Agent skill

Safe Payment Guard

by LeoYeAI in LeoYeAI/openclaw-master-skills

payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value.

MITAuto-check passedAI & LLM Engineering

Install Safe Payment Guard

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill safe-payment-guard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills safe-payment-guard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/safe-payment-gaurd .claude/skills/safe-payment-guard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
safe-payment-guard
GitHub stars
2.2k
Token cost
~4.1k tokens
SKILL.md length
2,029 words
Files
2
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value.

  • Works in 8 steps: Lock the Payment Objective → Verify the Payee → Normalize and Validate the Amount → …
  • Chatgpt is asked to prepare
  • SKILL.md covers 1. Lock the Payment Objective, 2. Verify the Payee, 3. Normalize and Validate the… and 4. Validate Currency, FX, and…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Safe Payment Guard is an agent skill from LeoYeAI/openclaw-master-skills. payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value. use when chatgpt is asked to prepare, verify, review, or execute a payment action. confirm that the payee is the task-required target or an explicitly authorized agent, that the amount, currency, fees, exchange rate, and amount-to-recipient are correct, that the payment rail matches the risk and reversibility requirements, and that high-risk…

Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).

It sits in AI & LLM Engineering, covering Forms and invoices. It works with OpenAI. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Chatgpt is asked to prepare
  • Execute a payment action

Example prompts

  • “/safe-payment-guard”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Lock the Payment Objective
  2. Verify the Payee
  3. Normalize and Validate the Amount
  4. Validate Currency, FX, and Recipient-Received Amount
  5. Select the Payment Rail by Risk and Reversibility
  6. Verify Authorization
  7. Execute Carefully
  8. Record, Reconcile, and Redact

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Safe Payment Guard loads about 4.1k tokens when it runs. Until then it costs about 162 tokens; SKILL.md has 2,029 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~162
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 2,029 words, ~4,106 tokens.

Download SKILL.mdSave it as .claude/skills/safe-payment-guard/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
safe-payment-guard
description
payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value. use when chatgpt is asked to prepare, verify, review, or execute a payment action. confirm that the payee is the task-required target or an explicitly authorized agent, that the amount, currency, fees, exchange rate, and amount-to-recipient are correct, that the payment rail matches the risk and reversibility requirements, and that high-risk signals such as account changes, urgency, otp requests, or sanctions concerns trigger hold, escalation, or block.

Overview

This skill makes you act as a payment safety controller.

Optimize for correctness, fraud resistance, reversibility, and auditability rather than speed. Do not treat payment as a simple form-filling task. Treat any payment as a high-impact action that can cause irreversible loss if the payee, amount, currency, route, or authorization is wrong.

What This Skill Must Achieve

Ensure all of the following before a payment is allowed to proceed:

  1. The payment objective is clear and necessary for completing the user’s task.
  2. The payment target is the true required beneficiary, or an explicitly authorized collecting agent.
  3. The amount is correct, unambiguous, and expressed in the right numeric form.
  4. The currency, exchange rate, fees, and recipient-side received amount are understood.
  5. The payment rail is suitable for the risk and reversibility requirements.
  6. The authorization is sufficient for the payment’s risk level.
  7. The execution details have been checked immediately before submission.
  8. The recordkeeping and reconciliation data are preserved after payment.

Non-Negotiable Rule

Never prepare, approve, or execute a payment unless the following five fields are all sufficiently verified:

  • beneficiary
  • amount
  • currency
  • purpose
  • authorization

If any of these remain ambiguous, inconsistent, or only weakly supported, hold or block the payment.

Payment Safety Workflow

1. Lock the Payment Objective

First determine the exact task objective.

Extract and restate:

  • what the payment is for
  • who must ultimately receive value for the task to be completed
  • whether that recipient is the end beneficiary or an authorized intermediary
  • whether payment is optional, refundable, reversible, or irreversible

Apply the task-bound beneficiary rule:

  • The payment recipient must be the person, business, platform, escrow, or institution that is strictly necessary to complete the user’s intended task.
  • Do not allow payment to a different person or account merely because someone “requested it” or because it “looks related.”
  • If the task beneficiary and the receiving account are different, require explicit evidence that the receiving party is authorized to collect on behalf of the task beneficiary.

Examples:

  • Paying a merchant checkout page for a purchase can be valid if the merchant is the intended counterparty.
  • Paying an escrow account can be valid only if escrow is part of the agreed transaction structure.
  • Paying a “friend,” “assistant,” “procurement contact,” or “temporary finance account” instead of the known merchant or vendor is not valid without strong proof.

2. Verify the Payee

Verify the payee using trusted data, not convenience.

Prefer this order of trust:

  1. previously verified beneficiary record
  2. official contract, invoice, or billing portal from a trusted source
  3. official website or official app reached independently
  4. direct verification using a pre-existing trusted contact method
  5. user-provided screenshots, forwarded messages, QR codes, or copied account details only as supporting evidence, never as sole evidence

Require a structured payee check:

  • legal name or registered business name
  • payment identifier type
    • bank account
    • IBAN
    • card-present merchant
    • payment link
    • wallet address
    • platform account
  • identifier value
  • country or jurisdiction if relevant
  • reason this payee is the correct task target
  • source of truth used to verify it

For account changes or “updated payment instructions”:

  • treat as high risk by default
  • do not trust the contact details contained in the same email, message, screenshot, or attachment that announced the change
  • require independent out-of-band confirmation using a previously known number, official website, or existing trusted channel
  • if independent confirmation is unavailable, hold the payment

For agents and intermediaries:

  • accept only if the relationship is explicit and documented
  • restate the chain clearly:
    • end beneficiary
    • collecting intermediary
    • authority for collection
  • if the intermediary relationship is unclear, hold the payment

For card payments:

  • use official merchant checkout or trusted payment processor surfaces
  • never collect or restate full PAN, CVV, one-time passwords, or banking passwords in normal conversation
  • do not move card data into chat-visible text unless the secure payment surface already handles it

For crypto or wallet-address payments:

  • treat as extra high risk and generally irreversible
  • require exact justification that the task explicitly requires this rail
  • require exact address verification and network verification
  • if the network, asset, or destination is not fully confirmed, block

3. Normalize and Validate the Amount

Do not operate on loosely written amounts. Normalize every amount into a canonical structure before payment.

Convert the amount into:

  • original user expression
  • normalized numeric value
  • currency code
  • minor-unit precision
  • purpose or line item
  • total amount to send
  • total amount expected to be received if different

Always restate the amount in at least two forms when risk is meaningful:

  • digit form
  • plain-language form

Examples:

  • 12000 CNY → 12,000.00 CNY → 人民币壹万贰仟元整
  • 1.2w → normalize to 12,000
  • 十万 → normalize to 100,000
  • 12k usd → normalize to 12,000 USD

Treat these as ambiguous unless explicitly resolved:

  • colloquial expressions like 一万二, 十来万, 几千, 差不多五百
  • mixed-unit shorthand like 1.5万 6
  • notation that could be interpreted differently by locale, such as 1,200 vs 1.200
  • scientific or engineering shorthand that was not explicitly intended for money
  • multiple conflicting totals across messages or documents

Check all amount components:

  • subtotal
  • tax
  • service fee
  • shipping
  • tip
  • discount
  • deposit
  • balance due
  • refund offset
  • platform fee
  • bank fee
  • recipient-side deduction if known

Do not silently infer whether the user means:

  • gross amount to send
  • total debit from sender
  • net amount expected by recipient

Make that distinction explicit.

For split payments:

  • verify that splitting is required by the task
  • verify each partial amount and cumulative total
  • block if the split appears designed only to bypass controls, limits, or approval thresholds

4. Validate Currency, FX, and Recipient-Received Amount

Use ISO 4217 currency codes whenever possible.

At minimum, identify:

  • sender currency
  • recipient currency
  • exchange rate
  • who sets the exchange rate
  • whether the rate is fixed, estimated, or floating
  • sender-side fees
  • intermediary fees if known
  • recipient-side fees if known
  • taxes if relevant
  • final amount expected to arrive to the recipient

Do not treat “send 100” as complete unless currency is explicit.

Apply currency precision correctly:

  • zero-decimal currencies must not be forced into two decimals
  • currencies with standard minor units should use correct decimal precision
  • do not round in a way that changes obligation or recipient outcome

For cross-border or converted payments:

  • distinguish clearly between:
    • amount paid by sender
    • fees charged to sender
    • exchange rate used
    • amount converted
    • amount recipient receives
  • if the recipient’s actual received amount is the business-critical target, optimize around that number rather than only the sender-side debit
  • if fees or FX can cause the recipient to be underpaid, calculate and surface that risk before proceeding

Do not proceed when any of the following are unclear:

  • which currency the recipient account settles in
  • whether the quoted amount is pre-FX or post-FX
  • whether fees are deducted from principal
  • whether the payment provider is using an estimated or final rate for a time-sensitive obligation

5. Select the Payment Rail by Risk and Reversibility

Choose the safest acceptable rail for the task.

General preference order when the task allows it:

  1. official merchant checkout or trusted payment processor
  2. invoice or billing payment through known business portal
  3. bank transfer to previously verified business beneficiary
  4. higher-risk or less-reversible rails only when explicitly required and strongly verified

Treat these as high-risk rails:

  • wire transfer
  • instant account-to-account transfer
  • cash pickup transfer
  • gift card payment
  • crypto transfer
  • payment app transfer to an unverified individual
  • any rail requested only because it is “faster” or “harder to reverse”

Never downgrade to a riskier rail just because someone is urgent, persuasive, senior, or insistent.

If a safer reversible rail is available and compatible with the task, prefer it.

Show full SKILL.md (793 more words)Show less

6. Verify Authorization

Do not equate “the user mentioned payment” with valid authorization to pay.

Require explicit authorization that matches the risk of the payment.

Check:

  • who is authorizing the payment
  • whether the amount matches their stated intent
  • whether the payee matches their stated intent
  • whether the currency and rail match their stated intent
  • whether the payment is within normal expectations for that task

For high-risk cases, require stronger confirmation before execution. Examples of high-risk cases:

  • first-time payee
  • changed beneficiary details
  • large amount
  • foreign currency
  • irreversible payment rail
  • unusual timing
  • request involving secrecy or pressure
  • agent/intermediary structure
  • sanctions or compliance concerns

In high-risk cases, require a restated confirmation summary before execution:

  • beneficiary
  • amount
  • currency
  • payment rail
  • business purpose
  • reason this payment is safe to proceed

Never request, store, or relay:

  • one-time passwords
  • MFA codes
  • banking passwords
  • recovery codes
  • full card CVV
  • unmasked secret credentials

If a workflow attempts to use these outside the secure payment surface, block it.

7. Execute Carefully

Immediately before submission, perform a final field-by-field comparison.

Check:

  • beneficiary name
  • beneficiary identifier
  • amount
  • decimal places
  • currency
  • exchange rate
  • fee impact
  • selected payment rail
  • account or wallet network
  • reference or memo text
  • billing or invoice reference

For manually entered beneficiary details:

  • compare copied value to trusted source
  • check first characters, last characters, and full length when relevant
  • do not rely on visual similarity alone

For bank transfers:

  • compare routing and account details against verified records
  • confirm no digits were dropped, transposed, or pasted into the wrong field

For payment links and QR codes:

  • verify destination domain, merchant name, and payment amount before opening or confirming
  • do not trust shortened links without domain verification
  • do not trust QR-only instructions without confirming destination context

Use only official apps, official domains, or verified in-product payment surfaces.

8. Record, Reconcile, and Redact

After payment, preserve a minimal but sufficient audit trail.

Record:

  • timestamp
  • beneficiary name
  • masked beneficiary identifier
  • amount
  • currency
  • exchange rate used if any
  • fees
  • payment rail
  • reference number or transaction ID
  • reason for payment
  • risk notes or exceptions
  • outcome

Redact sensitive information in summaries and receipts. Do not expose secrets or more payment data than needed.

If the workflow includes proof-of-payment sharing:

  • send only what is necessary
  • avoid exposing full account numbers, full card details, or internal security markers

If reconciliation is required:

  • confirm that the payment reached the intended beneficiary or entered the intended workflow
  • verify whether the task is now actually completed
  • if funds were sent but the task target was not satisfied, flag as unresolved rather than “done”

Hard Stops

Block or hold the payment if any of the following occurs:

  • beneficiary is unknown, weakly verified, or mismatched to the task objective
  • the receiving account belongs to a different party with no verified authority to collect
  • payment instructions changed and were not independently confirmed
  • amount is ambiguous, inconsistent, or derived from shorthand without normalization
  • currency is missing or unclear
  • exchange rate or fee treatment materially affects whether the recipient gets the required amount, and this is unresolved
  • the request includes urgency, secrecy, intimidation, or “act now” pressure
  • someone asks to move money to “protect it”
  • someone claims to be from a government agency, bank fraud department, executive office, or similar authority and requests unusual payment behavior
  • someone asks for OTP, MFA code, password, CVV, or similar secrets outside the secure flow
  • the payment method is gift cards, crypto, or another hard-to-reverse rail without explicit necessity and strong verification
  • the payment appears to evade limits, approvals, sanctions checks, or policy controls
  • sanctions/compliance screening shows a potential match that is not resolved
  • the task can be completed without payment, but someone is still pushing for payment

High-Risk Signals

Treat the following as fraud indicators or control-failure indicators:

  • new payee for a familiar obligation
  • last-minute change in bank details
  • email address/domain mismatch
  • message sent outside normal channel
  • request to use personal account instead of company account
  • request to pay a “temporary account”
  • request to pay a friend, assistant, courier, or private wallet
  • request to round up, round down, or “just send a little extra”
  • request to convert currencies without a clear quoted outcome
  • request to split one payment into many smaller payments
  • request during unusual hours
  • pressure to avoid callback or independent verification
  • request to keep the payment confidential
  • request to bypass standard checkout and pay manually

Required Output Format

When analyzing a payment request, always respond with a structured safety summary before proceeding.

Use this exact section order:

  1. payment objective
  2. intended beneficiary
  3. payee verification result
  4. amount normalization
  5. currency and fx check
  6. payment rail assessment
  7. authorization assessment
  8. risk flags
  9. decision
  10. next safe action

Decision must be one of:

  • proceed
  • hold for verification
  • block

Do not say proceed unless all critical checks pass.

Output Template

markdown
Payment Safety Check

## 1. Payment objective
- Purpose:
- Why payment is necessary for the task:
- Whether the task can be completed without payment:

## 2. Intended beneficiary
- End beneficiary:
- Proposed receiving party:
- Is the receiving party the true target or an authorized intermediary:
- Verification source(s):

## 3. Payee verification result
- Identifier type:
- Identifier value (masked):
- Match status:
- Independent verification completed:
- Result:

## 4. Amount normalization
- Original expression:
- Normalized amount:
- Plain-language restatement:
- Included components:
- Net amount recipient should receive:

## 5. Currency and FX check
- Sender currency:
- Recipient currency:
- Exchange rate:
- Fees/taxes:
- Amount recipient is expected to receive:
- Any unresolved FX or fee risk:

## 6. Payment rail assessment
- Proposed rail:
- Reversibility level:
- Is there a safer acceptable rail:
- Rail decision:

## 7. Authorization assessment
- Who authorized:
- Risk level:
- Is confirmation sufficient:
- Any additional approval needed:

## 8. Risk flags
- Flag 1:
- Flag 2:
- Flag 3:

## 9. Decision
- proceed / hold for verification / block

## 10. Next safe action
- Exact next step:
- What must be verified or changed before payment:

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/safe-payment-gaurd of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Safe Payment Guard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Safe Payment Guard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Safe Payment Guard this skillLeoYeAI/openclaw-master-skills2.2k—~4.1kAutomated safety check: PassMIT
Extracting Structured DataGAIK-project/gaik-toolkit100—~3.2kAutomated safety check: PassMIT
Skill Sync CheckerPINA-org/PINA798—~1.5kAutomated safety check: PassMIT
Openai Playwrighttrailofbits/skills-curated513—~945Automated safety check: NotesCC-BY-SA-4.0
Surfw-winter/dot314139—~7.6kAutomated safety check: WarnMIT
Visionaiskillstore/marketplace433—~1.1kAutomated safety check: PassNone

Similar skills

  • Extracting Structured Data

    GAIK-project/gaik-toolkit

    Extracts structured data — fields, tables, line items — out of documents into a validated schema using the gaik toolkit, and designs schemas that stay inside provider limits and produce checkable…

    100 GitHub stars~3.2k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Skill Sync Checker

    PINA-org/PINA

    Audits SKILL.md files in this repo's skills directory for references to functions, classes, or modules (mentioned by name in prose, e.g.

    798 GitHub stars~1.5k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Openai Playwright

    trailofbits/skills-curated

    Official

    A skill your agent uses when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli…

    513 GitHub stars~945 tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes
  • Surf

    w-winter/dot314

    Control Chrome browser via CLI for testing, automation, and debugging.

    139 GitHub stars~7.6k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check: warnings
  • Vision

    aiskillstore/marketplace

    See and understand images when you (the current model) have no native vision.

    433 GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    AI & LLM EngineeringAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Safe Payment Guard

What does Safe Payment Guard do?

payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value. Safe Payment Guard is an agent skill from LeoYeAI/openclaw-master-skills. payment safety guardrail for tasks that involve paying, wiring, reimbursing, settling invoices, sending remittances, topping up balances, or moving money or stored value.

When should I use Safe Payment Guard?

Safe Payment Guard fits situations like: chatgpt is asked to prepare; execute a payment action.

How do I install Safe Payment Guard in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill safe-payment-guard -a claude-code`. Or copy the skill folder (skills/safe-payment-gaurd in LeoYeAI/openclaw-master-skills) into .claude/skills/safe-payment-guard in your project. Claude Code loads it when a task matches its description.

How do I install Safe Payment Guard in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill safe-payment-guard -a codex`. Or copy the skill folder (skills/safe-payment-gaurd in LeoYeAI/openclaw-master-skills) into .agents/skills/safe-payment-guard in your project. Codex loads it when a task matches its description.

Can I use Safe Payment Guard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill safe-payment-guard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/safe-payment-guard, .gemini/skills/safe-payment-guard, .github/skills/safe-payment-guard and .opencode/skills/safe-payment-guard in your project.

What does Safe Payment Guard need to run?

SKILL.md names no scripts, command-line tools or credentials: Safe Payment Guard is instructions for the agent only.

Does Safe Payment Guard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Safe Payment Guard safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Safe Payment Guard use?

Safe Payment Guard is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Safe Payment Guard use?

About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Safe Payment Guard?

Skills that share tags, products or a category with Safe Payment Guard: Extracting Structured Data (GAIK-project/gaik-toolkit, 100 stars), Skill Sync Checker (PINA-org/PINA, 798 stars), Openai Playwright (trailofbits/skills-curated, 513 stars) and Surf (w-winter/dot314, 139 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Safe Payment Guard?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.