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/cplx/flighty-mcp-server/claude-mdgit clone --depth 1 https://github.com/CPLX/flighty-mcp-serverWrote 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/cplx/flighty-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/cplx/flighty-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cplx/flighty-mcp-server/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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
flighty-mcp-server 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 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.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flighty-mcp-server
MCP server for the Flighty flight tracking app. 15 tools (12 read, 3 write) covering flights, status, stats, connections, friends, airports, airlines, and add/follow/remove via Flighty API.
Version Numbering
Every commit that changes code must bump the version number. The version lives in three places that must stay in sync:
package.json—"version"manifest.json—"version"src/index.ts—const VERSION
Claude Desktop and Claude Code cache MCP tool definitions. Without a version bump, users will not see updated tool descriptions or new tools even after rebuilding.
After bumping, always rebuild the .mcpb: scripts/build-extension.sh
Build & Package
npm run build— compile TypeScriptscripts/build-extension.sh— build, then pack intodist/flighty-mcp-server.mcpb- The .mcpb uses the lockfile (
npm ci) for reproducible builds
Key Constraints
- macOS only — reads from Flighty's app sandbox
- No console.log() — stdout is the MCP JSON-RPC transport. Use
console.error()for logging. - All timestamps are UTC — converted from Unix timestamps via
tsToIso(). Tool responses include anotefield reminding AI callers of this. - Owner ID resolution is three-tier:
FLIGHTY_OWNER_USER_IDenv var → JWTsubfromFlighty.sqlite(only used if that userId actually has flights, to handle friend-share installs) → frequency fallback acrossUserFlight ∪ UserManualFlight. Never a bare heuristic when the JWT is available and valid. - Build token read from Info.plist at runtime — updates automatically when user updates Flighty.
- Write tools call Flighty's private API — protobuf encoding, no library dependency.
- Read-only mode —
FLIGHTY_READ_ONLY=1(ortrue/yes) skipsregisterWriteTools, dropping the tool count from 15 to 12..mcpbinstalls expose this as a Read-Only Mode checkbox viamanifest.jsonuser_config.read_onlymapped to the env var.
Git & GitHub
- PR-based workflow, never commit directly to main
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 · 44 lines · 610 tokens per session scan A 6e91075c36f6
flighty-mcp-server CLAUDE.md is an instructions file published in the GitHub repository CPLX/flighty-mcp-server (27 stars, last pushed 4d ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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
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).
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.
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.