What is pygraphistry AGENTS.md?

Repository instructions for the Graphistry PyGraphistry project. They explain where agent skills live, how shared skill folders are linked for different coding tools, and which checks to run.

Use them when setting up agent skills, linking the project’s shared instructions, running lint or tests, or assisting with a release to PyPI, Python’s package repository.

They prevent tools from looking in the wrong skill directory and keep local tool links separate from tracked project files. They also clarify the project’s expected verification steps.

pygraphistry AGENTS.md — Instructions file by graphistry

Install

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.

agentmods

npx agentmods add instructions/graphistry/pygraphistry/agents-md

Clone the repo

git clone --depth 1 https://github.com/graphistry/pygraphistry

Made for: Codex, OpenCode.

Per session 399 This file is loaded in full into every session.

When invoked 399 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00399	$0.00399
Opus 5	$0.00199	$0.00199
Sonnet 5	$0.00080	$0.00080
Haiku 4.5	$0.00040	$0.00040

Measured yesterday against content hash 761e39fcfa44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pygraphistry AGENTS.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 yesterday.

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.

AGENTS.md · 49 lines

What it actually says

AGENTS.md

This file defines AI assistant guidance for this repository.

Skill Locations

Canonical skills live under:

agents/skills/

For tools that expect .agents/skills/, use a local symlink:

ln -s agents .agents

Platform Path Conventions

OpenAI Codex: prefers .agents/skills/
Claude Code: often uses .claude/skills/
Other tools (Cursor/Copilot/etc.): may use .agents/skills/ or tool-specific paths

Recommended local setup:

# Canonical -> tool-expected path
ln -s agents .agents

# Claude path to shared skills
mkdir -p .claude
ln -s ../.agents/skills .claude/skills

/.agents/ is ignored in git to keep local tool wiring out of commits.

Guidance Priority

Follow repository docs and tests as source of truth.
Keep edits minimal and verifiable.
Run relevant lint/tests for touched areas.

Release Assistant Reminder

During publish assistance, after pushing tag X.Y.Z, always check .github/workflows/publish-pypi.yml run state.
Treat Publish distribution to PyPI in waiting as an expected manual gate for environment pypi-release; explicitly instruct maintainer to click Review deployments before expecting PyPI completion.
After the workflow completes, verify both TestPyPI and PyPI public metadata report X.Y.Z; PyPI may lag briefly after the job succeeds.
Create or verify the matching GitHub Release for tag X.Y.Z, then check Read the Docs. latest may update automatically, while tag-specific versions can require maintainer activation in the RTD dashboard.
Record release follow-ups discovered during readiness audits as issues in the owning repo before final handoff.

Changes

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.

yesterday First seen · 49 lines · 399 tokens per session scan A 761e39fcfa44

Subscribe to this mod's changes

pygraphistry AGENTS.md is an instructions file published in the GitHub repository graphistry/pygraphistry (2,551 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 399 tokens to every session, about $0.0020 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.

Code review GPU Git and workflow RAPIDS Testing graph graphistry python visualization

pygraphistry AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

AGENTS.md

Skill Locations

Platform Path Conventions

Guidance Priority

Release Assistant Reminder

What this file has done since we first saw it

Other instructions, from other repositories

dstack AGENTS.md

httpstat AGENTS.md

httpstat CLAUDE.md

stock-ai-graph CLAUDE.md

deepagents AGENTS.md

pygwalker CLAUDE.md