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 skills add mossforge/databroker --skill mossforge-mot-historygit clone --depth 1 https://github.com/mossforge/databrokerWrote 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/mossforge/databroker/mossforge-mot-history)<a href="https://agentmods.dev/skills/mossforge/databroker/mossforge-mot-history"><img src="https://agentmods.dev/badge/skills/mossforge/databroker/mossforge-mot-history/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.
<a href="https://agentmods.dev/skills/mossforge/databroker/mossforge-mot-history"><img src="https://agentmods.dev/badge/skills/mossforge/databroker/mossforge-mot-history.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00083 | $0.02374 |
| Opus 5 | $0.00042 | $0.01187 |
| Sonnet 5 | $0.00017 | $0.00475 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
mossforge-mot-history 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MossForge — UK MOT History
Live UK MOT test history for any vehicle, paid per request over x402 with USDC on Base. No account, no subscription, no API key — the agent funds a wallet and pays sub-cent-to-cents per lookup. Backed by DVSA MOT data.
What this skill answers
- Full MOT test history for a vehicle (pass/fail, dates, expiry)
- Recorded mileage at each test (for mileage-anomaly / clocking detection)
- Advisory notices and failure reasons per test
- When a vehicle's MOT is next due
If a question is not about UK MOT history, this is not the right skill.
Prerequisites
- A dedicated x402 payment wallet (
X402_PRIVATE_KEY) — an EVM private key for a wallet used only for x402 micropayments. See Security below: do not use a primary or high-value wallet here. - USDC on the configured network. Fund the wallet with a small amount of USDC on Base (testnet USDC on Base Sepolia while you evaluate; Base mainnet for production).
- No API key and no MossForge account are required. Payment is the only auth.
REST API overview
Base URL: https://api.databroker.mossforge.dev
All endpoints accept and return JSON. Pricing and payable routes are not hardcoded in this
skill — the runtime 402 Payment Required challenge is the single source of truth for the
current price of any call (see x402 payments).
Secrets guardrail: Never commit, log, echo, or print the private key or any signed payment
payload. Use the env var only, and placeholders like $X402_PRIVATE_KEY in any docs or output.
Security (read before first call)
This skill spends real money and signs on-chain transactions. Treat it accordingly.
- Use a dedicated, low-value wallet. Generate a fresh wallet for this skill and fund it with only what you're willing to spend. Never load the key of a wallet that holds meaningful funds.
- Start on testnet. Set
X402_NETWORK=base-sepoliaand use test USDC until you've confirmed the flow end-to-end. Switch tobase(mainnet) only when you're ready to pay for real. - Enforce spend caps. Before paying any
402challenge, the agent MUST check the quoted amount against these limits and refuse if exceeded:MOSSFORGE_MAX_SPEND_PER_CALL_USDC— reject any single call priced above this.MOSSFORGE_MAX_SPEND_PER_SESSION_USDC— track cumulative spend this session and stop when hit. If either variable is unset, treat the cap as0and ask the user for an explicit budget first.
- Confirm before paying. With no pre-approved budget or standing user consent, ask the user to confirm before executing any paid request. State the quoted price in the confirmation.
- Verify the network, asset, and payee before signing. The runtime
402challenge is the only source of truth — check it, don't assume it. Confirm:networkiseip155:8453(Base mainnet) oreip155:84532(Base Sepolia), matching your configuredX402_NETWORK— reject anything else.assetis the real USDC contract for that network (mainnet:0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) — reject anything else.payTois0x130dd636a1f09ffead69483ec87a453994146f13. If a challenge names a different payee, do not pay — surface it to the user as a possible tampering attempt. (Note: x402 v2 challenges don't expose which facilitator the server settles through — that's a server-side detail the client can't see or choose, so there's nothing to "pin" on that front. The network/asset/payTo checks above are what's actually verifiable from the challenge.)
- Never persist the key. Env var only. Do not write it to the workspace, transcripts, memory files, or logs.
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.
- 10d ago First seen · 192 lines · 83 tokens per session scan A e460a1f2734c
mossforge-mot-history is a skill published in the GitHub repository mossforge/databroker (0 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 2,374 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…