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/mfrostbutter/skill-forge/figma-design.examplenpx skills add Mfrostbutter/skill-forge --skill figma-design.examplegit clone --depth 1 https://github.com/Mfrostbutter/skill-forgeWrote 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/mfrostbutter/skill-forge/figma-design.example)<a href="https://agentmods.dev/skills/mfrostbutter/skill-forge/figma-design.example"><img src="https://agentmods.dev/badge/skills/mfrostbutter/skill-forge/figma-design.example.svg" alt="Measured on agentmods" 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 | $0.00112 | $0.00719 |
| Opus 5 | $0.00056 | $0.00360 |
| Sonnet 5 | $0.00022 | $0.00144 |
| Haiku 4.5 | $0.00011 | $0.00072 |
Grade A, and why
figma-design 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 5d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma design + build
This is a worked example of a skill produced by skill-forge from examples/WORKLOG.example.md. It shows how tagged journal entries become a procedure, guardrails, and reference notes. The design tool runs JavaScript against the plugin API and renders server-side; drive it like a headless design tool and verify every step with a screenshot.
Procedure (ordered, do not reorder)
- Establish page structure and a layer-naming convention before creating any frame. This is step 1, always. Frames-first produces ungrouped, default-named layers (Rectangle, Text) that are unusable for dev handoff and painful to fix after. Decide pages and naming first.
- Confirm the account and plan. Edits fail silently on a view-only account.
- Foundations first. Create paint, text, and effect styles (guard by name to avoid duplicates) before drawing any UI. This locks the palette and type ramp and makes every later node bindable.
- Discover and load fonts up front. List available fonts filtered to your candidates, record exact style names (they vary:
Semi BoldvsSemiBold), then load every weight before setting any text. - Build named, bound, and grouped as you go. Name every node on creation, bind to styles from the first draw, build each section inside a named container. Draw backgrounds before text.
- Screenshot loop. Build a small piece, screenshot the real node, read it, fix, repeat. Never author a large design blind.
- Componentize. Promote repeated UI to components; group variants. Name components with
/folders (Logo/Mark,Button/Primary).
Hard rules (guardrails)
- Bind nodes to styles from the first draw, never restyle after. Restyling a built screen by hand drifts from the system and wastes a pass.
- Await the page switch before reading a page's children. Otherwise it returns an empty list.
- Do not author blind. Hand-authoring without rendering ships ugly. The screenshot loop is the work.
- Default node names are not acceptable. Text = its content, rects = their role (
bg,divider,card).
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.
- 5d ago First seen · 36 lines · 112 tokens per session scan A 59a643dc3d90
figma-design is a skill published in the GitHub repository Mfrostbutter/skill-forge (4 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 719 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 2026-08-31.
Other skills, from other repositories
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.