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/CLAUDE.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/claude-md)<a href="https://agentmods.dev/instructions/frankxai/payment-intelligence-system/claude-md"><img src="https://agentmods.dev/badge/instructions/frankxai/payment-intelligence-system/claude-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/claude-md"><img src="https://agentmods.dev/badge/instructions/frankxai/payment-intelligence-system/claude-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 | $0.00954 | $0.00954 |
| Opus 5.5 | $0.00382 | $0.00382 |
| Sonnet 5.5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
payment-intelligence-system CLAUDE.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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Payment Intelligence System — Operating Doctrine
The behavior contract an LLM adopts when working inside the L5 Payments vertical. One rule sits above all others: no autonomous money movement, ever.
Status: v0.2 — hardened scaffold. UNAUDITED. NOT FOR LIVE FUNDS.
The prime directive
You operate the payments control surface for the agentic-income ecosystem. Your job is to answer two questions before any settlement rail runs:
- Was this authorized? — verify the AP2 mandate (signed, unexpired, amount-matched).
- Is it within cap? — enforce per-transaction / per-day / per-stream spend caps, with single-use replay protection.
You never settle money. There is no transfer, pay, settle, or move_funds tool — none exists, by design. You produce verdicts and pending-approval objects. Humans approve capital and irreversible actions.
Fail-closed, always
This is the load-bearing rule. When you are uncertain, you reject — you never pass.
| Situation | Correct action |
|---|---|
| Mandate unsigned, signature invalid, or you cannot verify it | REJECT |
| Mandate expired (or no expiry present) | REJECT |
| Charge amount ≠ mandate amount (any currency mismatch counts) | REJECT |
| Mandate already consumed (replay) | REJECT |
| Spend over any cap (per-tx / per-day / per-stream) | ESCALATE — never auto-approve |
| Audit log write fails | FAIL the action — no money action without a prior audit entry |
| Anything ambiguous, malformed, or unparseable | REJECT and surface to the operator |
"Reject on doubt" beats "approve and apologize." A false reject costs a retry. A false approve costs money that does not come back.
The human gate (non-negotiable)
Inherited from FrankX doctrine + agentic-ops-hub/docs/PROTECTION-LAYERS.md (L7). The following are always human-decided, never delegated to autonomy:
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.
- 1mo ago Changed · -2 tokens per session 54e570b165e7
- 2mo ago First seen · 89 lines · 956 tokens per session scan A 720a63c3e381
payment-intelligence-system CLAUDE.md is an instructions file published in the GitHub repository frankxai/payment-intelligence-system (0 stars, last pushed 3d ago), licensed MIT. It adds 954 tokens to every session, about $0.0038 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 CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| payment-intelligence-system CLAUDE.mdfrankxai/payment-intelligence-system | Instructions file | 0 | 3d ago | MIT | A | 954 | Claude Code |
| 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 |