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/thefraudfather/flint-plugin/verify-agent-integritynpx skills add thefraudfather/flint-plugin --skill verify-agent-integritygit clone --depth 1 https://github.com/thefraudfather/flint-pluginWrote 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/thefraudfather/flint-plugin/verify-agent-integrity)<a href="https://agentmods.dev/skills/thefraudfather/flint-plugin/verify-agent-integrity"><img src="https://agentmods.dev/badge/skills/thefraudfather/flint-plugin/verify-agent-integrity.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 5.1 | $0.00226 | $0.02466 |
| Opus 5 | $0.00113 | $0.01233 |
| Sonnet 5 | $0.00045 | $0.00493 |
| Haiku 4.5 | $0.00023 | $0.00247 |
Grade A, and why
flint-verify-agent-integrity 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 5d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FLINT: Verify Agent Integrity Before Payment
What this is for
AI agents are being handed spending authority across payment and stablecoin rails. The existing fraud stack was built for humans and degrades when an agent, rather than a person, is the one transacting. Inside a single organization, identity is largely solved (SPIFFE issues workload identity, A2A signs agent cards, the platform governs its own agents). None of that travels across an organizational boundary: when an agent shows up at a merchant or API the issuer is not a party to, the counterparty has no way to know the agent is who it claims, is allowed to make this purchase, and has not been hijacked mid-task.
FLINT is the layer that answers those questions at transaction time. This skill teaches you to use FLINT's verify-before-pay loop on your own, at the moment an agent is about to move value, so the agent can be trusted to transact and a signed evidence trail exists if anything is later disputed.
The distinction that matters: identity answers who the agent is, FLINT also answers is it authorized for this action and is it still uncompromised. Those last two are the integrity question, and they are what protects the user from an agent that has been taken over, diverted to a new payee, or impersonated.
FLINT is rail-neutral. It verifies the agent; it does not move the money. The payment rail (card, stablecoin, x402, ACH) still executes the transfer. FLINT sits in front of it and decides whether the transfer should proceed.
How agents get compromised (why this matters)
The unsettling part is that a compromised agent usually looks fine. Identity checks still say "yes, this is agent X." A few real patterns this verify-before-pay check is built to catch:
- Diversion by injected instruction. An agent reads a web page, email, invoice, or tool result that carries hidden instructions, and follows them, quietly changing the payee or redirecting a legitimate payment to an attacker's wallet. The agent passes every health check; its behavior simply drifted. The payment looks routine unless something verifies the action against the agent's declared authority before it executes. FLINT's integrity check plus a declared scope catches a payment that no longer matches what the agent was authorized to do.
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.
- 5d ago First seen · 180 lines · 226 tokens per session scan A 98e663087995
flint-verify-agent-integrity is a skill published in the GitHub repository thefraudfather/flint-plugin (0 stars, last pushed 2mo ago), licensed MIT. It adds 226 tokens to every session and 2,466 once invoked, about $0.0011 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
t2000-job
Escrow USDC for agent-to-agent deliverable work (A2A jobs). Use when hiring another agent for async work (research reports, builds, SLA tasks) or when selling deliverable work yourself (list a service: fixed price + SLA, no server needed), or posting/claiming open jobs on the board (t2 job open / claim) — anything…
t2000-receive
Generate a payment request for the t2000 Agent Wallet — print the wallet address, an ANSI QR code, and (via MCP) a Payment Kit URI (sui:pay?…). Use when asked to receive a payment, share a wallet address, create a payment link, or set up a fund-me link.
t2000-send
Send USDC, USDsui, or SUI from the t2000 Agent Wallet to another Sui address. Use when asked to pay someone, transfer funds, send money, tip a creator, or make a payment to a specific Sui address or SuiNS name. Do NOT use for API payments — use the t2000-pay skill for x402-protected services.
t2000-swap
Swap tokens on Sui via Cetus Aggregator (20+ DEXs, best-route across SUI, USDC, USDsui, USDT, USDe, ETH, GOLD, NAVX, WAL, vSUI, and more). Use when asked to swap, trade, convert, exchange, or "turn X into Y". Do not use for sending — use the t2000-send skill for transfers.
t2000-financial-amounts
Money and token-metadata safety — floor display amounts (never round up), per-token decimal precision, preset/chip amount math, and the canonical token registry that owns every coin type and decimal count. Use when formatting or displaying a balance, computing a max/percentage/preset amount, converting between display…
t2000-check-balance
Check the t2000 Agent Wallet balance on Sui. Use when asked about wallet balance, how much USDC / USDsui / SUI is available, or total funds. Also use before any send, swap, or pay operation to confirm sufficient funds exist.