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/kanaries/pygwalker/claude-mdgit clone --depth 1 https://github.com/Kanaries/pygwalkerWrote 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/kanaries/pygwalker/claude-md)<a href="https://agentmods.dev/instructions/kanaries/pygwalker/claude-md"><img src="https://agentmods.dev/badge/instructions/kanaries/pygwalker/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 | $0.00365 | $0.00365 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
pygwalker 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 4d 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
This project's contributor & agent guide is maintained in AGENTS.md — a single source of truth for the architecture, dev-mode workflow, and log locations. Read it before making changes.
@AGENTS.md
TL;DR for a coding agent
- Setup:
python -m venv venv && source venv/bin/activate && pip install -e ".[dev]", thencd app && yarn install && yarn build. - Run everything in dev mode with live reload + centralized logs:
python scripts/dev.py(starts the frontend watch build + JupyterLab withPYGWALKER_DEV=1/ANYWIDGET_HMR=1). Pass--no-browserfor headless runs. - Logs:
logs/frontend.log(build/watch),logs/jupyter.log(server URL + token),logs/pygwalker.log(kernel-side Python logs). Frontend runtime logs are in the browser console. - In a notebook: just
import pygwalker as pyg; pyg.walk(df)— no special setup; edits underapp/src/hot-reload into the widget. - Before pushing:
python scripts/local_ci.py(or, narrower,yarn typecheck+yarn buildinapp/, andruff check/ruff format --check/pytestfrom the root). - Don't: commit
pygwalker/templates/dist/, hand-editapp/src/interfaces/comm.generated.ts, or rely onPYGWALKER_DEV/ANYWIDGET_HMRat runtime for end users.
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.
- 4d ago First seen · 25 lines · 365 tokens per session scan A f8bf5f0137bc
pygwalker CLAUDE.md is an instructions file published in the GitHub repository Kanaries/pygwalker (15,953 stars, last pushed 23d ago), licensed Apache-2.0. It adds 365 tokens to every session, about $0.0018 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
mcp-data-explore CLAUDE.md
Claude Code instructions for Mingwei2/mcp-data-explore, covering claude.md, project overview, development commands, or and mcp server architecture.
semiotic CLAUDE.md
Claude Code instructions for nteract/semiotic, covering semiotic claude code instructions and claude code notes.
tableau-mcp CLAUDE.md
Instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.
trendspyg AGENTS.md
Instructions for flack0x/trendspyg, covering agents.md, what this library does, install, mcp server — the zero-code path and minimal recipes.
stata-code CLAUDE.md
Instructions for brycewang-stanford/stata-code, covering claude.md — stata-code project notes, communication, release coordination, pypi / testpypi trusted publishing — what to know and recovery: invalid-publisher failure.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).