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/thomaspinder/impulso/claude-mdgit clone --depth 1 https://github.com/thomaspinder/ImpulsoWrote 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/thomaspinder/impulso/claude-md)<a href="https://agentmods.dev/instructions/thomaspinder/impulso/claude-md"><img src="https://agentmods.dev/badge/instructions/thomaspinder/impulso/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 | $0.02353 | $0.02353 |
| Opus 5 | $0.01177 | $0.01177 |
| Sonnet 5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
Impulso 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 5d 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 — 169 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.
Project Overview
Impulso is a Python library for Bayesian Vector Autoregression (VAR). Early stage, requires Python >=3.11.
Commands
# Install dependencies and prek hooks
make install
# Run all code quality checks (lock file, pre-commit, type checking)
make check
# Run tests with coverage
make test
# Run a single test
uv run python -m pytest tests/test_foo.py::test_foo -v
# Run only fast tests (skip MCMC sampling)
uv run python -m pytest -m "not slow" -v
# Type check only
uv run ty check
# Lint/format only
uv run ruff check . && uv run ruff format .
# Build docs (Sphinx + MyST-NB executes notebooks, caches results)
make docs
# Serve the built docs locally on :8000
make docs-serve
# Build docs in smoke mode, warnings-as-errors (the CI gate)
make docs-ci # (docs-test is an alias)
# Check external links resolve (no notebook execution)
make docs-linkcheck
# Multi-version test (Python 3.11-3.14)
uv run tox
Architecture
- Source:
src/impulso/— library code, built as a wheel via Hatchling - Tests:
tests/— pytest with--cov, 90% coverage target (codecov.yaml) - Docs:
docs/— Sphinx + MyST-NB (docs/conf.py), tutorials as executable jupytextpy:percent.pynotebooks (read vianb_custom_formats), prose/reference pages as MyST.md. Docstrings auto-rendered via Sphinxautosummary(summary tables + per-object pages generated underdocs/reference/generated/, gitignored; custom stub templates indocs/_templates/autosummary/emit MyST) +napoleon.sphinx-codeautolinklinks API names in tutorial code to the reference;sphinxcontrib-bibtexpowers{cite}(bib indocs/references.bib);sphinx-sitemapemitssitemap.xml;numfig+ labelled$$…$$ (label)equations cross-referenced with{eq}`label`. Notebooks execute at build via jupyter-cache; no outputs are committed. Theme:shibuya. Tutorial.pyfiles are excluded from ruff (they are notebooks, not library code).
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.
- 5d ago First seen · 169 lines · 2,353 tokens per session scan A 3402db650546
Impulso CLAUDE.md is an instructions file published in the GitHub repository thomaspinder/Impulso (23 stars, last pushed 4d ago), licensed MIT. It adds 2,353 tokens to every session, about $0.0118 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 2026-08-30.
Other instructions, from other repositories
questdb CLAUDE.md
Claude Code instructions for questdb/questdb, covering claude.md, project overview, coding guidelines, tests and questdb's sql dialect.
arcadedb CLAUDE.md
Claude Code instructions for ArcadeData/arcadedb, covering claude.md, project overview, response formatting, project instructions and build and development commands.
AutoTS AGENTS.md
Instructions for winedarksea/AutoTS, covering autots agent overview, general code guidelines, small files & single responsibility, hyper-descriptive naming and high-signal comments.
barkley-reference-architecture CLAUDE.md
Claude Code instructions for labs-barkley/barkley-reference-architecture, covering claude.md — barkley reference architecture, what this repo is, before touching any code, non-negotiable framing — read this first and what belongs here — and what doesn't.
art-python AGENTS.md
AGENTS.md instructions for davidesg/art-python, covering agents.md — operating the atsw suite as an ai agent, the suite, core philosophy: evidence vs criterion, two modes and non-negotiable rules.
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).