Borrowing it
Nothing to install: this file belongs to RicardoSantos/mcp-fsolar. 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/RicardoSantos/mcp-fsolar/main/CLAUDE.mdgit clone --depth 1 https://github.com/RicardoSantos/mcp-fsolarWrote 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/ricardosantos/mcp-fsolar/claude-md)<a href="https://agentmods.dev/instructions/ricardosantos/mcp-fsolar/claude-md"><img src="https://agentmods.dev/badge/instructions/ricardosantos/mcp-fsolar/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/ricardosantos/mcp-fsolar/claude-md"><img src="https://agentmods.dev/badge/instructions/ricardosantos/mcp-fsolar/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 | $0.01992 | $0.01992 |
| Opus 5 | $0.00996 | $0.00996 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
mcp-fsolar 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 9d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — fsolar-mcp
Project overview
Felicity Solar battery MCP server + REST API. Exposes per-cell voltages, SOC, SOH, temperatures, BMS counters, balancing state, and computed health metrics to Claude and any MCP client.
Key documents
| File | What it covers |
|---|---|
README.md |
Setup, usage modes (MCP, REST API, embedded, JS library, webhooks), env vars |
CONTRIBUTING.md |
Branch naming, conventional commits, PR process |
SECURITY.md |
Security policy and responsible disclosure |
CHANGELOG.md |
Release history |
docs/ALGORITHMS.md |
Every derived metric formula (cell delta, SOC, SOH, trend), snapshot persistence, webhook system |
Running tests
npm test # build + run all unit and security tests via node --test on dist/
npm run test:security # build + run only the live security tests (server must be running)
Security tests need a pre-started server and matching credentials:
FELICITY_USER=x FELICITY_PASS=y FELICITY_API_KEY=secret FELICITY_MODE=http node dist/server.js &
FELICITY_API_KEY=secret npm run test:security
Project structure
server.ts Server factory (TypeScript source) — exports createServer() + startServer()
index.ts Public API barrel (TypeScript source) — re-exports all public symbols
bin/
fsolar-mcp.js CLI entry point — calls dist/server.js main() after build
dist/ Compiled output (tsc → CommonJS + .d.ts); this is what npm publishes
src/
constants.ts all shared magic numbers and thresholds (health, autonomy, webhooks, cycles)
errors.ts AppError class (Error subclass with statusCode)
logger.ts createLogger() — injectable structured JSON logger (writes to stderr)
middleware.ts makeGetAllowedOrigin, makeCheckAuth, makeRateLimit, readBody factories
hooks.ts Webhook store, SSRF validation, event delivery, per-event cooldowns, retry
compute.ts Health metric derivation (computeHealth, computeAutonomy)
analyze.ts computeAlerts, computeEnergyHistory, computeCellStats, computePowerStats
enums.ts HealthStatus, HookEvent, TrendDirection, ChargingState
client.ts FelicityClient — auth, pagination, caching
http.ts felicityRequest using fetch() + AbortSignal.timeout()
helpers.ts sleep(), pickSnapshotFields(), pickNextSunrise() and other shared utilities
state.ts startPoller, readState, snapshotEmitter
store.ts SnapshotStore, BatterySnapshotStore, DailySnapshotStore
battery.ts buildBattery — raw Felicity API → typed Battery
cache.ts MemoryCacheAdapter, CacheAdapter interface
test/
cache.test.ts MemoryCacheAdapter unit tests
client.test.ts FelicityClient unit tests
compute.test.ts computeHealth + computeAutonomy unit tests
errors.test.ts AppError unit tests
helpers.test.ts nullableInt, clamp, sleep, pickSnapshotFields, pickNextSunrise
hooks.test.ts HookStore SSRF, cooldowns, event filtering
logger.test.ts createLogger JSON output
middleware.test.ts CORS, auth, rate limit, body parsing
snapshot.test.ts BatterySnapshotStore trend computation
transform.test.ts buildBattery field mapping
analyze.test.ts computeAlerts, computeEnergyHistory, computeCellStats, computePowerStats unit tests
server.test.ts createServer HTTP route correctness and auth enforcement
state.test.ts startPoller, readState, snapshotEmitter unit tests
config.test.ts environment variable parsing and validation
security.test.ts Live HTTP security suite (auth, CORS, SSRF, rate limiting, webhooks)
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.
- 9d ago First seen · 174 lines · 1,992 tokens per session scan A 57beb267133a
mcp-fsolar CLAUDE.md is an instructions file published in the GitHub repository RicardoSantos/mcp-fsolar (0 stars, last pushed yesterday), licensed MIT. It adds 1,992 tokens to every session, about $0.0100 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).
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.
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.