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/lftpadilla/agent-dev-kit/tex-rendernpx skills add LFTPadilla/agent-dev-kit --skill tex-rendergit clone --depth 1 https://github.com/LFTPadilla/agent-dev-kitWhat 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 | $0.00063 | $0.01440 |
| Opus 5 | $0.00032 | $0.00720 |
| Sonnet 5 | $0.00013 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
tex-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 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TeX Render 📐
Renders LaTeX math to PNG, JPEG, WebP, or AVIF (and SVG). Use when you need a viewable image from LaTeX instead of raw code.
Location
The render script lives in the same skill folder as this SKILL.md:
<skill_folder>/
├── SKILL.md
├── package.json
└── scripts/
└── render.js
Use the directory containing this SKILL.md as the skill path. The script is at scripts/render.js relative to that folder. Invoke: node <skill_folder>/scripts/render.js. The agent loading this skill has the skill path—use it to run the script.
Install
One-time setup. After npm install run npm install` in the skill folder:
cd <skill_folder>
npm install
When to Use
- User or task asks to "render this equation as image" or "show formula as picture"
- Your reply would contain LaTeX — render formulas as images first, then respond with plain text
Workflow: Response Contains LaTeX
Output your reply interleaved: whenever you would output LaTeX, do this instead:
- Send the preceding plain text — call
messagewith the text written so far (no LaTeX). - Render the LaTeX expression with this skill (default PNG; no
--output dataurl). Parse the JSON for the PNG path. - Send the image — call
messagewithaction: "send",pathset to the rendered PNG, andmessageas short caption. - Continue outputting the rest of the message. Repeat the cycle (text → render → send image) for each LaTeX block.
Do not output raw LaTeX. Do not ask the user for permission to render — render and send images immediately when LaTeX would appear in your reply. Do not accumulate everything and send at the end — send text and images in order as you go.
Critical: Output in order: plain text → send → LaTeX → render → send image → plain text → send → LaTeX → render → send image → … The user must receive text and images in the natural reading order.
Example: Explaining Lagrangian:
→ Send "The Lagrangian is defined as " → Render L = T - V → Send image with caption "L = T - V" → Send ". The Euler-Lagrange equation is " → Render d/dt(∂L/∂q̇) - ∂L/∂q = 0 → Send image → Send " — this yields the equations of motion."
What ships with it
4 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.
- yesterday First seen · 126 lines · 63 tokens per session scan A 7d912a69d0b9
tex-render is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,440 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 2026-08-31.
Other skills, from other repositories
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
convex-billing
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.