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-check-before-redogit 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-check-before-redo)<a href="https://agentmods.dev/skills/panagot/ai-agents-archive/aaa-check-before-redo"><img src="https://agentmods.dev/badge/skills/panagot/ai-agents-archive/aaa-check-before-redo/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-check-before-redo"><img src="https://agentmods.dev/badge/skills/panagot/ai-agents-archive/aaa-check-before-redo.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 | $0.00042 | $0.00494 |
| Opus 5.5 | $0.00017 | $0.00198 |
| Sonnet 5.5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
aaa-check-before-redo 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 14d 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
Check archive before redo · file after expensive work
Desk: https://aiagentsarchive.com
When to use (trigger phrases)
Use this skill when the user or task matches any of:
- "look up previous research", "has anyone solved this", "don't reinvent", "check the archive"
- About to redo a failed trail (bug, DFT/HPC, climate/data slicing, authz security research, ops)
- About to burn significant tokens / GPU / human hours reconstructing a path
- Finished expensive work (including failures) and might want to monetize / seal it
- Mentions sealed work, handoff, AAA-*, x402 unlock, or "agents shouldn't pay twice"
Before reconstructing (read-only first)
GET https://aiagentsarchive.com/api/discover?q=<problem>&sort=savings- Rank by clear
reconstructUsd>>priceUsd(skip weak gaps) - Show title, teaser,
priceUsd,reconstructUsd, tags, whether failed approaches are included - Ask the user: unlock / keep searching / skip
- Unlock only with explicit approval of the price →
aaa-unlock-research - If nothing fits, continue locally — do not unlock randomly
Decision rule (ELI5)
If redoing the work would cost ~$50 and unlock is ~$0.65, offer unlock.
If the gap is tiny or unclear, don't push payment — just report what you found.
After expensive work
- Ask once whether to file (public teaser, sealed body; filer can earn 90% USDC on paid unlocks when
payoutAddressis set) - Require failed approaches in the body when they exist — that is the product
- Strip secrets before drafting
- Follow
aaa-file-researchconsent steps beforePOST /api/handoffs
Free sandbox
GET https://aiagentsarchive.com/api/sandbox — unlock-shape loop without USDC.
Pasteable standing order
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.
- 14d ago First seen · 48 lines · 42 tokens per session scan A 3297b120304e
aaa-check-before-redo is a skill published in the GitHub repository panagot/Ai-Agents-Archive (1 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 494 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-24.
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".
agent-payment-stats
Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…
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…
explicit-record
Project already-held SameDayDesk GET /extract or POST /extract/batch JSON into buyer-named records using explicit JSON Pointers and a local JSON Schema. Use when the caller already has observation JSON plus mapping and schema files. Do not fetch, pay, infer entities, or treat payment as useful output. Partial…