Borrowing it
Nothing to install: this file belongs to benswel/qr-for-agent-api. 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/benswel/qr-for-agent-api/main/CLAUDE.mdgit clone --depth 1 https://github.com/benswel/qr-for-agent-apiWrote 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/benswel/qr-for-agent-api/claude-md)<a href="https://agentmods.dev/instructions/benswel/qr-for-agent-api/claude-md"><img src="https://agentmods.dev/badge/instructions/benswel/qr-for-agent-api/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/benswel/qr-for-agent-api/claude-md"><img src="https://agentmods.dev/badge/instructions/benswel/qr-for-agent-api/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 | $0.03110 | $0.03110 |
| Opus 5.5 | $0.01244 | $0.01244 |
| Sonnet 5.5 | $0.00622 | $0.00622 |
| Haiku 4.5 | $0.00311 | $0.00311 |
Grade A, and why
qr-for-agent-api 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 2mo 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QR for Agent — Context for Claude
On arrival
Before starting any work, read the project status memory file to get up to speed on what's been done and what's pending:
~/.claude/projects/-Users-benjaminturc-Library-CloudStorage-GoogleDrive-benjamin-swel-fr-Mon-Drive-Claude-Code/memory/qr-for-agent-status.md
After pushing new features, update that same memory file: move completed items, add new TODOs, bump versions if applicable.
What is this project?
QR for Agent is a QR-as-a-Service API built for AI agents. It lets agents create, update, and track dynamic QR codes programmatically. The QR image never changes — but its destination URL can be retargeted at any time.
Live API: deployed on Railway (Docker-based)
MCP package: qr-for-agent on npm (packages/mcp/)
Marketing site: separate repo benswel/qr-for-agent-site, deployed on Cloudflare Pages at qrforagent.com
Architecture
src/
├── server.ts # Entry point — starts Fastify on configured port
├── app.ts # App builder: CORS, Swagger, auth plugin, route registration
├── config/index.ts # Env vars: PORT, HOST, BASE_URL, DATABASE_URL, SHORT_ID_LENGTH, ADMIN_SECRET
├── db/
│ ├── schema.ts # Drizzle schema: api_keys, qr_codes, scan_events, webhooks, webhook_deliveries, conversion_events
│ ├── index.ts # better-sqlite3 + drizzle-orm init (WAL mode)
│ └── migrate.ts # Auto-migration on startup
├── shared/
│ ├── types.ts # QrFormat, QrType (11 types), all *Data interfaces, PaginatedResponse, Plan, PLAN_LIMITS, Fastify augmentation
│ └── errors.ts # Structured errors with code + hint (agent-friendly)
├── modules/
│ ├── auth/ # X-API-Key auth plugin + key management
│ ├── qr/ # CRUD routes, service, schemas, custom SVG renderer
│ ├── domain/ # Custom domain management (GET/PUT/DELETE /api/domain + DNS checker)
│ ├── conversions/ # Conversion tracking (pixel + API + webhook dispatch)
│ ├── redirect/ # GET /r/:shortId — public redirect + scan recording + webhook dispatch
│ ├── analytics/ # GET /api/analytics/:shortId — scan stats
│ ├── webhooks/ # Webhook CRUD + HMAC delivery + delivery logging
│ ├── stripe/ # Stripe Checkout, Customer Portal, webhook handler
│ ├── image/ # GET /i/:shortId — public QR image (cacheable)
│ └── well-known/ # /.well-known/ai-plugin.json + mcp.json
├── cli/ # key:create, key:list scripts
packages/
└── mcp/ # Standalone MCP server (published as qr-for-agent on npm)
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.
- 2mo ago First seen · 171 lines · 3,110 tokens per session scan A 76f3c731d0b8
qr-for-agent-api CLAUDE.md is an instructions file published in the GitHub repository benswel/qr-for-agent-api (3 stars, last pushed 5mo ago), licensed MIT. It adds 3,110 tokens to every session, about $0.0124 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 2026-08-31.
qr-for-agent-api CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qr-for-agent-api CLAUDE.mdbenswel/qr-for-agent-api | Instructions file | 3 | 5mo ago | MIT | A | 3,110 | 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 |