A guide for using Loyal Spark, an onchain loyalty system on the Base blockchain. It covers loyalty points, rewards, vouchers, gift certificates, and peer-to-peer trading through MCP or REST.

Creating loyalty programs, issuing or transferring points, managing rewards and vouchers, redeeming gift certificates, and trading through escrow. It supports integrations with Base Account, CDP MPC, or another wallet.

It helps an agent follow the required onboarding and use the protocol's supported flows. It also explains that transactions return data ready for a wallet or signing service to approve.

loyal-spark — Skill for Claude Code and Codex by aspekt19

Install

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.

Any agent

npx skills add aspekt19/unboxed-loyalty-spark --skill loyal-spark

Clone the repo

git clone --depth 1 https://github.com/aspekt19/unboxed-loyalty-spark

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aspekt19/unboxed-loyalty-spark/loyal-spark/github.svg)](https://agentmods.dev/skills/aspekt19/unboxed-loyalty-spark/loyal-spark)

Your own site

<a href="https://agentmods.dev/skills/aspekt19/unboxed-loyalty-spark/loyal-spark"><img src="https://agentmods.dev/badge/skills/aspekt19/unboxed-loyalty-spark/loyal-spark/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aspekt19/unboxed-loyalty-spark/loyal-spark"><img src="https://agentmods.dev/badge/skills/aspekt19/unboxed-loyalty-spark/loyal-spark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,131 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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: 4 findings, up to medium

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 →

medium Data Exfiltration · line 63
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 64
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 65
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 MCP Rug Pull · line 52
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]

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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.01131
Opus 5	$0.00039	$0.00566
Sonnet 5	$0.00016	$0.00226
Haiku 4.5	$0.00008	$0.00113

Measured 8d ago against content hash 405fe65ea6ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

loyal-spark 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 8d 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.

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.

public/skills/loyal-spark/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loyal Spark Skill

[!IMPORTANT] Run the short onboarding below at the start of every conversation that touches Loyal Spark, including conversations that jump straight to a single tool. Onboarding is two sentences plus one disclaimer.

Detection

The Loyal Spark MCP exposes its tools to the harness when connected. If no get_platform_info, list_loyalty_programs, or create_loyalty_program tool is callable, the MCP server is not installed — direct the user to references/install.md and stop.

If Loyal Spark tools are available, load references/tone.md and continue to Onboarding. If sibling files are not readable, fetch the same relative path from the repository's public branch. Load references lazily only when the conversation needs them.

Onboarding

Briefly mention what is available — one sentence. The user can create native B20 loyalty programs on Base (or legacy ERC-20 through the API), mint and transfer points, manage rewards and vouchers, issue and redeem LOYAL-XXXXXX gift certificates, and trade tokens on a P2P escrow marketplace.
Show this disclaimer verbatim before any write:

By using Loyal Spark you agree to the Loyal Spark Terms (https://loyalspark.online/legal/terms) and Privacy Policy (https://loyalspark.online/legal/privacy). Loyal Spark prepares onchain calldata; the connected wallet (Base Account, CDP MPC, or a user wallet) is what actually signs and broadcasts transactions on Base mainnet (chain 8453).
Identity is optional up front. Only call profile tools when the user asks who they are or when a flow needs the bound wallet address.

Tools

Loyal Spark advertises its own tool catalog (39 merchant + 20 recipient tools). Read tool descriptions exposed by the MCP — they are the source of truth; do not preload a copied catalog from this skill.

Topic	Reference
Two API personas: `lsk_` vs `rwk_`	references/auth.md
B20 native spec and roles/policies	references/b20-native-spec.md
Payment choices: x402 exact, MPP, subscriptions	references/payment-scenarios.md · references/x402-paid.md
Calldata execution and fee obligations	references/calldata-flow.md
Pairing with Base MCP for signing	references/base-mcp-integration.md
Gift certificates	references/gift-certificates.md
Install steps	references/install.md
Tone, attribution and write-safety	references/tone.md

Read the full file on GitHub · 75 lines

Files

What ships with it

11 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.

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.

8d ago Changed · -16 lines · +1 tokens per session 405fe65ea6ff
12d ago First seen · 91 lines · 78 tokens per session scan A d5b76d4b6150

Subscribe to this mod's changes

loyal-spark is a skill published in the GitHub repository aspekt19/unboxed-loyalty-spark (13 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 1,131 once invoked, about $0.0004 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 2026-08-30.

Web3 and blockchain

signature-replay

Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.

PurpleAILAB/Decepticon · 31 tokens

official-sui-skills

Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…

MystenLabs/sui · 116 tokens

bridge

Cross-chain token transfers using Wormhole and CCTP.

alsk1992/CloddsBot · 13 tokens

onchainkit

Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.

alsk1992/CloddsBot · 24 tokens

marginfi

MarginFi — Solana lending and borrowing.

alsk1992/CloddsBot · 11 tokens

crypto-market-rank

Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…

tradecatlabs/tradecat-public · 85 tokens