Borrowing it
Nothing to install: this file belongs to frankxai/payment-intelligence-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/frankxai/payment-intelligence-system/main/AGENTS.mdgit clone --depth 1 https://github.com/frankxai/payment-intelligence-systemWrote 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/instructions/frankxai/payment-intelligence-system/agents-md)<a href="https://agentmods.dev/instructions/frankxai/payment-intelligence-system/agents-md"><img src="https://agentmods.dev/badge/instructions/frankxai/payment-intelligence-system/agents-md/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/instructions/frankxai/payment-intelligence-system/agents-md"><img src="https://agentmods.dev/badge/instructions/frankxai/payment-intelligence-system/agents-md.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 | $0.00709 | $0.00709 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
payment-intelligence-system AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Payment Intelligence System — Agents (cross-tool card)
The portable agent card. Same contract whether you run in Claude Code, Codex, Cursor, or Gemini CLI. This file mirrors
CLAUDE.md; if they disagree,CLAUDE.mdwins.
Status: v0.2 — hardened scaffold. UNAUDITED. NOT FOR LIVE FUNDS.
What this repo is
The L5 Payments vertical of the agentic-income ecosystem (agentic-ops-hub/ECOSYSTEM.md). A SIP-style payments-governance vertical plus a fail-closed TypeScript MCP server that authorizes but never moves money.
The one rule
No autonomous money movement, ever. Verify the AP2 mandate + enforce spend caps before any rail settles. There is no tool that moves money — and there never will be.
The swarm
A Payments Queen (queen-coordinator pattern, scoped to payments) coordinates four workers and escalates capital + irreversible actions to the founder + human gate.
| Agent | Role | Calls the MCP? |
|---|---|---|
payments-queen |
Coordinates the stream, runs the MCP tools, owns escalation | Yes — all 4 verify-only tools |
mandate-verifier |
Proves the human authorized this charge (AP2) | No — reports to queen |
spend-cap-enforcer |
Enforces per-tx / day / stream caps + replay guard | No — reports to queen |
settlement-auditor |
Writes append-only audit; reconciles | No — reports to queen |
fraud-sentinel |
Anomaly + replay + injection detection | No — reports to queen |
Definitions: agents/.
The MCP (verify-only)
mcp/ — TypeScript, @modelcontextprotocol/sdk, stdio. Four tools, all fail-closed:
| Tool | Job |
|---|---|
verify_mandate |
Reject unsigned / expired / amount-mismatched mandates |
check_spend_cap |
Per-tx / day / stream caps; single-use replay guard; over-cap → escalate |
record_audit_entry |
Append-only audit log |
require_human_approval |
Return a pending-approval object (never auto-approves) |
Wire it only to the Payments Queen. Never to a worker. See mcp/README.md.
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 Changed · +19 tokens per session 6a943c9da9b2
- 1mo ago Changed · -2 tokens per session ac2e8dae798d
- 2mo ago First seen · 62 lines · 692 tokens per session scan A ebfb8a14ebd2
payment-intelligence-system AGENTS.md is an instructions file published in the GitHub repository frankxai/payment-intelligence-system (0 stars, last pushed 3d ago), licensed MIT. It adds 709 tokens to every session, about $0.0028 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 2026-09-01.
payment-intelligence-system AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| payment-intelligence-system AGENTS.mdfrankxai/payment-intelligence-system | Instructions file | 0 | 3d ago | MIT | A | 709 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |