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 razel369/intentfence --skill inspect-x402-endpointsgit clone --depth 1 https://github.com/razel369/intentfenceWrote 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/razel369/intentfence/inspect-x402-endpoints)<a href="https://agentmods.dev/skills/razel369/intentfence/inspect-x402-endpoints"><img src="https://agentmods.dev/badge/skills/razel369/intentfence/inspect-x402-endpoints/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/razel369/intentfence/inspect-x402-endpoints"><img src="https://agentmods.dev/badge/skills/razel369/intentfence/inspect-x402-endpoints.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 | $0.00070 | $0.00843 |
| Opus 5 | $0.00035 | $0.00421 |
| Sonnet 5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
inspect-x402-endpoints 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect x402 Endpoints
Use IntentFence to make one bounded, credential-free request to a public HTTPS route and validate its live x402 challenge. IntentFence never follows redirects, forwards caller credentials, or pays the target.
Collect the policy
Require one target_url. Default to GET; use HEAD or POST only when the
caller identifies the intended method. For POST, include only the public body
needed to elicit the payment challenge.
Ask for these optional limits when they matter:
max_price_usdc: the largest target price the caller accepts.allowed_payees: the exact Base recipient addresses the caller already approved.
Never send a cookie, API key, bearer token, wallet signature, private key, or seed phrase to the target or IntentFence. This check proves endpoint readiness and policy fit at the observation time; it does not prove merchant identity, authorization, delivery, or future behavior.
Run the check
Prefer the MCP tool intentfence_x402_readiness at:
https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp
Pass arguments such as:
{
"target_url": "https://merchant.example/api/paid-resource",
"method": "GET",
"max_price_usdc": "0.10",
"allowed_payees": ["0x1111111111111111111111111111111111111111"]
}
The live check costs exactly 0.002 USDC on Base. Make the first call without a
payment to inspect IntentFence's own PAYMENT-REQUIRED response. Before a
wallet signs or an MCP client automatically retries, show the fee and obtain
the caller's explicit authorization. Cap the IntentFence payment at 2000 USDC
atomic units and preserve the input unchanged across the retry.
If no x402-capable signer is available, return the challenge and integration guidance. Do not ask the caller to paste reusable wallet credentials.
Use REST when MCP is unavailable
POST the same input to:
https://agentpass-protocol.rmalka06.chatgpt.site/api/x402-readiness?utm_source=agent_skill&utm_medium=agent&utm_campaign=inspect_x402_endpoints
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.
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.
- 9d ago First seen · 88 lines · 70 tokens per session scan A f1703f174cf2
inspect-x402-endpoints is a skill published in the GitHub repository razel369/intentfence (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 843 once invoked, about $0.0003 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
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
solidity-security
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
routing-card-authoring
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.
hephaestus-upload
Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.
hep-network
Staff a task from registered Local, owner Cloud, and public Hub agents.
hep-upload
Upload an Agentlas agent after asking Cloud vs Hub first.