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 haorantang97/LabArt --skill tephragit clone --depth 1 https://github.com/haorantang97/LabArtWrote 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/haorantang97/labart/tephra)<a href="https://agentmods.dev/skills/haorantang97/labart/tephra"><img src="https://agentmods.dev/badge/skills/haorantang97/labart/tephra/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/haorantang97/labart/tephra"><img src="https://agentmods.dev/badge/skills/haorantang97/labart/tephra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00243 | $0.07998 |
| Opus 5 | $0.00121 | $0.03999 |
| Sonnet 5 | $0.00049 | $0.01600 |
| Haiku 4.5 | $0.00024 | $0.00800 |
Grade A, and why
tephra 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 4d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
14 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.
- agents/openai.yaml 267 B
- references/modules.md 9.0 KB
- references/proposals-density.md 38 KB
- references/proposals-edge.md 27 KB
- references/proposals-rain.md 23 KB
- references/worked-example.md 20 KB
- scripts/dp_fitness.py 2.6 KB runs code
- scripts/m4_check.py 3.0 KB runs code
- scripts/m4_erode.py 1.8 KB runs code
- scripts/native_check.py 1.3 KB runs code
- scripts/p4_mask.py 2.0 KB runs code
- scripts/strand_check.py 1.5 KB runs code
- scripts/tephra.py 128 KB runs code
- scripts/upscale_nearest.py 541 B runs code
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.
- 4d ago First seen · 316 lines · 243 tokens per session scan A 9a7b3e826343
tephra is a skill published in the GitHub repository haorantang97/LabArt (285 stars, last pushed 5d ago), with no licence file. It adds 243 tokens to every session and 7,998 once invoked, about $0.0012 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 2026-09-07.
Other skills, from other repositories
chalk-logic
Create Chalk Logic concept-led chalkboard illustrations from briefs. Use for sparse wordless chalkboard explanations, non-diagram editorial chalk compositions, or prompt-only Chalk Logic recipes.
signal-geometry
Create Signal Geometry abstract illustrations and posters from concepts or briefs. Use when the user asks for sparse geometric visuals, editorial posters, spatial systems, or prompt-only image recipes.
director-cinematography
A guide to visual storytelling for video, covering shot sizes, composition, camera movement, lighting, focus range, color temperature, and lens characteristics. It also explains how to turn these choices into video prompts.
writer-screenwriter
A professional screenwriting guide based on methods associated with Lawrence Kasdan and Tony Gilroy. It covers story structure, scenes, dialogue, quality checks, and formats for films and series.
director-art-design
A prompt-writing guide for generating character-setting and scene images with a consistent visual style and recurring character details.
workbench-storyboard-planner
A Chinese-language storyboarding planner that turns a story into a structured shot plan. A storyboard maps each scene or camera shot, including its duration, characters, setting, props, style, references, and prompts.