Borrowing it
Nothing to install: this file belongs to hoodsy/solar-data-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/hoodsy/solar-data-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/hoodsy/solar-data-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/hoodsy/solar-data-mcp/claude-md)<a href="https://agentmods.dev/instructions/hoodsy/solar-data-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hoodsy/solar-data-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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
solar-data-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.
What it actually says
CLAUDE.md — solar-data-mcp
Open-source monorepo of MCP servers making US open solar data agent-accessible: four
domain servers (nrel-solar, solar-economics, solar-market, solar-forecast) behind the
solar-data-mcp umbrella. Feature-complete for v1; work one package at a time and
keep every gate green.
Commands
- Install:
uv sync - Test (fixtures only, no live calls):
uv run pytest - Record fixtures (needs keys in .env):
uv run pytest --record - Lint/type:
uv run ruff check . && uv run mypy --strict - Key check:
uv run solar-data-mcp doctor
Architecture rules
- uv workspace:
packages/core(shared) + one package per server (packages/nrel-solar, ...)packages/solar-data-mcp(umbrella: all four servers' tools on one stdio entry; the user-facing install — PyPI'ssolar-mcpname belongs to an unrelated project)
- Every tool returns the
ToolResultenvelope from core: data + units + source + assumptions + warnings - NEVER silently default a parameter — every injected default goes in
assumptions - All HTTP goes through core's client (retry, token-bucket rate limit, SQLite cache). NREL limit: 1,000 req/hr
- Validate inputs with pydantic BEFORE any HTTP call; errors must name the field and allowed range
- Tool names: verb_noun. Docstrings: purpose, when-to-use-vs-siblings, one worked example, units
Testing rules
- CI makes ZERO live API calls — replay fixtures from
fixtures/<source>/ - Pure logic (economics math, normalization) gets plain unit tests, no mocks
- Coverage floor: 85% across all packages (enforced in CI via --cov flags)
Style
- Python 3.11+, mypy --strict clean, ruff clean
- MIT license headers not required; keep files small and single-purpose
Out of scope (do not build unless asked)
- PVDAQ, TOU tariff simulation, REopt, any web UI (v2 candidates)
- Google Solar adapter (optional package, later; never a core dependency)
Definition of done — every change
- Gates for any new work:
uv run pytestgreen (replay only), ruff + mypy --strict clean, coverage ≥85% (CI), fixtures scrubbed of keys, every injected default inassumptions - Release: push a
v*tag →.github/workflows/release.ymlpublishes all six packages to PyPI via Trusted Publishing (OIDC, deps before the umbrella). Full runbook, including one-time PyPI/GitHub setup and post-release manual steps: docs/RELEASING.md - Security: vuln disclosure via SECURITY.md; sync_* downloads are restricted to each dataset's official host; secrets are scrubbed from the cache/logs/envelopes
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 · 45 lines · 651 tokens per session scan A 9cd77071d2ec
solar-data-mcp CLAUDE.md is an instructions file published in the GitHub repository hoodsy/solar-data-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 651 tokens to every session, about $0.0033 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
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).
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).
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.
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.