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 thcjp/hermes-skills --skill figma-2git clone --depth 1 https://github.com/thcjp/hermes-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/thcjp/hermes-skills/figma-2)<a href="https://agentmods.dev/skills/thcjp/hermes-skills/figma-2"><img src="https://agentmods.dev/badge/skills/thcjp/hermes-skills/figma-2/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/thcjp/hermes-skills/figma-2"><img src="https://agentmods.dev/badge/skills/thcjp/hermes-skills/figma-2.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 | $0.00127 | $0.02820 |
| Opus 5 | $0.00063 | $0.01410 |
| Sonnet 5 | $0.00025 | $0.00564 |
| Haiku 4.5 | $0.00013 | $0.00282 |
Grade A, and why
figma-2 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 9d 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
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 9d ago First seen · 353 lines · 127 tokens per session scan A 2c39adbebce1
figma-2 is a skill published in the GitHub repository thcjp/hermes-skills (1 stars, last pushed 21d ago), with no licence file. It adds 127 tokens to every session and 2,820 once invoked, about $0.0006 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
excalidraw
Hand-drawn diagrams in Excalidraw JSON (architecture, flowcharts).
ux-intuition
Develop the instinct for what makes a product feel right, beyond what data can tell you. Covers quality evaluation, interaction judgment, and knowing when something is off even if you can't articulate why. Use when evaluating designs, reviewing prototypes, or when metrics say it's fine but something feels wrong.
working-with-design
Partner with design to create better products, not just prettier ones. Covers when to involve design, how to give useful feedback, and respecting the design process. Use when PM-design handoffs feel clunky, design feedback conversations are unproductive, or design is brought in too late.
user-psychology
Apply motivation, friction, and trust patterns to product decisions. Maps cognitive biases and behavioral triggers to specific UI and copy choices. Use when reviewing flows for drop-off points or when something feels right but doesn't convert.
aha-moment-mapping
Identify the moment when a new user first experiences your product's core value. Maps the path from signup to that moment and removes friction in between. Use when new user retention is poor, redesigning onboarding, or when the product has strong acquisition but weak activation.
microcopy
The small words that shape big experiences. Button labels, tooltips, confirmations, placeholders, and the 3-word strings that determine whether a product feels polished or half-finished. Use during any copy audit pass.