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/a554b554/reactant/plotnpx skills add a554b554/Reactant --skill plotgit clone --depth 1 https://github.com/a554b554/ReactantWhat 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 | $0.00020 | $0.00792 |
| Opus 5 | $0.00010 | $0.00396 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
plot 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plot
Generate a data visualization by producing and executing a Python script (Matplotlib/Seaborn) based on the prompt, surrounding context, and a referenced data file.
Input
- File path: the file being processed.
- Surrounding text: the paragraph or block where the
<@plot: ...>tag appears. - Prompt: description of the desired visualization, including chart type, styling, and any specific formatting instructions.
Workflow
- Read the surrounding text and prompt.
- Identify the data file from the prompt's context references (
``). Read the data file to understand its structure (columns, types, number of rows). - Identify the output path from the prompt's context references. If none is specified, save the plot in the same directory as the source file with a name derived from the prompt (e.g.,
plot_completion_time.png). - Generate a self-contained Python script that:
- Reads the data file (using
pandasfor CSV/TSV/Excel, or appropriate libraries for other formats). - Produces the requested visualization using
matplotliband/orseaborn. - Applies any styling or formatting instructions from the prompt.
- Saves the figure to the output path with
dpi=300andbbox_inches='tight'.
- Reads the data file (using
- Execute the script in a single Bash command:
python -c " <generated script here> " - Verify the output file was created.
- Replace the
<@plot: ...>tag with a format-appropriate image reference:- Markdown (
.md): - LaTeX (
.tex):\includegraphics{output_path.png} - other format, try to determine by yourself.
- Markdown (
Context References
The prompt may contain context references wrapped in double backticks ( ``). These point to external resources.
- As data source: The reference points to the data file to visualize. E.g.,
<@plot: bar chart using ``data/results.csv``>-- readdata/results.csvas the input data. - As output path: The reference specifies where to save the generated plot. E.g.,
<@plot: line chart, save to ``figures/trend.png``>-- save the plot tofigures/trend.png. - Resolve references relative to the source file's directory unless an absolute path is given.
- Remove the
delimiters from the output. - If the input tag does not contain any context reference, ask user the elaborate.
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 · 60 lines · 20 tokens per session scan A c41361fbe4b3
plot is a skill published in the GitHub repository a554b554/Reactant (54 stars, last pushed 29d ago), licensed MIT. It adds 20 tokens to every session and 792 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…