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/nirholas/three.ws/reactivenpx skills add nirholas/three.ws --skill reactivegit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/reactive)<a href="https://agentmods.dev/skills/nirholas/three.ws/reactive"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/reactive.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 | $0.00020 | $0.00523 |
| Opus 5 | $0.00010 | $0.00262 |
| Sonnet 5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
pump-fun-reactive scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
pump-fun-reactive
Connects to the real PumpPortal WebSocket feed and drives <agent-3d> avatar reactions
from live pump.fun events — no LLM in the loop.
Tools
enable_live_reactions
Opens a WebSocket to wss://pumpportal.fun/api/data, subscribes to new token launches
and migrations, and starts emitting avatar events every 2 seconds based on market activity.
- Returns
{ ok: true, started: true }on first call. - Returns
{ ok: true, already: true }if already running. - Reconnects automatically on disconnect (exponential backoff, up to 10 attempts).
Requires ctx.protocol — an AgentProtocol instance (or any object with an emit(action) method).
disable_live_reactions
Closes the WebSocket and stops the aggregator. Returns { ok: true, stopped: true }.
Event logic (2-second aggregator window)
Priority order within each window:
- Any migration (
txType: 'migrate') →gesture: celebrate+emote: celebration+speak: "<name> graduated!" - Big initial buy (highest-
solAmountcreate event hassolAmount > 5 SOL) →emote: curiosity+speak: "<name> just opened with a X.XX SOL buy." - Count of
txType: 'create'events:- 0 →
emote: patience - 1–2 →
emote: curiosity+look-at: user - 3–9 →
gesture: wave+emote: curiosity - 10+ →
gesture: wave+emote: celebration+speak: "Pump.fun is on fire — N new launches in 2 seconds."
- 0 →
Usage
// Install the skill and call enable
await registry.install({ uri: './pump-fun-skills/reactive/' });
const skill = registry.findSkillForTool('enable_live_reactions');
await skill.invoke('enable_live_reactions', {}, { protocol });
// Stop later
await skill.invoke('disable_live_reactions', {}, {});
What ships with it
4 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.
- yesterday First seen · 54 lines · 20 tokens per session scan A 8da17d4f4771
pump-fun-reactive is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 523 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
blockchain-cross-chain
Cross-chain protocols, IBC, LayerZero, Wormhole, Axelar, CCIP, bridges, atomic composability, shared sequencer, cross-chain message passing. Covers trust models (light clients, external validators, ZK proofs), bridge security, token representation (canonical, wrapped, native), relayer economics, and cross-chain…
xpr-network-dev
XPR Network (formerly Proton) blockchain development - proton-tsc smart contracts, @proton CLI and web SDK, RPC and Hyperion queries, DeFi (MetalX, Alcor, LOAN), NFTs, the XPR Agents job board, node and Hyperion operations. Use for anything mentioning XPR, Proton, or @proton packages.
blockchain-management
Use this skill when asked about blockchain project management, DAO governance, multi-sig operations, treasury management, tokenomics design, and web3 project methodology. Languages: Solidity, TypeScript, Python. Covers DAO governance frameworks (Compound Governor, Aave, Snapshot, Tally), multi-sig wallet operations…
modernize-move
Detects and modernizes outdated Move V1 syntax, patterns, and APIs to Move V2+. Use when upgrading legacy contracts, migrating to modern syntax, or converting old patterns to current best practices. NOT for writing new contracts (use write-contracts) or fixing bugs.
threejs-docs
Comprehensive Three.js reference covering core API (objects, cameras, lights, materials, geometries, renderers, scenes, textures, math, animation, audio, loaders, helpers, nodes), all addons (controls, postprocessing, loaders, exporters, geometries, shaders, WebXR, physics), TSL (Three.js Shading Language) functions…
coinmarketcap
Expert assistant for CoinMarketCap Pro API — price quotes, listings, historical OHLCV, market metrics, Fear & Greed Index, CMC100/CMC20 indices, exchange data, DEX data, airdrops, trending, community sentiment. Covers 10+ endpoint categories across REST + MCP + x402 pay-per-call modes. Use when the user wants: current…