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.
npx agentmods add instructions/rafaelcg/stripekit/agents-mdgit clone --depth 1 https://github.com/rafaelcg/stripekitWhat 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 | $0.01047 | $0.01047 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
stripekit 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 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working on the stripekit codebase. (To learn how to use stripekit in a project, read SKILL.md or llms.txt instead.)
What this is
stripekit is the "create-next-app of Stripe": a CLI that reconciles a declarative stripe.config.ts into the user's own Stripe account and scaffolds correct billing code. It is a tool, not a platform — no hosted service, no runtime dependency in generated code. See README.md and DESIGN.md for the full picture.
Layout
packages/stripekit/src/— the CLI + library.config/—defineConfig, zod schema, TS config loader.reconciler/— the core:desired.ts(config → desired state),diff.ts(pure diff → plan),apply.ts,read-state.ts,pull.ts,plan.ts.cli/commands/—init,plan,push,pull,dev,check.init/— framework/auth detection + scaffolding.
packages/stripekit/templates/init/— the billing code emitted byinit(real TS files, not compiled by the tool).packages/stripekit/test/— vitest;fake-stripe.tsis an in-memory Stripe used to test the whole reconcile loop offline.docs/— VitePress site.examples/playground/— a scratch project.
Setup & commands
Node 20+ and pnpm. From the repo root:
pnpm install
pnpm -C packages/stripekit build # bundle CLI + types (tsup)
pnpm -C packages/stripekit test # vitest
pnpm -C packages/stripekit typecheck # tsc --noEmit
pnpm format # prettier
pnpm docs:build # build the docs site
Always run test, typecheck, and format before committing.
Releasing
stripekit is published to npm. Keep one version number across packages/stripekit/package.json, src/constants.ts (VERSION), docs/public/.well-known/mcp/server-card.json, server.json, .claude-plugin/plugin.json, and .claude-plugin/marketplace.json.
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.
- 2d ago First seen · 70 lines · 1,047 tokens per session scan A e3e98f8e7896
stripekit AGENTS.md is an instructions file published in the GitHub repository rafaelcg/stripekit (2 stars, last pushed 25d ago), licensed MIT. It adds 1,047 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
yournextstore CLAUDE.md
Claude Code instructions for yournextstore/yournextstore, a project described as: AI-Native Open-Source Next.js commerce. Powered by Stripe. Ultra fast with typesafe Commerce SDK. Built for AI development (Claude, Codex, Cursor).
yournextstore AGENTS.md
AGENTS.md instructions for yournextstore/yournextstore, covering agents.md, commands, key files & directories, platform-managed files — do not modify and project patterns.
velobase-harness AGENTS.md
Instructions for velobase/velobase-harness, covering ai agent guide, task router, integration router, core rules and general.
velobase-harness copilot-instructions.md
Instructions for velobase/velobase-harness: Read AGENTS.md first. It is the English canonical AI agent guide for this repository.
e-commerce-agents CLAUDE.md
Instructions for nitin27may/e-commerce-agents, covering claude.md, what this is, working artifacts location, key commands and start everything from scratch (one command).
storefront AGENTS.md
AGENTS.md instructions for saleor/storefront, covering saleor paper — agent guide (always-on), how to get context (read in this order; stop when answered), precedence, critical commands and non-negotiable rules.