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 OutlineDriven/outline-driven-development --skill design-consultationgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/design-consultation)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/design-consultation"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/design-consultation/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/outlinedriven/outline-driven-development/design-consultation"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/design-consultation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00737 |
| Opus 5 | $0.00026 | $0.00368 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
design-consultation 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design consultation
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /design-consultation |
| Authority | Write only the named local artifacts: DESIGN.md, CLAUDE.md pointers, and design artifacts (mockups or an HTML preview). No remote, VCS, credential, paid, published, or deployed mutation. Roll back by reverting those files. |
| Side effect | Local writes to DESIGN.md, CLAUDE.md pointers, and design artifacts, bounded to the current project directory. |
| Done | An approved design system is persisted in DESIGN.md. |
Inputs
- A design brief or the feature/surface under design, supplied by the user. Required.
- Project context: existing design tokens, brand guidance, target surface (web, TUI, mobile), and any existing DESIGN.md to extend. Optional; read what is present.
- User approval is the in-loop gate: no design system is persisted until the user approves it.
Procedure
-
Read the project context that is present: existing DESIGN.md, design tokens, brand guidance, and the target surface. Do not invent context that is absent; state what is missing. Done when: present context is read and missing context is named.
-
From the brief and context, propose a design system: color palette, typography scale, spacing and rhythm, component primitives, and interaction states. Keep the proposal concrete and tied to the named surface. Done when: the five system parts are proposed and tied to the named surface.
-
Produce a preview the user can react to: mockups or a self-contained HTML preview rendered for the target surface. The preview must reflect the proposed tokens, not generic defaults. Done when: a preview exists that reflects the proposed tokens.
-
Present the proposal and preview to the user and request approval. This is the gate: do not write DESIGN.md before approval. Done when: the proposal and preview are presented and approval is requested.
-
On approval, persist the approved design system in DESIGN.md: tokens, component primitives, and the rules needed to apply them. Add CLAUDE.md pointers that reference DESIGN.md as the design source of truth. Done when: DESIGN.md and CLAUDE.md pointers are written.
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 · 45 lines · 53 tokens per session scan A c2bd30ea4122
design-consultation is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 737 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 2026-09-03.
Other skills, from other repositories
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
humansense2system
Use when the user wants to compile taste and "this feels wrong" signals into machine-consumable tokens, rules, forbidden combinations, and examples. Elicits concrete cases, classifies each into one of four buckets, and writes a structured rule/pattern document. Not for remote, credential, publish, deploy, or…
typography-audit
Use when asked to audit typography across a codebase. Produces a file:line report with concrete fixes ordered by impact and flags unverifiable rules. Not for building a type system or token scale.
design
Use when starting UI work, defining palettes or tokens, fixing AI-generic UI, or persisting a design system to DESIGN.md (modes: implement, persist). Not for live URLs: use web-design-review.
polished-web-prototype
Use when /polished-web-prototype runs or a user builds an artifact from a mockup, design plan, or brief. Not for variant galleries: use design-variants. Not for live audits: use web-design-review.
ui-design
Use when directing, building, or auditing React/Next.js Tailwind UI: visual direction, responsive/dark-mode retrofits, UX audits. Not for typography or motion: use typography-audit or ui-animation.