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 firatcand/forge --skill draft-designgit clone --depth 1 https://github.com/firatcand/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/firatcand/forge/draft-design)<a href="https://agentmods.dev/skills/firatcand/forge/draft-design"><img src="https://agentmods.dev/badge/skills/firatcand/forge/draft-design/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/firatcand/forge/draft-design"><img src="https://agentmods.dev/badge/skills/firatcand/forge/draft-design.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 | $0.00051 | $0.00658 |
| Opus 5.5 | $0.00020 | $0.00263 |
| Sonnet 5.5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
draft-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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/draft-design
Preconditions
spec/PRD.mdmust exist- Project has a UI surface (marketing site, app UI, email, docs). Skip for pure-backend products.
Init prompt
When /draft-design runs the first time on a project, ask:
Do you have a design system to reference, or should I create one for this project?
A) Reference external — point me at a URL, file path, or brand-book asset. The project's DESIGN.md will be generated consistent with that reference, but stored locally as a self-contained doc.
B) Create new — I'll generate a self-contained palette, type scale, spacing, components, voice from your product requirements.
Save the answer to .forge/settings.yaml:
design:
mode: project_owned # project_owned | reference_external
reference: <url-or-path> # only if mode = reference_external
Orchestration
- Read PRD
- Read
.forge/settings.yamlfordesign.mode+design.reference - Check if user has a
ux-design,graphic-design, orfrontend-design-proskill — invoke with PRD + reference (if any) as context - Determine project surface area (marketing site, app UI, email, docs)
- Generate
spec/DESIGN.mdaccording to mode:- project_owned — write self-contained tokens, components, layouts, voice derived from product requirements
- reference_external — read the reference, extract its guidelines (palette, type scale, spacing, voice register), write DESIGN.md consistent with it as a self-contained local doc
Important: no @inherit pattern
DESIGN.md is a self-contained project artifact. It does NOT inherit at runtime from a maintainer-global brand book or external file. If a reference is configured, it constrains generation of DESIGN.md, but DESIGN.md itself is the project's source of truth from that point forward.
Output
Print:
DESIGN written to spec/DESIGN.md (mode: {{design_mode}})
Summary:
- Tokens: [palette + type scale]
- Components: [primitives + composites]
- Voice: [tone + register]
- Reference: [if any]
Gate 3 — review the DESIGN. To proceed:
• /ingest-spec to validate BRIEF + PRD + SPEC + DESIGN coherence
• Edit spec/DESIGN.md directly
• /draft-design --refine [section] to re-generate
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.
- 1mo ago First seen · 71 lines · 51 tokens per session scan A 038a2f4a8737
draft-design is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 658 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
ui-verify
(loop-engineering) Visually inspects UI changes by screenshotting routes with pnpm snap and reading the images against a design checklist (layout, spacing, hierarchy, semantic tokens, empty/loading/error states). Use after implementing any UI change, before opening a PR that touches src/app or src/components, or when…
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
design-an-interface
Generate radically-different module or API contract designs in parallel, then compare on depth, simplicity, and ease-of-correct-use. Trigger when the user is shaping a new module surface, exploring contract options, comparing module shapes, or applying "design it twice" to a first-pass sketch.
{skill_name}
Personal taste skill — 5 evidence-derived anchors ({anchornames}) for prose, code, design, and decisions. Two modes: audit judges an artifact against the two-sided charter; anchor loads the taste register before producing. Trigger with "{triggerphrase}", "taste-test", "is this slop?", or "overkill?".
loft
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks.…