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/stellarpunk/mcp-server-ascom/claude-mdgit clone --depth 1 https://github.com/stellarpunk/mcp-server-ascomWrote 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/stellarpunk/mcp-server-ascom/claude-md)<a href="https://agentmods.dev/instructions/stellarpunk/mcp-server-ascom/claude-md"><img src="https://agentmods.dev/badge/instructions/stellarpunk/mcp-server-ascom/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 | $0.02226 | $0.02226 |
| Opus 5 | $0.01113 | $0.01113 |
| Sonnet 5 | $0.00445 | $0.00445 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
mcp-server-ascom 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - ASCOM MCP Server (v0.4.0)
Bridge ASCOM devices to Claude via MCP. Now with instant connections!
Quick Start
# Activate venv
source .venv/bin/activate
# Run server
python -m ascom_mcp
# Run tests
pytest tests/unit/ -v # Unit tests (40+ passing ✅)
pytest tests/integration/ -v # Integration tests (NEW!)
pytest tests/mcp/ -v # MCP protocol tests
Architecture
Our server is a "USB cable" between MCP and ASCOM:
Claude → MCP Protocol → Our Server → HTTP/Alpaca → seestar_alp → Telescope
(FastMCP 2.0) (Translation) (ASCOM) (Community) (Hardware)
↑ ↓
└── Event Stream ←── Real-time events from devices (v0.4.0)
FastMCP 2.0 Patterns
1. Context Parameter (Required)
@mcp.tool()
async def telescope_goto(ctx: Context, device_id: str, ra: float, dec: float):
await ctx.info(f"Slewing to RA={ra}, Dec={dec}") # Direct logging
# NOT ctx.logger.info() - that's wrong!
2. ToolError for User-Friendly Errors
raise ToolError(
"Device not found. Run discovery first.",
code="device_not_found",
recoverable=True,
details={"suggestions": ["Try: discover_ascom_devices"]}
)
3. Structured Logging
await ctx.debug("tool_called: telescope_goto")
await ctx.info(f"connected: device_id={device_id}")
await ctx.error(f"failed: {str(e)}")
Key Commands (v0.4.0 IoT Patterns)
Direct Connection (No Discovery Required!)
# Connect instantly with connection string
telescope_connect(device_id="[email protected]:5555")
# Or use pre-configured device
telescope_connect(device_id="telescope_1")
# Discovery only when adding new devices
discover_ascom_devices(timeout=5.0) # Optional!
# Initialize telescope (CRITICAL for Seestar!)
telescope_custom_action(
device_id="Telescope_0",
action="action_start_up_sequence",
parameters={"lat": 40.745, "lon": -74.0256, "move_arm": True}
)
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 · 317 lines · 2,226 tokens per session scan A 8174d4e8d247
mcp-server-ascom CLAUDE.md is an instructions file published in the GitHub repository stellarpunk/mcp-server-ascom (0 stars, last pushed 1y ago), licensed MIT. It adds 2,226 tokens to every session, about $0.0111 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
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.