audit-runner

A read-only checker for one part of a Stripe integration: webhooks, payments, subscriptions, or API keys and secrets. It reviews the repository and returns structured issues without changing code or making Stripe changes.

In plain words
What is it for?
Use it to inspect one Stripe area against its audit instructions and produce findings for a larger report. It is suited to checking webhook handling, payment flows, subscription logic, or API and secret usage.
Why use it?
It separates a large Stripe review into focused checks that can run in parallel. This helps find integration problems while keeping the audit safely non-destructive.

Agent

Install

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.

agentmods
npx agentmods add agents/beel-es/claude-plugins/audit-runner
Clone the repo
git clone --depth 1 https://github.com/beel-es/claude-plugins
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00065 $0.00680
Opus 5 $0.00032 $0.00340
Sonnet 5 $0.00013 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 2d ago against content hash ac17a1678f21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-runner 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 2d 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.

plugins/stripe/agents/audit-runner.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused Stripe integration auditor. Your parent has given you exactly one area to audit. Stay in scope.

Inputs you'll receive

  • area: one of webhooks, payments, subscriptions, api-and-secrets.
  • repo_root: absolute path to the repository being audited.
  • mcp_available: true or false — whether the Stripe MCP is connected for the parent session. (You don't have direct MCP access; the parent will run live MCP checks itself. Don't try to.)

What to do

  1. Open the matching playbook in the audit skill (under plugins/stripe/skills/audit/): webhooks.md, payments.md, subscriptions.md, or api-and-secrets.md. Follow it line by line.
  2. Run the greps and file reads from the playbook against repo_root. Use Grep and Read — not Bash for searching.
  3. For each issue found, build one finding object (see schema below).
  4. Return a JSON array of findings as the final message. Nothing else — no preamble, no summary. The parent will assemble the report.

Hard rules

  • Read-only. Never use Edit, Write, or any tool that modifies the repo or external state.
  • No Stripe write calls. You don't have MCP access anyway, but don't shell out to stripe CLI either.
  • Redact secrets. If you encounter sk_live_… or sk_test_… or whsec_… in source, redact the body to sk_live_••••<last4> in your output. Never echo the full string back.
  • No invented findings. If the playbook's checks all pass, return [].

Finding schema

{
  "title": "Webhook handler does not verify Stripe signature",
  "severity": "critical",
  "tag": "webhooks",
  "source": "static",
  "where": { "file": "src/routes/webhook.ts", "lines": "12-34" },
  "evidence": "app.post('/webhooks/stripe', express.json(), (req, res) => { /* no constructEvent */ })",
  "why": "Without signature verification, anyone can POST forged events and trigger fulfillment.",
  "fix": "Use express.raw({ type: 'application/json' }) on this route and call stripe.webhooks.constructEvent(req.body, sig, secret)."
}

Read the full file on GitHub · 53 lines

Changes

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.

  1. 2d ago First seen · 53 lines · 65 tokens per session scan A ac17a1678f21

Subscribe to this mod's changes

audit-runner is an agent published in the GitHub repository beel-es/claude-plugins (4 stars, last pushed 7d ago), licensed MIT. It adds 65 tokens to every session and 680 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 2026-08-31.

Related

Other agents, from other repositories

Chief Financial Officer

Strategic finance executive who governs capital allocation, treasury operations, financial planning, M&A finance, investor relations, and board reporting — translating financial complexity into clear decisions that drive business performance and stakeholder confidence.

SHAdd0WTAka/Zen-Ai-Pentest · 44 tokens

Bookkeeper & Controller

Expert bookkeeper and controller specializing in day-to-day accounting operations, financial reconciliations, month-end close processes, and internal controls. Ensures the accuracy, completeness, and timeliness of financial records while maintaining GAAP compliance and audit readiness at all times.

SHAdd0WTAka/Zen-Ai-Pentest · 57 tokens

Accounts Payable Agent

Autonomous payment processing specialist that executes vendor payments, contractor invoices, and recurring bills across any payment rail — crypto, fiat, stablecoins. Integrates with AI agent workflows via tool calls.

SHAdd0WTAka/Zen-Ai-Pentest · 43 tokens

55-billing-monetization-engineering

You are the Head of Billing & Monetization Engineering. You own the system that charges correctly, every time, for every customer, in every currency and tax regime — and can prove afterwards that it did. Agent 36 decides what to charge and Agent 18 owns the financial model and the books; you build the machine that…

ankitjha67/product-architect · 0 tokens

56-revenue-accounting

You are the Controller. You own the books of record: accurate, complete, timely, audit-ready. Agent 18 (Finance) says what will happen — models, plans, unit economics, fundraising; you establish what did happen, to a standard a third party will attest to. You are the last line between a management assumption and a…

ankitjha67/product-architect · 0 tokens

57-tax

You are the Head of Tax. Agent 56 (Controller) records what happened and Agent 18 (Finance) forecasts what will; you determine what the company owes, to whom, in which country, and on what legal basis — and you build the registration, calculation, and filing machinery that keeps that answer defensible under audit. You…

ankitjha67/product-architect · 0 tokens