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 vidhunnan/agentic-skills --skill design-briefgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/design-brief)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-brief"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-brief/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/vidhunnan/agentic-skills/design-brief"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-brief.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 | $0.00136 | $0.02437 |
| Opus 5 | $0.00068 | $0.01218 |
| Sonnet 5 | $0.00027 | $0.00487 |
| Haiku 4.5 | $0.00014 | $0.00244 |
Grade A, and why
design-brief 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 10d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-brief
Writes the document design work usually starts without: what this is for, who it's for, and what would count as having worked.
Everything downstream depends on it. design-critique reviews against a brief —
without one, feedback has nothing to be measured against and collapses into taste,
where the loudest preference wins. design-decisions cites it for the constraints
a fork was weighed under. case-study-writer opens with it. A model asked to
critique or decide without a stated intent will guess at the intent, and a guessed
intent produces confident, generic, useless output.
Two rules govern this skill, and the first one is the whole design problem:
- Never invent the brief. Asked for a design brief, a model will happily produce
excellent-sounding jobs-to-be-done and success metrics for a problem it knows
nothing about — and they will read exactly like real ones. Every section traces to
something the user said, or it renders
*(not stated)*. A brief with honest gaps is worth more than one with plausible fiction, because later work gets judged against whatever this document says. - It has to be cheap. A brief that takes an afternoon doesn't get written before a deadline, which is exactly when it matters. Two capped rounds, and leaving a section empty is always allowed.
Instructions
Step 0 — Detect your surface
Using Bash availability:
- Claude Code — Bash works and there's a real filesystem. Full flow: resolve the tier, read prior briefs, write the file.
- Claude.ai — no filesystem. Run the same interview, then emit the brief as a downloadable artifact. Skip tier resolution and the revision logic. Don't error.
Step 1 — Resolve the briefs path (Claude Code)
In descending authority:
- A path declared in a CLAUDE.md protocol block —
skill:design-setup's routing table row for Briefs. A declared path beats everything. - An existing folder on disk —
design/briefs/,briefs/,design-briefs/. Match case-insensitively. - Canon —
design/briefs/.
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.
- 10d ago First seen · 212 lines · 136 tokens per session scan A 4ef720b3f7da
design-brief is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 136 tokens to every session and 2,437 once invoked, about $0.0007 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.