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 panagot/Ai-Agents-Archive --skill aaa-unlock-researchgit clone --depth 1 https://github.com/panagot/Ai-Agents-ArchiveWrote 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/panagot/ai-agents-archive/aaa-unlock-research)<a href="https://agentmods.dev/skills/panagot/ai-agents-archive/aaa-unlock-research"><img src="https://agentmods.dev/badge/skills/panagot/ai-agents-archive/aaa-unlock-research/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/panagot/ai-agents-archive/aaa-unlock-research"><img src="https://agentmods.dev/badge/skills/panagot/ai-agents-archive/aaa-unlock-research.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 | $0.00030 | $0.00250 |
| Opus 5 | $0.00015 | $0.00125 |
| Sonnet 5 | $0.00006 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
aaa-unlock-research 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 11d 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.
What it actually says
Unlock sealed research (user must approve payment)
Third-party desk: https://aiagentsarchive.com
Use only when the user explicitly asks to unlock a packet.
Consent (required before any unlock)
GET /api/handoffs/:id— show title, teaser, priceUsd, reconstructUsd estimate.- Tell the user unlock may spend USDC on Base if they use
X-PAYMENT(or writes a desk ledger receipt otherwise). - Wait for explicit user approval of the price.
- Only then
POST /api/handoffs/:id/unlockwith{ "payer": "did:aaa:<32 hex>" }andX-AGENT-ID.
Replay after unlock is free via GET .../body.
Safe browse (no payment)
GET /api/status,/api/example,/api/discover— catalog metadata only
If nothing fits
Do not unlock randomly. Ask the user whether to keep searching or stop.
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.
- 11d ago First seen · 27 lines · 30 tokens per session scan A 4ee753962c0c
aaa-unlock-research is a skill published in the GitHub repository panagot/Ai-Agents-Archive (1 stars, last pushed 8d ago), licensed MIT. It adds 30 tokens to every session and 250 once invoked, about $0.0002 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
bankr-shopify
Shopify Admin & Storefront GraphQL APIs via curl, with Bankr-native bridges. Manage products, orders, customers, inventory, metafields, webhooks, and bulk ops, then wire merchant data to onchain primitives — store a Bankr-resolvable handle (ENS, Twitter, Farcaster, wallet) on each customer as a metafield, expose…
lienfi
Research and buy tokenized US tax lien certificates on LienFi (Base, USDC) — screen the live book by NET yield with no credential, then, once your operator has authorized your wallet in a browser, register and run the prepare → sign → confirm → submit → report purchase loop from the wallet you control. LienFi signs…
megapot
On-chain USDC lottery on Base with daily drawings. Buy tickets (quick-pick or custom numbers), check the jackpot and drawing state, claim winnings, set up recurring subscriptions, and manage LP positions. Trigger on "megapot", "lottery ticket", "jackpot", "quick pick", or "did I win".
scvd-general-store
A live x402 practice counter: real settlement, no sandbox, from $0.001. Free conformance checking for any issuer's signed offers and receipts, ours or a competitor's. An evidence observatory: signed observation of what other endpoints and payments actually did, never a ranking. Reachable six ways, including browser…
x402-before-you-pay
Before an agent pays an x402 endpoint, read its 402 terms and run scvd.store's free preflight and dry run over the same bytes; decide pay / donotpay / cannottell with every reason named. Use when code or an agent is about to call a paid x402 URL, when a 402 looks wrong, or when a payment "never went through".…
web-extract
Extract public webpages as structured JSON through SameDayDesk. Use GET /extract for a single public HTTPS page, or one bounded POST /extract/batch for 2–5 caller-supplied public HTTPS URLs and explicit desired fields. A caller may explicitly request a one-item batch. Free discovery reads live schemas and 402 terms…