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/beyarkay/claude-skills/quickplotnpx skills add beyarkay/claude-skills --skill quickplotgit clone --depth 1 https://github.com/beyarkay/claude-skillsWhat 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 | $0.00092 | $0.01412 |
| Opus 5 | $0.00046 | $0.00706 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
quickplot 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
quickplot
Turn raw numbers into a compact unicode sparkline histogram + box-and-whisker plot, plus a full numeric summary, printed in the terminal. For quick-and-dirty "what does this distribution look like" checks — real/paper plots happen elsewhere.
Group name on the left, graphics (histogram over box-&-whisker) on the right,
all on a shared fixed x-axis; the full numeric summary is a column-aligned list
below. The histogram is 2 character rows tall by default (16 levels of vertical
resolution, linear — bar heights stay proportional), which makes low-count tail
bins visible without distorting anything; --rows 1 drops to a compact single
row.
200 samples each
Normal ▃ ▂█
▁ ▁▂▁▃▄▆▆█▆██████▄█▅▁▂▅ ▃ ▁▁ ▁ <- histogram (2 rows)
├──────────[==┃==]───────────┤ <- box & whisker
Exponential █
█▃▆█▅▅▄▃▄▄▃▃▁▂▁▁▂ ▁▁ ▁ ▁
├─[==┃===]─────────────────────┤
Uniform ▃ ▁ ▄▃ ▁ ▃ ▆ ▁▃ ▁▃ ▁█ ▁ ▃▁▁ ▁▃▄
▅█▇█▄██▅█▇▇▇█▄▄▇█▇▅▅██▇██▇▇██▅▅▇▅▂▇▄▅█▄███▅███
├──────────[===========┃==========]──────────┤
└──────────┴──────────┴───────────┴──────────┴ <- shared axis (once)
0.16 24.6 49 75.6 100
Normal: n=200 min 18.6 q1 41.5 med 49.9 q3 56 max 82.6 mean 49.5 sd 11.2
Exponential: n=200 min 0.16 q1 4.31 med 10.8 q3 21 max 69.9 mean 14.5 sd 13.6
Uniform: n=200 min 1.22 q1 24.6 med 50.1 q3 75 max 100 mean 50.2 sd 29.5
Box & whisker reads ├ min · [ q1 · ┃ median · ] q3 · ┤ max. Stacking
several groups lets you eyeball-compare spreads since every box sits on the
same axis.
The contract — why this is a script, not eyeballing
plot.py is the only thing allowed to turn the data into a picture or a
summary. It computes the histogram, the box plot, and the full seven-number
summary itself. You run it and paste its output verbatim.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 100 lines · 92 tokens per session scan A d2bbc97fc9cf
quickplot is a skill published in the GitHub repository beyarkay/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,412 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.