Borrowing it
Nothing to install: this file belongs to pedrobtz/tslab-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/pedrobtz/tslab-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/pedrobtz/tslab-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/pedrobtz/tslab-mcp/claude-md)<a href="https://agentmods.dev/instructions/pedrobtz/tslab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pedrobtz/tslab-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 | $0.02684 | $0.02684 |
| Opus 5 | $0.01342 | $0.01342 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
tslab-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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
uv sync --all-groups # set up (installs ~291 packages, ~2.3 GB)
uv run pytest # fast suite (~1.5s); excludes `slow` via addopts
uv run pytest -m slow # exercises TimeCopilot (~3.5 min, no weight downloads)
uv run pytest -m '' # everything
uv run pytest tests/test_features.py::test_acf1_within_bounds # single test
uv run ruff check src tests
uv run mypy # strict on src/; first cold run takes ~10 min
uv build
Verify the wire protocol, not just the functions — a tool can pass its unit test and still fail a client handshake:
npx @modelcontextprotocol/inspector uv run tslab-mcp
What this is
An MCP server exposing deterministic time-series forecasting. The session driving the tools is the reasoning engine; this package computes numbers and never calls an LLM.
Two backends, chosen automatically in backends.select():
- statsforecast (core, always installed) runs the eleven statistical models. ~340 MB, no torch.
- TimeCopilot (optional
foundationextra) runs the pretrained models and Prophet. ~2 GB, and only reached when a request names one of its models.
A request whose models are all statistical never touches TimeCopilot. A mixed request goes entirely to TimeCopilot, which carries the statistical models too — letting it merge the frames avoids reimplementing an upstream join.
Architecture
Four invariants drive nearly every design decision. Breaking one looks locally harmless and is not.
Handles, not dataframes. Panels live in registry.py's module-level
_STORE, keyed by a short handle. Tools take the handle and return summaries,
aggregates, and file paths. A CV frame is n_series × h × n_windows × n_models
rows — serialising one into a tool result exhausts the session's context on the
first call. Every bulk return path is capped by a schema-enforced maximum and
reports truncated plus the omitted count.
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 · 197 lines · 2,684 tokens per session scan A 6e9197f43659
tslab-mcp CLAUDE.md is an instructions file published in the GitHub repository pedrobtz/tslab-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 2,684 tokens to every session, about $0.0134 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.