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 skills/graphistry/pygraphistry/reviewnpx skills add graphistry/pygraphistry --skill reviewgit clone --depth 1 https://github.com/graphistry/pygraphistryWhat 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 | $0.00069 | $0.03840 |
| Opus 5 | $0.00034 | $0.01920 |
| Sonnet 5 | $0.00014 | $0.00768 |
| Haiku 4.5 | $0.00007 | $0.00384 |
Grade A, and why
review 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 2d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review (pygraphistry)
Invocation
/review [<PR-number-or-branch>] [mode=findings|pr-comments|both] [fixes=deferred|inline]
Defaults:
- Target: current branch PR (
gh pr view --json number,headRefName,baseRefName,url) mode=findingsfixes=deferred
mode:
findings: local artifacts only underplans/<task>/pr-comments: draft locally, post only after explicit user confirmation in the same sessionboth: run findings then comment flow
fixes:
deferred: read-only reviewinline: after each converged wave, apply confirmedBLOCKER/IMPORTANTfixes in separate commits
Runtime Assumptions
- Run from repo root.
ghis authenticated (gh auth status).- Local branch reflects PR head (
origin/<base>...HEADmatches intended review scope). plans/is local working memory and normally gitignored.
Plan-First Requirement
Always use the plan skill flow:
- If
plans/<task>/plan.mdexists, reuse it and append a review section. - Else reload
.agents/skills/plan/SKILL.mdand createplans/<task>/plan.md. - Record PR metadata,
mode,fixes, and timestamp. - Reload plan before every step; update plan immediately after every step.
<task>: prefer review-pr-<N> or <branch>-review.
Phase 0: Resolve Scope + Stack Context
- Resolve PR context (number/title/url/head/base).
- Record stack context:
gh pr view <PR> --json baseRefName,headRefName,title,body
gh pr list --base <headRefName>
- If stacked, explicitly mark out-of-scope upstream/downstream work in
plan.md. - Set diff range reference:
origin/<base>...HEAD.
Phase 1: Research Criteria Before Findings
Create plans/<task>/research/ with:
context.mdpolicies.mdcredentials.mdcanvas-<dimension>.md(only for dimensions that apply)
1a) Collect context + changed files
gh pr view <PR> --json number,title,headRefName,baseRefName,url,body
git fetch origin <baseRefName> <headRefName>
git diff --name-only origin/<base>...HEAD
git log --oneline origin/<base>..HEAD
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.
- 2d ago First seen · 346 lines · 69 tokens per session scan A c24bd7054c82
review is a skill published in the GitHub repository graphistry/pygraphistry (2,551 stars, last pushed today), licensed BSD-3-Clause. It adds 69 tokens to every session and 3,840 once invoked, about $0.0003 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 skills, from other repositories
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI. Use when the user asks to inspect or manage Lepton workspaces, endpoints/deployments, dev pods, batch jobs, fine-tuning jobs, Ray clusters, Slurm clusters, Dynamo endpoints, storage, secrets, nodes, ingress, templates, logs, authentication, or…
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
data-analysis
Comprehensive data analysis skill for CSV files using Python and pandas.
dstack-presets
Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.
httpstat
Diagnose website and API performance using httpstat — a curl wrapper that visualizes HTTP timing breakdowns (DNS, TCP, TLS, server processing, content transfer). Use this skill whenever the user wants to debug slow websites, analyze HTTP/HTTPS latency, profile API response times, understand curl timing output, find…
geopandas
Use when performing vector spatial data analysis in Python — reading/writing shapefiles, spatial joins, overlay operations, choropleth maps. GeoPandas: extends pandas DataFrames with geometry columns for Pythonic spatial analysis.