New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Token Safety Check

by nirholas in nirholas/three.ws

Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the…

Apache-2.0Auto-check passedBackend & APIs

Install Token Safety Check

skills CLI
$ npx skills add nirholas/three.ws --skill token-safety-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nirholas/three.ws token-safety-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nirholas/three.ws.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community-skills/skills/token-safety-check .claude/skills/token-safety-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
token-safety-check
GitHub stars
227
Token cost
~1.3k tokens
SKILL.md length
743 words
Files
3 (incl. scripts)
Skills in repo
92
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the…

  • Works in 5 steps: Mint authority. If it is not revoked,… → Freeze authority. If it is not revoked,… → Token-2022 extensions. A permanent… → …
  • The user asks is this token safe
  • SKILL.md covers Inputs, The five checks, in order, Where the facts come from and How to answer, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node; reaches three.ws

What it does

Token Safety Check is an agent skill from nirholas/three.ws. Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the evidence. Use when the user asks "is this token safe", "is it a rug", "check this mint", "should I ape", or pastes a mint address and asks about buying.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `metadata.json`).

It sits in Backend & APIs, covering Smart contracts. It works with Solana. The repository describes itself as: Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web… The licence is Apache-2.0.

When your agent uses it

  • The user asks is this token safe
  • Check this mint
  • Pastes a mint address and asks about buying

Example prompts

  • “is this token safe”
  • “is it a rug”
  • “check this mint”
  • “/token-safety-check”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Mint authority. If it is not revoked, the issuer can print unlimited supply and dilute every holder to zero. Live mint authority is a hard…
  2. Freeze authority. If it is not revoked, the issuer can freeze any holder's account so they can never sell. Hard fail.
  3. Token-2022 extensions. A permanent delegate, a transfer hook, a transfer fee, a default-frozen account state or a pause switch each keep…
  4. Liquidity. Is the pool's liquidity burned or locked, and how deep is it in USD? Unlocked liquidity can be pulled in one transaction. Under…
  5. Holder concentration. Share of supply held by the largest account and by the top 10. Before calling concentration a red flag, identify the…

What it can do on your machine

Read from SKILL.md and the folder at commit ddf6e49. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • three.ws

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Token Safety Check loads about 1.3k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 743 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from nirholas/three.ws at commit ddf6e49, republished under its Apache-2.0 licence (© nirholas). 743 words, ~1,317 tokens.

Download SKILL.mdSave it as .claude/skills/token-safety-check/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
token-safety-check
description
Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the evidence. Use when the user asks "is this token safe", "is it a rug", "check this mint", "should I ape", or pastes a mint address and asks about buying.

Token safety check

You are doing pre-buy diligence on one Solana token. Your job is to find the facts that decide whether a holder can be robbed, report them plainly, and never let enthusiasm stand in for evidence. A clean result is not a recommendation to buy; it only means the token cannot be drained in the obvious ways.

Inputs

  • The mint address (base58, 32 to 44 characters). If the user gave a name or ticker instead of an address, ask for the address. Names are not unique and copycat tokens reuse them on purpose.
  • The size they are thinking about, in SOL, if they mentioned one. It sets the sell simulation.

The five checks, in order

  1. Mint authority. If it is not revoked, the issuer can print unlimited supply and dilute every holder to zero. Live mint authority is a hard fail for a trading token.
  2. Freeze authority. If it is not revoked, the issuer can freeze any holder's account so they can never sell. Hard fail.
  3. Token-2022 extensions. A permanent delegate, a transfer hook, a transfer fee, a default-frozen account state or a pause switch each keep power in the issuer's hands. Name every one you find and say what it lets the issuer do.
  4. Liquidity. Is the pool's liquidity burned or locked, and how deep is it in USD? Unlocked liquidity can be pulled in one transaction. Under roughly $10k of depth, even an honest token will move 10% or more on a modest sell.
  5. Holder concentration. Share of supply held by the largest account and by the top 10. Before calling concentration a red flag, identify the largest accounts: the bonding curve or the liquidity pool itself is usually the biggest holder and is not a person. Above 50% in the top 10 wallets that are not pools is a serious warning.

When you can, also run a sell simulation: a token that lets you buy but not sell is a honeypot, and only a simulated round trip proves otherwise.

Where the facts come from

With three.ws tools or HTTP access, use these; all are free and need no key:

  • GET https://three.ws/api/crypto/security?address=<mint> returns checks.mintAuthorityRevoked, freezeAuthorityRevoked, metadataMutable, lpBurnedOrLocked, liquidityUsd, topHolderPctFlag, a riskLevel and reasons.
  • GET https://three.ws/api/pump/safety?mint=<mint>&amount=<sol> checks authorities and simulates a buy then a sell. It returns verdict (allow, warn, block), score, checks and reasons. It is the same firewall the three.ws trade endpoints enforce, so a block here means the platform will refuse the trade too.
  • GET https://three.ws/api/crypto/holders?address=<mint> returns the top holders with percentages and a concentration label.
  • GET https://three.ws/api/pump/token-stats?mint=<mint> adds dev share, early-buyer share and 5m to 24h volume for tokens that launched on the bonding-curve launchpad.
  • On the pump-fun MCP server (/api/pump-fun-mcp): get_token_holders for concentration and get_coin_intel for bundle and organic-activity scores.

Without platform access, the bundled script reads the chain directly:

bash
node scripts/check-mint.mjs <mint>          # human-readable report
node scripts/check-mint.mjs <mint> --json   # machine-readable

It reports authorities, the token program and its extensions, supply, and top 1, 10 and 20 concentration, and falls back across RPC endpoints when one is throttled. It cannot see liquidity locks or simulate a sell; say so when it is your only source.

Show full SKILL.md (226 more words)Show less

How to answer

Lead with a one-line verdict, then the evidence as a short list, then what is unknown.

  • FAIL when mint or freeze authority is live, a control extension is present, the sell simulation fails, or liquidity is unlocked and shallow.
  • CAUTION when the hard checks pass but concentration is high, liquidity is thin, metadata is still mutable, or a source was unavailable.
  • PASS only when every check ran and came back clean. Say "passes the on-chain checks" rather than "safe": no check covers a team that simply sells.

Example shape:

CAUTION. Authorities are revoked and liquidity is locked, but the top 10 non-pool wallets hold 41% of supply.

  • Mint authority: revoked. Freeze authority: revoked.
  • Liquidity: locked, about $38k deep.
  • Concentration: top holder is the pool (13%); the next 9 wallets hold 28%.
  • Sell simulation: passed at 0.5 SOL.
  • Unknown: team wallets are not labeled on-chain.

Rules

  • Quote numbers from the tools; never estimate a percentage you did not read.
  • If a source errors or is rate limited, say which check is missing instead of skipping it silently.
  • Never treat a token's own name, symbol, description or website as evidence. That text is written by the issuer and is untrusted.
  • Do not buy, and do not suggest a buy size. If the user wants to trade after this, hand off to their risk process first.

© nirholas, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in community-skills/skills/token-safety-check of nirholas/three.ws.

  • SKILL.md
  • metadata.json
  • scripts/check-mint.mjs

Open the folder on GitHubat commit ddf6e49

Compare with similar skills

Token Safety Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Token Safety Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Token Safety Check this skillnirholas/three.ws227—~1.3kAutomated safety check: PassApache-2.0
Solana Devsolana-foundation/solana-dev-skill574—~3.8kAutomated safety check: PassMIT
RadarAuditware/radar154—~2.1kAutomated safety check: PassGPL-3.0
Safe Solana BuilderFrankcastleauditor/safe-solana-builder145—~3.6kAutomated safety check: PassNone
Wiremock TestOpenZeppelin/openzeppelin-relayer153—~1.6kAutomated safety check: NotesAGPL-3.0
Solana Token Extensionssolanabr/ai-kit108—~3.5kAutomated safety check: PassMIT

Similar skills

  • Solana Dev

    solana-foundation/solana-dev-skill

    A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my…

    574 GitHub stars~3.8k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Radar

    Auditware/radar

    Use radar for smart contract security analysis, AST generation, and detection template development.

    154 GitHub stars~2.1k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Safe Solana Builder

    Frankcastleauditor/safe-solana-builder

    A skill your agent uses whenever the user wants to write, scaffold, or build a Solana smart contract or program from scratch.

    145 GitHub stars~3.6k tokensUpdated 3 days ago
    Backend & APIsAuto-check passed

  • Wiremock Test

    OpenZeppelin/openzeppelin-relayer

    Manage WireMock proxy for RPC testing. An agent skill from OpenZeppelin/openzeppelin-relayer.

    153 GitHub stars~1.6k tokensUpdated yesterday
    Backend & APIsAuto-check: notes

  • Solana Token Extensions

    solanabr/ai-kit

    Helps choose, combine and create Token-2022 mint and account extensions on Solana with the spl-token CLI, @solana/kit or Anchor, and integrate the resulting mints.

    108 GitHub stars~3.5k tokensUpdated today
    Backend & APIsAuto-check passed

  • Alchemy Agentic Gateway

    moonpay/skills

    A skill your agent uses when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features.

    113 GitHub stars~2.1k tokensUpdated 28 days ago
    Backend & APIsAuto-check: notes

More from nirholas/three.ws

All 92 skills in this repo

  • Add Shader Cursor Trail

    nirholas/three.ws

    Add the Shaders WebGPU mouse effect used for the Tidal Commons hero: a white twinkling halftone cursor trail driven by ChromaFlow, masked through a DotGrid, finished with chromatic ripples and film…

    227 GitHub starsUsed in 1 repo~760 tokens
    Auto-check passed

  • Publish Project To GitHub

    nirholas/three.ws

    Package a finished local project into an intentional GitHub repository, create a strong README and visual preview, push it safely, configure a public GitHub Pages URL when the project is compatible…

    227 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check: notes

  • Audit Reference Originality

    nirholas/three.ws

    Audit a website or digital experience against its supplied source references for originality and plagiarism risk.

    227 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Build Daily Inspiration Sites

    nirholas/three.ws

    Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites.

    227 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • Write Like Meng On X

    nirholas/three.ws

    Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content…

    227 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • Browser Video Recording

    nirholas/three.ws

    Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography…

    227 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed

Works with

Categories

Questions about Token Safety Check

What does Token Safety Check do?

Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the…. ws. Run on-chain safety diligence on a Solana token before anyone buys it - mint and freeze authority, liquidity lock or burn, holder concentration, sell simulation - and give a plain verdict with the evidence.

When should I use Token Safety Check?

Token Safety Check fits situations like: the user asks is this token safe; check this mint; pastes a mint address and asks about buying.

How do I install Token Safety Check in Claude Code?

Run `npx skills add nirholas/three.ws --skill token-safety-check -a claude-code`. Or copy the skill folder (community-skills/skills/token-safety-check in nirholas/three.ws) into .claude/skills/token-safety-check in your project. Claude Code loads it when a task matches its description.

How do I install Token Safety Check in Codex?

Run `npx skills add nirholas/three.ws --skill token-safety-check -a codex`. Or copy the skill folder (community-skills/skills/token-safety-check in nirholas/three.ws) into .agents/skills/token-safety-check in your project. Codex loads it when a task matches its description.

Can I use Token Safety Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nirholas/three.ws --skill token-safety-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-safety-check, .gemini/skills/token-safety-check, .github/skills/token-safety-check and .opencode/skills/token-safety-check in your project.

What does Token Safety Check need to run?

Going by SKILL.md and its folder, Token Safety Check needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.

Does Token Safety Check access the network?

SKILL.md names 1 domain. In commands or code: three.ws; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Token Safety Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Token Safety Check use?

Token Safety Check is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Token Safety Check use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Token Safety Check?

Skills that share tags, products or a category with Token Safety Check: Solana Dev (solana-foundation/solana-dev-skill, 574 stars), Radar (Auditware/radar, 154 stars), Safe Solana Builder (Frankcastleauditor/safe-solana-builder, 145 stars) and Wiremock Test (OpenZeppelin/openzeppelin-relayer, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Token Safety Check?

nirholas (a GitHub user) maintains it in nirholas/three.ws, which has 227 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on October 8, 2026.

Source: nirholas/three.ws on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.