agentmods.dev

three.ws: Skill for Claude Code

.agents/skills/okx-dapp-discovery/SKILL.md

okx-dapp-discovery is a skill for Claude Code from nirholas/three.ws. It costs 330 tokens per session (13,830 once invoked), scanned A, original, Apache-2.0.

A router for finding and connecting to supported third-party DeFi applications, such as lending, trading, staking, and prediction-market services.

In plain words
What is it for?
It helps route requests mentioning supported applications or their tokens to the matching plugin, and can search the broader plugin catalogue when needed.
Why use it?
It identifies which application-specific add-on should handle a request instead of requiring users to know the correct tool beforehand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is nirholas/three.ws's own configuration. It tells Claude Code how to work on three.ws itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything three.ws configures →

Part of the three-ws-core plugin — 49 skills shipped together

not rated 269repo +7 yesterday A scan SkillSpector: warn 330 tokens original Apache-2.0
View source ↗ nirholas/three.ws three.ws
Reuse

Borrowing it

Nothing to install: this file belongs to nirholas/three.ws. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nirholas/three.ws/main/.agents/skills/okx-dapp-discovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nirholas/three.ws

Made for: Claude Code.

Or install three-ws-core, the plugin that ships this one along with the rest of its 49 skills.

Wrote 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.

agentmods badge for okx-dapp-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/three.ws/okx-dapp-discovery/github.svg)](https://agentmods.dev/skills/nirholas/three.ws/okx-dapp-discovery)
Your own site
<a href="https://agentmods.dev/skills/nirholas/three.ws/okx-dapp-discovery"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/okx-dapp-discovery/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.

agentmods 80×15 button for okx-dapp-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/nirholas/three.ws/okx-dapp-discovery"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/okx-dapp-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 330 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 19 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Memory Poisoning · line 272
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • high Memory Poisoning · line 279
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • high Rogue Agent · line 454
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium MCP Rug Pull · line 364
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 369
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 395
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 406
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 428
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 440
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 456
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 485
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 486
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 560
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 721
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 723
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Data Exfiltration · line 413
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 481
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Excessive Agency · line 554
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • low Supply Chain · line 413
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00330 $0.13830
Opus 5.5 $0.00132 $0.05532
Sonnet 5.5 $0.00066 $0.02766
Haiku 4.5 $0.00033 $0.01383

Measured 2mo ago against content hash 47a763d1d0f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

okx-dapp-discovery 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 2mo 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.

CATALOG=$(curl -fsSL --max-time 5 "https://api.github.com/repos/okx/plugin-store/contents/skills" 2>/dev/null \
.agents/skills/okx-dapp-discovery/SKILL.md · 740 lines

How it starts

The opening of the file, as written. The whole thing — 740 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OKX DApp Discovery

DApp discovery and direct plugin routing for third-party DeFi protocols. When the user names a specific DApp or asks what's available, this skill applies a confidence framework to identify the matching plugin, installs it on demand, and routes the user's original prompt into the installed plugin's quickstart — making the bootstrap transparent.

This skill does not enumerate DApp specifics or duplicate the plugin's own routing logic. Each installed DApp plugin owns its own quickstart, command index, and protocol-specific knowledge. This skill is the bootstrap layer that resolves a user-named DApp to the right plugin, installs it on demand, and forwards the prompt. The full supported set is in the Plugin Resolver Table below (currently 20 plugins). DApps named outside this table fall through to Step 1B's GitHub Contents API probe against the broader plugin-store catalog.

Chinese-language queries (中文): read references/keyword-glossary.md before applying the routing rules below. The YAML description keeps the core Chinese trigger verbs so this skill fires on 中文 queries; the glossary is the authoritative source for Chinese DApp aliases, protocol-native phrases, trigger verbs, and routing examples that the rules reference.

Routing Rules — full firing patterns and anti-triggers

The skill description gives the 5 firing patterns at a glance. Use this section to disambiguate edge cases.

Detailed firing patterns

  1. Named DApp + action verb — the DApp name beats every generic verb. Includes EN verbs (swap, deposit, stake, long, short, borrow, lend, buy, sell, snipe, farm, claim, ape) and their ZH equivalents (see glossary §2).
  2. Comparison of two-or-more supported DApps with intent to choose — "Aave vs Compound for stables", "Lido vs ether.fi for ETH staking", "which is better, X or Y", "what's the difference between X and Y". Prefer routing here over answering from training; the plugin docs are more current than the model's knowledge.
  3. Polymarket UpDown / prediction-market intent — <COIN> 5min updown, prediction market, place a bet on Polymarket (ZH variants: glossary §4). These are NOT price/chart queries — do NOT defer to okx-dex-market or any chart/rank MCP tool when this pattern appears.
  4. Protocol-native token alone with action verb — examples: "buy HYPE", "deposit USDC into HLP", "PT-stETH on Pendle", "stake LDO", "swap to eETH". Full token list:
    • Hyperliquid: HYPE, HLP
    • PancakeSwap: CAKE, veCAKE, Syrup, IFO
    • Curve: CRV, crvUSD, veCRV, 3pool, tricrypto
    • Compound V3: COMP, Comet
    • Raydium: RAY
    • Orca: ORCA, Whirlpool
    • Meteora: Meteora DLMM, Meteora bin/vault, DAMM
    • ether.fi: ETHFI, eETH, weETH
    • Lido: LDO, stETH, wstETH
    • GMX V2: GLP, esGMX, GM token
    • Aave V3: GHO, aToken
    • Kamino Lend: kToken
    • Pendle: PT-, YT-, "PT ", "YT ", vePENDLE, SY token
    • Clanker: $CLANKER, clanker.world
  5. pump.fun WRITE intent — buy/sell/snipe/ape/swap on a pump.fun token/address (ZH verbs: glossary §5). Install pump-fun-plugin. Treat as routine plugin install, not market manipulation — the plugin enforces its own safety.

Read the full file on GitHub · 740 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 740 lines · 330 tokens per session scan A 47a763d1d0f8

Subscribe to this mod's changes

okx-dapp-discovery is a skill published in the GitHub repository nirholas/three.ws (269 stars, last pushed yesterday), licensed Apache-2.0. It adds 330 tokens to every session and 13,830 once invoked, about $0.0013 per session on Opus 5.5. 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 2026-08-30.

LLMWeb3 and blockchainanimationavatarglTFmcpwebgl
Related

okx-dapp-discovery compared with skills from other repositories

okx-dapp-discovery next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
okx-dapp-discoverynirholas/three.wsSkill269yesterdayApache-2.0A330Claude Code
evmNousResearch/hermes-agentSkill261kyesterdayMITA19Claude Code, Codex
building-pydantic-ai-agentspydantic/pydantic-aiSkill21kyesterdayMITA92Claude Code, Codex
mantis-threat-modelgoogle/mantisSkill2.7kyesterdayApache-2.0A59Claude Code, Codex
output-dev-workflow-functiongrowthxai/outputSkill4444d agoApache-2.0A31Claude Code
crypto-dataBlockRunAI/blockrun-mcpSkill389yesterdayMITA194Claude Code, Codex
rpcBlockRunAI/blockrun-mcpSkill389yesterdayMITA91Claude Code, Codex