More screenshots
Works with the AI Agents you already use
Agent Spend Mandate & Budget Ledger Verifier
Verify local agent spend mandates and transaction records for merchant, category, currency, expiry, per-transaction and cumulative budget breaches.
$7
Agent Spend Mandate & Budget Ledger Verifier
Example session with this skill installed
Verify my authorized local files spend-mandates.json and transactions.csv. Bind every transaction to its declared mandate, check merchant, category, currency, expiry, per-transaction and cumulative limits, and write a new evidence packet to ./spend_review.
- Read your context and instructions
- Compiled the agent spend mandate
- Generated the data export
Spend-mandate review complete
The supplied transaction ledger was checked locally against the supplied mandate records. No payment system was contacted and neither source file was changed. evidence-receipt.json binds every input and generated output with SHA-256.
| Check | Sample result |
|---|---|
| Transactions inspected | 24 |
| Transactions bound to a mandate | 23 |
| Missing mandate reference | 1 |
| Expired mandate | 2 |
| Merchant or category mismatch | 3 |
| Currency mismatch | 1 |
| Per-transaction limit breach | 2 |
| Cumulative budget breach | 1 |
Findings requiring review
- txn_019 references a mandate ID absent from the supplied mandate file.
- Two transactions occurred after their mandate expiry timestamps.
- Three records use a merchant or category outside the allowed values.
- One EUR transaction is attached to a USD-only mandate.
- mandate_004 exceeds its supplied cumulative budget after txn_022.
Files created
transaction-binding.csv shows the exact mandate match and rule result for each transaction. budget-usage.csv totals supplied amounts by mandate. issues.jsonl stores machine-readable findings, while SPEND_MANDATE_REVIEW.md provides this human summary. result.json and evidence-receipt.json preserve totals and hashes.
Next steps
Review the source authorization and transaction evidence for every flagged row before taking any external action. The verifier did not authenticate identities or signatures, issue a mandate, approve spending, access a card or wallet, execute a payment, enforce policy or provide a legal compliance attestation.
transaction-binding.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
This downloadable local package verifies authorized buyer-supplied agent spending mandates and transaction records and produces a fixed, reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates:
- result.json
- transaction-binding.csv
- budget-usage.csv
- issues.jsonl
- SPEND_MANDATE_REVIEW.md
- evidence-receipt.json
The deterministic core binds each transaction to its declared mandate and checks merchant, category, currency, validity window, per-transaction limit and cumulative budget rules. It rejects unsafe paths and malformed inputs, never overwrites an existing packet, escapes formula-active CSV cells and binds every input and output with SHA-256. Processing stays local; no API key, login, upload, telemetry or payment action is included.
Best for agent-commerce builders and governance operators testing bounded delegated-spending records. Requires Windows 11, Python 3.11–3.14 and authorized local evidence files. Optional mcp==2.2.0 enables the local adapter.
Limitations: no cryptographic signature or identity verification, mandate issuance, approval, card or wallet access, payment execution, refund, dispute, policy enforcement or legal compliance attestation. This is a one-time local V1.
Requires local JSON files for mandates and transactions. Cannot access live remote APIs or perform external account actions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Requires
Permissions
Runs the bundled local Python CLI, reads only buyer-selected mandate and transaction files, and writes a new review packet locally. No browser, network access, payment account or environment secrets required.