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 rhein1/agoragentic-integrations --skill integration-qualificationgit clone --depth 1 https://github.com/rhein1/agoragentic-integrationsWrote 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/rhein1/agoragentic-integrations/integration-qualification)<a href="https://agentmods.dev/skills/rhein1/agoragentic-integrations/integration-qualification"><img src="https://agentmods.dev/badge/skills/rhein1/agoragentic-integrations/integration-qualification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00490 |
| Opus 5 | $0.00015 | $0.00245 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
integration-qualification 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 3d 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
Integration qualification
Use this workflow when an external framework, host, protocol, or package may deserve an Agoragentic adapter or compatibility record.
- Identify the canonical upstream project from official metadata.
- Pin the exact stable tag, source commit, released asset name, size, URL, and independently recomputed SHA-256 digest.
- Record release drift without changing the pin or executing a newer binary.
- Classify levels with the prerequisite graph in
src/index.mjs: policy and runtime both branch from source; exact requires runtime; hosted requires exact; production requires hosted. Never infer a capability from an adjacent branch. - Build only the minimum truthful adapter needed for the requested level.
- Run conformance and adversarial cases at the exact evidence boundary. Verify bytes before extraction or execution.
- Generate and verify a schema-closed, public-safe evidence packet. Require real RFC 3339 timestamps, credential-free HTTPS URLs, positive safe-integer byte counts, nonblank evidence references, own required object fields, and dense index-only arrays. Reject proxies, accessors, cycles, credentials, local identities, private paths, and provider data before hashing. The JSON Schema is structural; always require the runtime verifier because schema-only acceptance is not evidence. The generic verifier does not dereference or authenticate caller-supplied evidence references, so the integration-specific consumer must cross-bind exact expected references and digests. Inherited values or a new hash never cure malformed evidence.
- Mark every unresolved failed or unknown observation that blocks promotion in
promotion_blockers. Preserve supported evidence levels, but withhold candidate levels until blockers are resolved; do not relabel a security or quality blocker as an action-boundary violation. - Prepare a draft PR and keep promotion human-owned.
- Record the result as verified, blocked, regressed, or
update_availablewith exact evidence references.
Never treat code, fixtures, docs, generated examples, model output, CI, or a successful hash check as exact-runtime, hosted, or production evidence by itself.
Stop before credentials, paid calls, deployment, publication, outreach, public compatibility claims, wallet or settlement changes, trust changes, or ranking changes unless the owner grants separate exact authority.
What ships with it
5 files 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.
- 3d ago First seen · 24 lines · 31 tokens per session scan A 58a84ccecb8c
integration-qualification is a skill published in the GitHub repository rhein1/agoragentic-integrations (36 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 490 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 2026-09-04.
Other skills, from other repositories
agent402
Pay-per-call access to Agent402.Tools: 500+ deterministic web tools (browser rendering, web search, PDFs, OCR, finance, SEC EDGAR, crypto/macro data, an OpenAI-compatible LLM gateway, stats/forecasting, 200+ pure-CPU utilities) plus a neutral Smart Order Router across the wider x402 ecosystem. Discover with GET…
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…
corbits-marketplace
Paid API marketplace for AI agents via Corbits. Search hundreds of premium API proxies, call them with automatic USDC micropayments (x402 protocol), and fund the payment wallet with MoonPay. Use when the user wants to access paid data APIs (crypto prices, weather, financial data, etc.) with per-request billing and no…
blockrun-cli
Use the blockrun CLI to pay-per-request AI (chat/image/video/music/speech), live data (web/X search, prediction markets, Pyth prices, 40+ chain RPC), and any x402-paid endpoint — all billed from a local USDC wallet, no API keys. Use when the user asks to run a model, generate media, query crypto/prediction/web data…
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…
xfuel-a2a-bid
Coordinate agent-to-agent work on XFuel's A2A circuit: discover provider agents, send an A2A message with TFUEL escrow, settle a bid on delivery via Fair Exchange (PAS signature), and (on-chain) form agent swarms of up to 18 members. Use when an agent needs to delegate a task to another agent, run a compute auction…