Borrowing it
Nothing to install: this file belongs to huangzesen/xhelio-spice. 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/huangzesen/xhelio-spice/main/CLAUDE.mdgit clone --depth 1 https://github.com/huangzesen/xhelio-spiceWrote 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/huangzesen/xhelio-spice/claude-md)<a href="https://agentmods.dev/instructions/huangzesen/xhelio-spice/claude-md"><img src="https://agentmods.dev/badge/instructions/huangzesen/xhelio-spice/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/huangzesen/xhelio-spice/claude-md"><img src="https://agentmods.dev/badge/instructions/huangzesen/xhelio-spice/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 | $0.02561 | $0.02561 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
xhelio-spice 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 11d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — xhelio-spice
What This Is
xhelio-spice is a standalone Python package that wraps SpiceyPy with automatic SPICE kernel management. Users call get_position("PSP", ...) and xhelio-spice handles kernel download, caching, loading, and computation. It was extracted from helio-ai-agent's spice/ module in Feb 2026.
Repository Structure
src/xhelio_spice/
__init__.py # Public API re-exports, version
missions.py # NAIF IDs, kernel URLs, name resolution, SEGMENTED_MISSIONS
kernel_manager.py # Download, cache, load/unload kernels (singleton)
ephemeris.py # get_position, get_trajectory, get_state
frames.py # transform_vector, coordinate frame listings
server.py # MCP server (FastMCP, 6 tools)
__main__.py # python -m xhelio_spice entrypoint
manifests/ # Bundled JSON manifests for segmented missions
__init__.py
cassini.json # 505 SPK segments (2001–2017)
mro.json # 185 SPK segments (2006–2026)
mars2020.json # 52 SPK segments (2019–2036)
lro.json # LRO SPK segments
lunar_prospector.json # Lunar Prospector SPK segments
mgs.json # Mars Global Surveyor SPK segments
mars_odyssey.json # 98 SPK segments (2001–2026)
stardust.json # 14 SPK segments (1999–2011)
akatsuki.json # 10 SPK segments (2011–2021)
grail.json # 9 SPK segments (2011–2012)
magellan.json # 8 SPK segments (1990–1994)
exomars_tgo.json # 322 SPK segments (2018–2026)
chandrayaan1.json # 300 SPK segments (2008–2009)
scripts/
build_manifest.py # Developer script to regenerate manifests from NAIF
tests/ # 220 tests, all mocked (no network/SPICE needed)
pyproject.toml # hatchling build, xhelio-spice-mcp CLI entrypoint
server.json # MCP registry manifest
Key Design Decisions
- Kernel cache:
XHELIO_SPICE_KERNEL_DIRenv var >~/.xhelio_spice/kernels/default. helio-ai-agent overrides to~/.helio-agent/spice_kernels/viaagent/mcp_client.py. - Two kernel strategies:
- Single-file missions (PSP, SOLO, Juno, etc.): one SPK file per mission, downloaded in full via
ensure_mission_kernels(). - Segmented missions (Cassini, MRO, Mars 2020, LRO, Lunar Prospector, MGS, Mars Odyssey, Stardust, Akatsuki, GRAIL, Magellan, ExoMars TGO, Chandrayaan-1): many SPK files with time coverage recorded in bundled JSON manifests. Only segments overlapping the requested time window are downloaded, via
ensure_segmented_kernels().
- Single-file missions (PSP, SOLO, Juno, etc.): one SPK file per mission, downloaded in full via
- ACE, Wind, DSCOVR are not supported — no public SPK kernels. Would need JPL Horizons API or CDF orbit files.
- Cache management:
get_cache_info()groups cached files by mission.delete_mission_cache(),delete_cached_files(), andpurge_cache()allow selective or full cleanup. Every MCP tool response includescache_size_mbso the LLM can monitor disk usage. - MCP server uses
_create_server()factory pattern for lazymcpimport and testability. - Thread safety: KernelManager is a singleton with RLock — SPICE has a global kernel pool.
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.
- 11d ago First seen · 148 lines · 2,561 tokens per session scan A 753ef23f8293
xhelio-spice CLAUDE.md is an instructions file published in the GitHub repository huangzesen/xhelio-spice (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,561 tokens to every session, about $0.0128 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
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.
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.
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).
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).