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 flonat/flonat-research --skill tikzgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/tikz)<a href="https://agentmods.dev/skills/flonat/flonat-research/tikz"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/tikz/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/flonat/flonat-research/tikz"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/tikz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 276 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.03114 |
| Opus 5 | $0.00028 | $0.01557 |
| Sonnet 5 | $0.00011 | $0.00623 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
tikz 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 8d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikZ Collision Audit
Purpose: Find and fix residual visual collisions in TikZ figures in a given .tex file. Labels on arrows, text inside boxes, arrows crossing arrows — this skill catches them using measurement, not intuition.
The fundamental rule: an AI agent cannot reliably eyeball where TikZ elements land. All placement must be verified mathematically before declaring it safe.
Critical context: this is a repair tool, not the primary defense
tikz runs after TikZ has been generated. It audits existing code and fixes what it finds. But it cannot reliably fix diagrams that were never built with measurement in mind.
The upstream defense is writing TikZ safely from the start:
- Every
\nodedeclares explicitminimum widthandminimum height - Every edge label carries a directional keyword (
above,below, etc.) - A coordinate map comment block precedes every
tikzpicture - Standard diagram types use canonical safe templates
scaleis never used on complex diagrams
When new decks are authored via beamer-deck, prefer applying these rules during generation. tikz is the downstream cleanup pass for anything that slipped through or for legacy/hand-written TikZ.
When upstream rules were applied: tikz should find few or no issues. Run it as a check.
When upstream rules were NOT applied (legacy TikZ, hand-written diagrams, inherited decks): tikz does its best, but expect more findings, more iteration, and lower reliability on autosized nodes and scaled diagrams.
The companion reference tikz_rules.md (in this skill's directory) contains the full formulas and worked examples — read it once before running the audit passes below.
Step 1: Identify the file and run the pre-check
If the user specified a file, use it. If not, ask. Then:
grep -n "tikzpicture\|begin{frame}\|node\|draw\|bend\|foreach" [file].tex | head -100
Get a sense of scope: how many TikZ diagrams, how many frames, how many arrows.
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.
- 8d ago First seen · 277 lines · 55 tokens per session scan A fd30e2997333
tikz is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 3,114 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 2026-09-03.
Other skills, from other repositories
thesis-figure-skill
An academic-diagram skill for creating research-paper figures as TikZ/LaTeX code or draw.io XML. TikZ is code that embeds precisely into LaTeX papers, while draw.io XML creates diagrams editable in the draw.io app.
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
law-of-similarity
Apply the Law of Similarity — shared colour, shape, or size signals that elements belong to one category. Use when signalling relationships across distance. For grouping by position, use law-of-proximity.
concept-selection
Choose between competing concepts against criteria fixed in advance, and record what each rejected concept was testing. Use when several directions are alive and one has to win. For picking which problem to work on, use opportunity-framework (ux-strategy); for deciding by production traffic, use a-b-test-design.
aesthetic-usability
Apply the Aesthetic-Usability Effect — polished, consistent interfaces are perceived as more usable and forgive minor friction. Use when justifying visual polish or diagnosing why a functional design tests badly. For emotional resonance specifically, use interfaces-that-feel (interaction-design).
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).