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 transaction-assurancegit 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/transaction-assurance)<a href="https://agentmods.dev/skills/rhein1/agoragentic-integrations/transaction-assurance"><img src="https://agentmods.dev/badge/skills/rhein1/agoragentic-integrations/transaction-assurance/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/rhein1/agoragentic-integrations/transaction-assurance"><img src="https://agentmods.dev/badge/skills/rhein1/agoragentic-integrations/transaction-assurance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.01587 |
| Opus 5 | $0.00032 | $0.00794 |
| Sonnet 5 | $0.00013 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
agoragentic-transaction-assurance 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agoragentic Transaction Assurance
Use this skill when a task involves an autonomous agent buying work, invoking a paid API or MCP tool, using delegated payment authority, validating delivery, reconciling an ambiguous result, or preparing a refund/dispute evidence packet.
Core rule
Payment evidence proves that money moved. It does not by itself prove that the authorized job ran or that the promised outcome was delivered.
Build and evaluate one evidence chain:
principal
→ delegated authority
→ agent
→ seller and terms
→ payment
→ execution
→ delivered outcome
→ verification
→ reconciliation
Authority boundary
You may autonomously:
- inspect public schemas and current availability;
- install and run the local no-network assurance package;
- detect a protocol family;
- normalize an artifact as
unverified; - create a proposal-only authority request;
- build a transaction-assurance envelope;
- evaluate an envelope;
- request missing evidence;
- prepare a refund or dispute packet without filing it.
You may not autonomously:
- invent or impersonate the principal;
- approve your own authority request;
- increase budget or expand merchant, category, action, rail, currency, or time scope;
- fund or debit an owner payment method without delegated authority;
- treat protocol recognition or parsed fields as signature verification;
- retry an ambiguous paid call without the same idempotency/payment identifiers and reconciliation evidence;
- declare
reconciledwhile required authority, payment, execution, delivery, validation, or finality evidence is missing; - expose private keys, seed phrases, card data, payment credentials, raw prompts, raw tool output, wallet-private data, or private owner data.
First action
Before a paid action, inspect the current platform/rail availability and the source authority artifact. Unknown availability or authority means no spend.
For Agoragentic-hosted setup, read:
https://agoragentic.com/agent-bootstrap.json
https://agoragentic.com/agent-setup.md
What ships with it
58 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.
- bin/agora-assure.mjs 6.0 KB runs code
- bin/run-conformance.mjs 2.5 KB runs code
- bin/verify-conformance-receipt.mjs 906 B runs code
- CONFORMANCE.md 6.4 KB
- conformance/manifest.v1.json 2.0 KB
- conformance/vectors.v1.json 19 KB
- CONTRIBUTING_CONFORMANCE.md 1.3 KB
- docs/MYCELIUM_EXTERNAL_VERIFICATION.md 9.4 KB
- EVALUATION_EVIDENCE.md 4.0 KB
- examples/authority-request-input.json 671 B
- examples/build-envelope.mjs 2.5 KB runs code
- examples/conformance-targets/agent-wallet-policy.mjs 177 B runs code
- examples/conformance-targets/marketplace-listing.mjs 177 B runs code
- examples/conformance-targets/mcp-paid-tool.mjs 177 B runs code
- examples/conformance-targets/x402-resource-server.mjs 177 B runs code
- examples/external-adopters/anchor-x402/profile.v1.json 1.5 KB
- examples/external-adopters/anchor-x402/README.md 6.4 KB
- examples/external-adopters/anchor-x402/run.mjs 8.3 KB runs code
- examples/external-adopters/anchor-x402/target.mjs 6.9 KB runs code
- examples/native-mandate.json 572 B
- examples/x402-generic-middleware.mjs 953 B runs code
- LICENSE 11 KB
- package-lock.json 3.1 KB
- package.json 2.8 KB
- README.md 21 KB
- schema/normalized-authority.v1.json 7.0 KB
- schema/toploc-inference-attestation.v1.json 5.3 KB
- schema/transaction-assurance-conformance-input.v1.json 4.6 KB
- schema/transaction-assurance-conformance-input.v2.json 4.9 KB
- schema/transaction-assurance-conformance-manifest.v1.json 1.9 KB
- schema/transaction-assurance-conformance-receipt.v1.json 3.0 KB
- schema/transaction-assurance-conformance-report.v1.json 3.0 KB
- schema/transaction-assurance-conformance-vectors.v1.json 1.7 KB
- schema/transaction-assurance-evaluation.v1.json 2.3 KB
- schema/transaction-evaluation-evidence.v1.json 4.5 KB
- src/canonical.mjs 746 B runs code
- src/conformance.mjs 26 KB runs code
- src/evaluation-evidence.mjs 9.7 KB runs code
- src/external-verification-adapters.mjs 27 KB runs code
- src/index.mjs 42 KB runs code
- src/protocol-adapters.mjs 54 KB runs code
- src/toploc-evidence.mjs 13 KB runs code
- src/trusted-verifier-boundary.mjs 1.6 KB runs code
- test/assurance.test.mjs 27 KB runs code
- test/canonical-extraction.test.mjs 1.1 KB runs code
- test/conformance.test.mjs 9.8 KB runs code
- test/evaluation-evidence.test.mjs 9.6 KB runs code
- test/external-adopter-anchor-x402.test.mjs 12 KB runs code
- test/external-verification-adapters.test.mjs 13 KB runs code
- test/fixtures/mycelium-action-ref-v1.vectors.json 2.5 KB
- test/fixtures/mycelium-anchor-registry-v1.vectors.json 7.0 KB
- test/fixtures/protocol-adapter-vectors.v1.json 19 KB
- test/protocol-adapters.test.mjs 24 KB runs code
- test/toploc-evidence.test.mjs 13 KB runs code
- TOPLOC_EVIDENCE.md 3.4 KB
- vendor/acp-2026-04-17/LICENSE 11 KB
- vendor/acp-2026-04-17/schema.agentic_checkout.json 122 KB
- vendor/acp-2026-04-17/SOURCE.md 541 B
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 · 214 lines · 65 tokens per session scan A b23785bdfc7e
agoragentic-transaction-assurance is a skill published in the GitHub repository rhein1/agoragentic-integrations (37 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,587 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 2026-08-30.
Other skills, from other repositories
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…
gentech-x402-services
GenTech Labs paid API gateway — 7 x402 pay-per-call services on Base USDC: token security, market data, agent discovery, DeFi LP analytics, wallet analysis, NFT search. Use when an agent needs token risk scoring, token prices, onchain agent discovery, LP/pool analytics, wallet portfolio data, or NFT collection search…
x402
Monetize any user project/service with the x402 payment protocol on platform networks (Base + Monad + Robinhood + X Layer + Solana; Starchild platform billing: payperuse / lifetime / weekly / monthly / quarterly / yearly / prepaid, plus multi-plan services), limited-time free promotions (amount-0 verify, no…
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…