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 skills add ai4s-research/ai4s-skills --skill mindmap-rendergit clone --depth 1 https://github.com/ai4s-research/ai4s-skillsWrote 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/skills/ai4s-research/ai4s-skills/mindmap-render)<a href="https://agentmods.dev/skills/ai4s-research/ai4s-skills/mindmap-render"><img src="https://agentmods.dev/badge/skills/ai4s-research/ai4s-skills/mindmap-render/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ai4s-research/ai4s-skills/mindmap-render"><img src="https://agentmods.dev/badge/skills/ai4s-research/ai4s-skills/mindmap-render.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00030 | $0.02827 |
| Opus 5.5 | $0.00012 | $0.01131 |
| Sonnet 5.5 | $0.00006 | $0.00565 |
| Haiku 4.5 | $0.00003 | $0.00283 |
Grade A, and why
mindmap-render 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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Use this skill when the user asks to:
- Create a mindmap from a topic or data.
- Convert a Markdown outline into a visual mindmap image or PDF.
- Generate a colorful, presentation-quality mindmap with auto-export to PNG/PDF.
- Build a structured outline (unordered list) and then render it as a mindmap.
Prerequisites
Assume the runtime environment already has Python 3.10+, Playwright, and Chromium installed (they are provisioned in the container). Do not proactively run pip install or playwright install — just run the render script directly. Only if the first run fails with a clear missing-dependency error (ImportError, missing-browser error, etc.), then repair the environment:
pip install -r scripts/requirements.txt
playwright install chromium
and retry. Never install speculatively before a failure is observed.
Workflow
Step 1 — Determine input source
Ask the user (or infer from context):
- Topic: What is the central theme?
- Data source: Do they already have a Markdown file, or should you research and write one?
- Source fidelity vs synthesis — a spectrum, not a binary. The more specifically the request points to a named existing artifact (a particular book's table of contents (ToC), a particular course's syllabus, a specific spec or documentation structure, a numbered chapter list), the more you should reproduce the source's real structure verbatim — preserve original labels and numbering, follow the source's natural depth, and add NO fabricated descriptions. The more the request is a broad topic with no single canonical source, the more the structural targets below apply. Most requests sit somewhere on this spectrum; judge and lean accordingly.
- Theme:
air(light blue glow + white cards, default),editorial(warm paper + jewel-tone branches),midnight(deep black + neon accents), orzen(soft misty background + muted pastels). - Language:
- If the user explicitly specifies a language (e.g. "in English", "in Japanese"), use that language for all node text (labels + layer-5 descriptions).
- Otherwise, match the language of the user's request; default to English when the request language is unclear.
- Do not translate proper nouns, model names, or established technical terms — preserve them inline.
What ships with it
3 files 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.
- 1mo ago First seen · 152 lines · 30 tokens per session scan A 4d6f0f22adfd
mindmap-render is a skill published in the GitHub repository ai4s-research/ai4s-skills (254 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 2,827 once invoked, about $0.0001 per session on Opus 5.5. 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
remote-compute
Use when the user asks to run, submit, monitor, or cancel a job on a remote machine over SSH — their own GPU/CPU server, a workstation, or a Slurm cluster ("the cluster", a login node, "my 3090 box", "the compute server"). Picks a saved machine, runs the work directly over SSH (or via Slurm when present), tracks it…
domain-check
Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a…
computer-use
Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first computer call. Covers the observe-act-observe loop, why…
publication-figures
Use whenever you generate or review a chart, plot, table, or paper figure in this workspace, including work delegated by paper-writing, literature-survey, and experiment skills. Applies the Open Science publication style, enforces readable final-size layout for figures and tables, and rejects generic diagram-tool…
modal-run
Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own modal CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.
traceability-review
Use when the user asks to review, verify, or audit a report, manuscript, or analysis in the workspace for traceability — resolving citations, flagging numbers with no source, and checking figures against the code that generated them. Emits a structured review block the app renders as reviewer findings. Verifies…