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/cacheforge-ai/cacheforge-skills/rug-checkernpx skills add cacheforge-ai/cacheforge-skills --skill rug-checkergit clone --depth 1 https://github.com/cacheforge-ai/cacheforge-skillsWrote 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/cacheforge-ai/cacheforge-skills/rug-checker)<a href="https://agentmods.dev/skills/cacheforge-ai/cacheforge-skills/rug-checker"><img src="https://agentmods.dev/badge/skills/cacheforge-ai/cacheforge-skills/rug-checker.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 | $0.00034 | $0.02368 |
| Opus 5 | $0.00017 | $0.01184 |
| Sonnet 5 | $0.00007 | $0.00474 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
rug-checker scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rug Checker — Agent Skill Definition
Skill Metadata
| Field | Value |
|---|---|
| Slug | rug-checker |
| Version | 0.1.3 |
| Author | Anvil AI |
| Category | DeFi / Security |
| Chain | Solana |
| Risk Level | Read-only (no wallet interactions) |
Activation Triggers
Activate this skill when the user's message matches any of these patterns:
| Pattern | Example |
|---|---|
| Rug check / rug pull check | "Do a rug check on BONK" |
| Token safety | "Is this token safe?" |
| Scam check | "Is this a scam?" |
| Token risk analysis | "What's the risk on this token?" |
| Honeypot check | "Is this a honeypot?" |
| Token audit | "Audit this token" |
| LP locked | "Is the LP locked on this?" |
| Mint authority | "Can they mint more tokens?" |
| Token lookup + Solana address | "What is DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263?" |
Note: If the user asks "Should I buy [token]?", redirect: "I can't advise on whether to buy — but I can check the on-chain risk factors for you." Then run the analysis.
Address detection: If the user provides a base58 string of 32-44 characters, treat it as a Solana token address. If they provide a name/symbol, resolve it first.
Agent Workflow
Step 1: Extract the Token
Parse the user's message for either:
- A Solana address (base58, 32-44 chars matching
[1-9A-HJ-NP-Za-km-z]{32,44}) - A token name or symbol (e.g., "BONK", "bonk", "Wheelchair Fish")
If unclear, ask: "Which token would you like me to check? Give me the contract address or token name."
Step 2: Resolve the Token
bash scripts/detect-token.sh <address_or_name>
Output varies by input type:
If given a Solana address: JSON with found: true/false, address, name, symbol, market data.
If given a name/symbol: JSON with ambiguous: true and a candidates array containing up to 5 matches with address, name, symbol, liquidity, and age. If detect-token returns candidates, you MUST present them to the user and ask which one they mean. NEVER auto-pick a candidate. Checking the wrong token is worse than not checking at all.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 216 lines · 34 tokens per session scan A 68dd1089aedf
rug-checker is a skill published in the GitHub repository cacheforge-ai/cacheforge-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 2,368 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
solhunt
Solana wallet health analysis and SOL recovery expert. Analyzes wallet efficiency, finds recoverable SOL from zero-balance token accounts, and builds trustless recovery transactions. Never requires private keys.
zerion-api
Query crypto wallet portfolios, transactions, DeFi positions, and token prices across EVM chains and Solana using Zerion's MCP server.
Solana Agent Builder
Build AI-powered agents for Solana blockchain — trading bots, DeFi strategies, token analysis, and on-chain automation with TypeScript.
baozi-prediction-markets
Trade, create, and manage Solana prediction markets on Baozi.bet — autonomous betting, market creation, affiliate earnings, and portfolio tracking.
pump-swarm
Coordinated multi-wallet trading on Pump.fun.
trading-solana
Trade tokens on Solana DEXes - Jupiter, Raydium, Orca, Meteora, Pump.fun.