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/bravodev-hub/appointme/claude-mdgit clone --depth 1 https://github.com/bravodev-hub/appointmeWrote 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/bravodev-hub/appointme/claude-md)<a href="https://agentmods.dev/instructions/bravodev-hub/appointme/claude-md"><img src="https://agentmods.dev/badge/instructions/bravodev-hub/appointme/claude-md.svg" alt="Measured on agentmods" 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 | $0.02201 | $0.02201 |
| Opus 5 | $0.01100 | $0.01100 |
| Sonnet 5 | $0.00440 | $0.00440 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
appointme 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 5d 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 — 167 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 (claude.ai/code) when working with code in this repository.
Build and Development Commands
Running the Full Stack (Recommended)
cd src/AppointMe.Aspire && dotnet run
This starts all services via .NET Aspire: SQL Server, Keycloak, Mailpit, API, and Frontend.
Backend Only
dotnet build AppointMe.sln # Build entire solution
dotnet run --project src/AppointMe.Api # Run API
Frontend Only
cd src/AppointMe.Frontend
npm install
npm run dev # Development server (port 5173)
npm run build # Production build
npm run lint # ESLint
npm run generate:api # Regenerate API client from OpenAPI spec (see /regenerate-api skill)
Regenerating the frontend API client after backend contract changes
After any change that alters the OpenAPI surface — new/renamed/removed endpoint, changed *Request.cs/*Response.cs shape, changed route or HTTP verb, changed auth/permission attributes on an endpoint — invoke the /regenerate-api skill in the same task. It waits for the API to be reachable on https://localhost:7233, runs npm run generate:api, and reports the diff on src/AppointMe.Frontend/src/api/. The backend must be restarted (Aspire dashboard → restart appointme-api, or relaunch dotnet run in src/AppointMe.Aspire) so orval reads the new contract — a reachable-but-stale backend silently produces a stale client.
Do not invoke /regenerate-api for backend-only changes that don't affect the contract (internal handlers, domain events, EF config, migrations, tests).
Testing
dotnet test # All tests
dotnet test src/CRM/AppointMe.Crm.Tests # Single test project
dotnet test --filter "FullyQualifiedName~TestName" # Single test
Architecture
This is a modular monolithic .NET 10 application following Domain-Driven Design principles.
Module Structure
src/
├── AppointMe.Api/ # ASP.NET Core API entry point
├── AppointMe.Aspire/ # .NET Aspire orchestrator for local dev
├── AppointMe.Shared/ # Shared domain abstractions and value objects
├── Identity/AppointMe.Identity/ # User auth module (Keycloak)
├── Organizations/AppointMe.Organizations/ # Companies & employees
├── CRM/AppointMe.Crm/ # Customer management
├── Booking/AppointMe.Booking.Contracts/ # Booking contracts (TBD)
└── AppointMe.Frontend/ # React/Vite/TypeScript frontend
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.
- 5d ago First seen · 167 lines · 2,201 tokens per session scan A 8c016e88b769
appointme CLAUDE.md is an instructions file published in the GitHub repository bravodev-hub/appointme (46 stars, last pushed 11d ago), licensed MIT. It adds 2,201 tokens to every session, about $0.0110 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
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.
MailFathom AGENTS.md
AGENTS.md instructions for Krzysztof318/MailFathom, covering mailfathom development instructions, project status, where the rest of the contract lives, critical repository rules and the two roles this contract is written for.
django-saas-boilerplate CLAUDE.md
Claude Code instructions for eriktaveras/django-saas-boilerplate, covering django saas boilerplate, tech stack, project structure, key conventions and user model.
landing-kit-building CLAUDE.md
Instructions for dkadts/landing-kit-building, covering landing kit — protocol for ai agents, 7 rules (default for all sessions), workflow for a new landing (mandatory order), anti-ai-slop checklist (auto-enforced by /audit) and sources of truth.
chassis AGENTS.md
Instructions for dvd90/chassis, covering agent guide, the 60-second mental model, do this, don't do this and where things live.
chassis copilot-instructions.md
Instructions for dvd90/chassis: This project follows the conventions in AGENTS.md — read it before making changes. Summary of the non-negotiables.