Borrowing it
Nothing to install: this file belongs to dannybauman/groundstation. 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/dannybauman/groundstation/main/CLAUDE.mdgit clone --depth 1 https://github.com/dannybauman/groundstationWrote 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/dannybauman/groundstation/claude-md)<a href="https://agentmods.dev/instructions/dannybauman/groundstation/claude-md"><img src="https://agentmods.dev/badge/instructions/dannybauman/groundstation/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/dannybauman/groundstation/claude-md"><img src="https://agentmods.dev/badge/instructions/dannybauman/groundstation/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 | $0.00575 | $0.00575 |
| Opus 5.5 | $0.00230 | $0.00230 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
groundstation 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 16d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
groundstation — session rules
A Development Seed labs prototype. Full architecture in docs/architecture.md, test conventions in evals/README.md, the artifact attribution model in docs/stack.md.
Scope: minimalist, mostly MCP
Groundstation is the MCP tools and the behind-the-scenes functionality agents call. Field tests are its one visual surface. Galleries, viewers, living worlds and other visual products belong in their own repos, which can depend on groundstation. A visual addition earns its place here only when it clearly improves a tool's existing output or the field tests, and it stays small.
DevSeed tools first
Before building a capability or reaching for a generic dependency, ask: does a DevSeed tool already do this? Prefer it, even when a generic option looks marginally easier — this project exists to show the DS/open-source stack working, so using our own tools IS the product. The family to check first: TiTiler, rio-tiler, titiler-pgstac, cogeo-mosaic/MosaicJSON, rio-cogeo, eoAPI, stac-fastapi, pgstac, Gazet, stactools, lonboard/deck.gl-raster (viz). When unsure, search the developmentseed and cogeotiff GitHub orgs before adding anything.
And attribute it. Any tool that ends up in an artifact's render path gets an entry in docs/stack.md (the curated attribution source) in the same PR, with a when rule saying which render facts put it on screen, a pipeline stage, and its island when it has one — the stack layer can only credit what the file lists, and it reads no code to do it. Attribution is to projects, never people.
Working agreements
- one branch + one small PR per change, evals in
evals/unit_checks.pybefore the PR, eval output pasted in the PR body - a tool that returns a derived number returns, in the same object, the conditions under which it should not be read at face value — the rule and the audit are in
docs/adr-caveats.md - bump the version in every PR that ships behavior — installs cache per version. It lives in 3 files that must agree:
.claude-plugin/plugin.json,.claude-plugin/marketplace.jsonandpyproject.toml(thenuv lock);evals/unit_checks.pyfails when they drift - multi
-mcommits, Claude co-author trailer - deliberate shortcuts get a
ponytail:comment naming the ceiling and the upgrade path - the shared titiler.xyz is a courtesy: be frugal in tests and demos, batch live checks, stop on 429
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.
- 16d ago Changed · +4 lines · +81 tokens per session a1a386f66f6e
- 23d ago Changed · +47 tokens per session b8380053f2eb
- 2mo ago Changed · +1 lines · +84 tokens per session faba6769e6a6
- 2mo ago First seen · 18 lines · 363 tokens per session scan A 2a5195326ee1
groundstation CLAUDE.md is an instructions file published in the GitHub repository dannybauman/groundstation (0 stars, last pushed yesterday), licensed MIT. It adds 575 tokens to every session, about $0.0023 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.
groundstation CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| groundstation CLAUDE.mddannybauman/groundstation | Instructions file | 0 | yesterday | MIT | A | 575 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |