by aeonfun

IndexedMIT★ 782
Write a review

Chalk Labs

Need help deploying investigation-report?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aeonfun-investigation-report

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot, lp-lock) into one verdict. Keyless core.

Use cases: documents, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/investigation-report

What's inside

Skill name
investigation-report
Description
One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot, lp-lock) into one verdict. Keyless core.
License
MIT
Metadata
var: · mode: read-only · title: Investigation Report · category: crypto
Instructions
384 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

> **${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=` is `quick` (the old rug-scan fast path — minimal reads) or `deep` (full standalone logic of each selected check; **default**). If the subject address is empty, log `REPORT_NO_TARGET` and 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. its `HONEYPOT_*` 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 `${var}` (validate: `0x` + 40 hex). Chain = Base (`chainid=8453`, explorer `basescan.org`).
- **Etherscan v2 unified API** (`https://api.etherscan.io/v2/api?chainid=8453&…`) — used by the `rug`, `contract`, `deployer`, `holders` checks. Works **keyless** at a lower rate limit.
- **Base RPC** (`${BASE_RPC_URL:-https://mainnet.base.org}`) — used by `honeypot`, `lp`, and the `eth_call`/`eth_getLogs`/`eth_getStorageAt`/`eth_getCode` reads 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 `$SECRET` on the line, never a header). Raises the rate limit and unlocks verified source, full deployer history, and the holder list. Used by `rug`, `contract`, `deployer`, `holders`.
  - `BASE_RPC_URL` — overrides the default public Base RPC. Used by every RPC read; primary for `honeypot` and `lp`.
- **Preamble (run once, before dispatch):** read `memory/MEMORY.md` and the last ~2–3 days of `memory/logs/` so a repeat investigation can note what changed since last time and avoid re-reporting the same signal. Parse `${var}` → subject address, `--checks` (default all six), `--depth` (default `deep`).

## Steps

Dispatch to each selected check below (default: all six). Each is self-contained — collect its verdict/section; **never let one check's failure stop the others**. `--depth=quick` runs the lightweight path noted in each branch (rug-scan-style inline sampling, fewer calls); `--depth=deep` runs the full standalone logic.

### Check `rug` — Rug Scan

A fast, opinionated rug verdict: does the contract let someone print, freeze, or drain — and is supply/liquidity concentrated enough to pull?

**1. Verify contract + pull source**
```bash
TOKEN="${var}"
# ./secretcurl substitutes {ETHERSCAN_API_KEY} internally, so no `$SECRET` hits the
# command line (a bare one is refused by the Bash permission analyzer). Append the key
# only when set — Etherscan v2 works keyless at a lower rate limit.
KEYQ=""; [ -n "${ETHERSCAN_API_KEY:+x}" ] && KEYQ="&apikey={ETHERSCAN_API_KEY}"
./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=contract&action=getsourcecode&address=${TOKEN}${KEYQ}" | jq '.result[0]'
```
Capture `ContractName`, `Proxy`, `Implementation`, `SourceCode`. Empty `SourceCode` = **unverified** → strong risk signal.

**2. Scan source for dangerous powers** — grep the returned source (case-insensitive) for these signals and record which fire:

| Signal | Patterns | Weight |
|--------|----------|--------|
| Unverified source | empty `SourceCode` | +3 |
| Mint authority | `function mint`, `_mint(` callable by owner | +2 |
| Blacklist / freeze | `blacklist`, `isBlocked`, `_freeze`, `addBan` | +2 |
| Pausable transfers | `whenNotPaused`, `function pause` | +1 |
| Mutable fees/tax | `setFee`, `setTax`, `updateTaxes` | +2 |
| Owner not renounced | owner != `0x0` (see step 3) | +1 |
| Proxy / upgradeable | `Proxy == "1"` or `delegatecall` + upgrade fn | +2 |
| Trading toggle | `enableTrading`, `tradingActive`, `setSwapEnabled` | +1 |

**3. Check ownership state** — call `owner()` (selector `0x8da5cb5b`) via `eth_call`:
```bash
curl -m 10 -s -X POST "${BASE_RPC_URL:-https://mainnet.base.org}" -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"eth_call","params":[{"to":"'"$TOKEN"'","data":"0x8da5cb5b"},"latest"],"id":1}' | jq -r '.result'
```
Trailing 40 hex chars = the owner address. All-zero → ownership renounced (lowers risk). A live EOA/multisig → flag the step-2 powers as *currently exercisable*.

**4. Holder concentration (quick read)**
```bash
KEYQ=""; [ -n "${ETHERSCAN_API_KEY:+x}" ] && KEYQ="&apikey={ETHERSCAN_API_KEY}"
./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=token&action=tokenholderlist&contractaddress=${TOKEN}&page=1&offset=10${KEYQ}" | jq '.result'
```
Compute top-1 and top-10 share of supply. Flag `+2` if top-1 > 30% (excluding known LP/lock/burn addresses), `+1` if top-10 > 70%. If this endpoint returns empty on the keyless tier, note `holders=unavailable` and skip this signal rather than failing. **Depth:** on `--depth=deep` *when the `holders` check is also selected*, take the top-1/top-10 EOA share from that check's full result instead of this 10-row sample.

**5. LP / liquidity check** — identify the token's main pool (Aerodrome / Uniswap V3 on Base). If LP tokens sit in a known locker or burn address (`0x000…dead`, Unicrypt, Team Finance) → liquidity locked (lowers risk). If LP is held by the deployer EOA → `+2` (pull risk). **Depth:** on `--depth=deep` *when the `lp` check is also selected*, use that check's `LOCKED/PARTIAL/UNLOCKED` verdict here.

**6. Score + verdict** — sum the weights:

| Score | Verdict |
|-------|---------|
| 0–2 | `LOW` |
| 3–5 | `ELEVATED` |
| 6–8 | `HIGH` |
| 9+ | `CRITICAL` |

The verdict must come from this table — no freelance labels. Section end-states: `RUG_SCAN_OK` (LOW), `RUG_SCAN_FLAGGED` (≥ELEVATED), `RUG_SCAN_ERROR` (all fetches failed).

### Check `contract` — Contract Audit

Deep structural inspection: what powers exist, who holds them, and whether they're still exercisable.

**1. Source + verification**
```bash
ADDR="${var}"
KEYQ=""; [ -n "${ETHERSCAN_API_KEY:+x}" ] && KEYQ="&apikey={ETHERSCAN_API_KEY}"
./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=contract&action=getsourcecode&address=${ADDR}${KEYQ}" | jq '.result[0] | {ContractName, Proxy, Implementation, CompilerVersion, verified: (.SourceCode != "")}'
```
If unverified, say so plainly: no static analysis is possible and audit confidence is low. Continue with the onchain checks below.

**2. Proxy / upgradeability** — if `Proxy == "1"` or the source contains `delegatecall`, read the EIP-1967 implementation slot:
```bash
curl -m 10 -s -X POST "${BASE_RPC_URL:-https://mainnet.base.org}" -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"eth_getStorageAt","params":["'"$ADDR"'","0x360894a13ba1a3210667c828492db98dca3e2076cc3735a920a3ca505d382bbc","latest"],"id":1}' | jq -r '.result'
```
A non-zero slot = upgradeable (Transparent/UUPS). Upgradeable means post-deploy logic can change — flag who controls the upgrade (admin/owner from step 3).

**3. Ownership & admin roles** — probe common accessors via `eth_call` and record any that return a non-zero address:

| Function | Selector |
|----------|----------|
| `owner()` | `0x8da5cb5b` |
| `admin()` | `0xf851a440` |
| `paused()` | `0x5c975abb` |

```bash
curl -m 10 -s -X POST "${BASE_RPC_URL:-https://mainnet.base.org}" -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"eth_call","params":[{"to":"'"$ADDR"'","data":"0x8da5cb5b"},"latest"],"id":1}' | jq -r '.result'
```
Check whether the owner address itself has code (multisig/contract) vs is an EOA via `eth_getCode`.

**4. Dangerous function surface** — from verified source, enumerate externally-callable, owner-gated functions and classify:
- **Supply**: `mint`, `burnFrom`
- **Access**: `blacklist`, `setFreeze`, `pause`/`unpause`
- **Economics**: `setFee`, `setTax`, `setMaxTx`, `setLimits`
- **Control**: `transferOwnership`, `upgradeTo`, `setImplementation`
- **Drain**: arbitrary `call`/`delegatecall` reachable by admin, `withdraw`/`rescueTokens` that can move user funds

From aeonfun/aeon, MIT.

More from aeonfun/aeon

Signals

Stars
782
Forks
292
Open issues
0
Last commit (this folder)
Oct 1, 2026 (1 month ago)
Last release
Jul 9, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from aeonfun

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get investigation-report running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying investigation-report?

CallGet help
Cite this page

investigation-report skill. Agent Mart. https://agentmart.dev/skills/aeonfun-investigation-report (last updated 2026-10-24)