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/mindsetconsulting/sflight-mcp/claude-mdgit clone --depth 1 https://github.com/MindsetConsulting/sflight-mcpWrote 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/mindsetconsulting/sflight-mcp/claude-md)<a href="https://agentmods.dev/instructions/mindsetconsulting/sflight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mindsetconsulting/sflight-mcp/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 | $0.04525 | $0.04525 |
| Opus 5 | $0.02263 | $0.02263 |
| Sonnet 5 | $0.00905 | $0.00905 |
| Haiku 4.5 | $0.00453 | $0.00453 |
Grade A, and why
sflight-mcp CLAUDE.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:4004/odata/v4/flights/Carriers How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — sflight-mcp
Instructions for Claude Code when working in this repository. Human-readable too — this doubles as a developer quick-reference.
Repository
https://github.com/MindsetConsulting/sflight-mcp.git
What This Project Is
SAP SFLIGHT data model (airlines, flights, bookings, passengers) as a modern SAP CAP CDS application with a built-in MCP server (19 tools). It demonstrates three ways to interact with SAP data through AI:
| Demo Path | Transport | Audience | Works Locally? |
|---|---|---|---|
| 1. Claude Code (CLI) | stdio (MCP) | Developers, power users | Yes |
| 2. OData Service Endpoint | HTTP REST | API consumers, apps | Yes |
| 3. Claude for Excel | HTTP/SSE (MCP) | Business users | Only when deployed (or via supergateway locally) |
Platform Support
| Component | macOS | Linux | Windows (native) | Windows (WSL2) |
|---|---|---|---|---|
CAP server (cds watch) |
Yes | Yes | Yes | Yes |
| OData endpoints (Demo 2) | Yes | Yes | Yes | Yes |
MCP server build (tsc) |
Yes | Yes | Yes | Yes |
| Claude Code CLI | Yes | Yes | No | Yes |
| Setup script (bash) | Yes | Yes | No (use .ps1) |
Yes |
| Claude for Excel (Demo 3) | Yes | N/A | Yes | N/A |
Windows note: Claude Code requires WSL2. The OData service and MCP server build work natively. A PowerShell setup script is provided at
scripts/setup.ps1.
Quick Start — The 1-2-3
Prerequisite: Node.js 18+ and
@sap/cds-dkinstalled globally. If not:nvm install 22 && npm install -g @sap/cds-dk
macOS / Linux / WSL2
# Step 1: Clone and install
git clone https://github.com/MindsetConsulting/sflight-mcp.git
cd sflight-mcp
npm install
# Step 2: Build the MCP server
cd mcp-server && npm install && npm run build && cd ..
# Step 3: Start the CAP server
cds watch
# Open http://localhost:4004 — 26 entities, 4 views, 24 CSV files loaded
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.
- 4d ago First seen · 466 lines · 4,525 tokens per session scan A d09829ab130c
sflight-mcp CLAUDE.md is an instructions file published in the GitHub repository MindsetConsulting/sflight-mcp (1 stars, last pushed 6mo ago), licensed Unlicense. It adds 4,525 tokens to every session, about $0.0226 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
btp-cf-mcp AGENTS.md
Instructions for marianfoo/btp-cf-mcp, covering agents.md, project overview, design principles, build & test and live mcp smoke: mcpurl=… mcpkey=… node test/smoke.mjs.
btp-cf-mcp CLAUDE.md
Instructions for marianfoo/btp-cf-mcp: All project guidance for AI agents lives in AGENTS.md — one source of truth shared by every tool (Claude Code, Codex, Cursor, Copilot). Claude Code inlines it via the import below; if your tool does not resolve imports, read AGENTS.md before doing anything else. Do not add…
p21-api-documentation CLAUDE.md
Claude Code instructions for mrwuss/p21-api-documentation, covering project: p21 api documentation, quick context, how to navigate (read this before opening docs), apis covered and project structure.
erpl-adt CLAUDE.md
Claude Code instructions for DataZooDE/erpl-adt, covering claude.md, git commits and pull requests, project overview, build commands and architecture.
sap-superpowers CLAUDE.md
Claude Code instructions for vigneshbarani24/sap-superpowers, covering sap superpowers v3.1, skills (53+), meta skills (5), consulting skills (9) and development skills (8).
sap-mcp-servers CLAUDE.md
Instructions for marianfoo/sap-mcp-servers: This repo's contributor/agent guide lives in AGENTS.md — read that. It applies to all agents (Claude Code, Codex, Cursor, …), not just Codex, and covers the workspace layout, the build order (auth first), the env contract, secrets policy, and the release/publish flow.