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/stripe/link-cli/claude-mdgit clone --depth 1 https://github.com/stripe/link-cliWhat 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 | $0.03641 | $0.03641 |
| Opus 5 | $0.01820 | $0.01820 |
| Sonnet 5 | $0.00728 | $0.00728 |
| Haiku 4.5 | $0.00364 | $0.00364 |
Grade A, and why
link-cli 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 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working with code in this repository.
Project Overview
Link CLI — lets agents get secure, one-time-use payment credentials from a Link wallet. pnpm + Turborepo monorepo:
@stripe/link-sdk(packages/sdk): Typed Link API client and resource implementations. It acceptsaccessTokenorgetAccessToken; it does not own OAuth state. Entry:src/index.ts.@stripe/link-cli(packages/cli): Commander.js + Ink/React CLI that consumes@stripe/link-sdk. Entry:src/cli.tsx.
Commands
pnpm install # install dependencies
pnpm run build # build all packages (turbo)
pnpm run dev # watch mode
pnpm run test # run all tests
pnpm run typecheck # type-check all packages
pnpm biome check . # lint + format check (CI)
pnpm run check # lint + format with auto-fix
Run a single test:
cd packages/cli && pnpm vitest run src/utils/__tests__/line-item-parser.test.ts
The CLI integration tests in packages/cli/src/__tests__/cli.test.ts run against the compiled dist/cli.js. Run pnpm run build before running them if the source has changed.
Run the CLI locally:
node packages/cli/dist/cli.js <command>
Architecture
SDK Resources
Defined in packages/sdk/src/resources/interfaces.ts:
ISpendRequestResource— CRUD + request-approval for spend requests
The SDK only accepts credentials. Device authorization, refresh-token
persistence, login state, and auth-specific errors live under
packages/cli/src/auth/.
CLI Command Structure
Commands in packages/cli/src/cli.tsx (incur framework). Each has two output modes:
- Interactive (default): Ink/React components from
packages/cli/src/commands/ - JSON (
--format json): JSON to stdout, errors as JSON withcodeandmessagefields with exit code 1
Commands: auth login|logout|status, spend-request create|update|retrieve|request-approval|cancel, payment-methods list, shipping-address list, mpp pay|decode, serve.
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 · 152 lines · 3,641 tokens per session scan A 31366bd3759d
link-cli CLAUDE.md is an instructions file published in the GitHub repository stripe/link-cli (745 stars, last pushed 4d ago), licensed MIT. It adds 3,641 tokens to every session, about $0.0182 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.