Borrowing it
Nothing to install: this file belongs to darshjoshi/skyglance-mcp. 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/darshjoshi/skyglance-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/darshjoshi/skyglance-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/darshjoshi/skyglance-mcp/claude-md)<a href="https://agentmods.dev/instructions/darshjoshi/skyglance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/darshjoshi/skyglance-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 5.1 | $0.01700 | $0.01700 |
| Opus 5 | $0.00850 | $0.00850 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
skyglance-mcp 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — SkyGlance MCP
What This Is
An MCP server that answers questions about aircraft: what's overhead right now and where to look, what a given plane is, where a flight is, and what has passed over before. 24 tools, free data, no API keys.
Sibling project: skyglance-mac — same data,
macOS menu bar app. Its docs/ are the research this is built on and are worth
reading before changing anything here: FREE-STACK.md, OVERHEAD-DETECTION.md,
COVERAGE-AND-COST.md.
Architecture
src/skyglance/server.py— MCP tool definitions. Thin: validate, delegate, format.src/skyglance/feeds.py— three ADS-B feeds queried in parallel and merged. Circuit breakers, rate-slot reservation, coordinate coarsening, last-good snapshot.src/skyglance/geometry.py— elevation, bearing, slant range, closest point of approach.src/skyglance/enrich.py— adsbdb → hexdb → planespotters, cached forever.src/skyglance/interest.py— scoring: which aircraft is worth mentioning.src/skyglance/weather.py— Open-Meteo, the "can you actually see it" gate.src/skyglance/store.py— SQLite history: aircraft, passes, enrichment cache.src/skyglance/poller.py— background poller + single-instance lock.src/skyglance/traces.py— ~24h flight paths fromglobe.adsb.lol/data/traces. Reduction is the whole job here: a raw trace is ~2,600 points / 450 KB, which is unusable in a context window. It gets segmented into legs and downsampled toPATH_SAMPLESpoints each. Don't raise that without checking the output size.src/skyglance/airports.py— ICAO lookup plus observed departing/arriving/on-ground classification by climb rate. Airport records are cached forever; airports don't move.src/skyglance/airport_data.py— ~1,150 major airports embedded from OurAirports (public domain). Generated bytools/build_airports.py; don't hand-edit.src/skyglance/world.py— the global sweep. adsb.lol's point query has no radius cap, so a 12,000 nm radius returns ~6,000 aircraft worldwide in ~1.3s. That single response is ~3.7 MB from volunteers, so it is fetched at most once per 60 seconds, process-wide, shared between concurrent callers, and served from cache in between. Never call it to answer something a 60 nm circle can answer.
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.
- 7d ago First seen · 124 lines · 1,700 tokens per session scan A 3f4bff6980ab
skyglance-mcp CLAUDE.md is an instructions file published in the GitHub repository darshjoshi/skyglance-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,700 tokens to every session, about $0.0085 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 2026-08-31.
Other instructions, from other repositories
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.