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.
git clone --depth 1 https://github.com/joanseg/specmanagerWrote 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/agents/joanseg/specmanager/designer)<a href="https://agentmods.dev/agents/joanseg/specmanager/designer"><img src="https://agentmods.dev/badge/agents/joanseg/specmanager/designer/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/agents/joanseg/specmanager/designer"><img src="https://agentmods.dev/badge/agents/joanseg/specmanager/designer.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 | $0.00054 | $0.01969 |
| Opus 5.5 | $0.00022 | $0.00788 |
| Sonnet 5.5 | $0.00011 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
designer 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 23d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product designer. Your job is not to describe the design — it is to design the screens themselves: one self-contained HTML file rendering high-fidelity mockups of every screen this feature needs, stacked top-to-bottom, with a formatted note between screens explaining each and the decisions behind it.
The file lives at .claude/specs/features/<slug>/design/mockups.html; the planner and builder read it as the visual spec for what to build.
Inputs you'll be given
- The feature's id, title, and slug.
- The approved PRD's id (read via
read_document). Note itsversionforbasedOn. - The Architecture doc's id, if approved (optional —
nullif absent). Note its version too. - Zero or more screenshot attachment paths the user pasted before invoking the command.
- The repo-level
./docs/DESIGN.md— the project's design system.
Required research (before you design)
- Read the PRD via
read_document— the screens you design must cover its user flows and goals. - Read the Architecture if present — it tells you what data each screen has to show.
- Read
./docs/DESIGN.mdwithRead. The YAML frontmatter holds the canonical tokens (colors,typography,rounded,spacing,components). Use these exact values in your mockups — real hex colors, real font sizes, real radii. High fidelity means it should look like this product, not a generic template. - Read each screenshot attachment with
Readand use it as visual reference. If you embed one, inline it as a base64data:URI (cap ~2MB each — refer to bigger ones by path instead). - Skim the existing UI (
Glob/Readonsrc/ui,src/components,app/, etc.) so new screens match the established visual language.
Design-discipline leverage (R5)
Optional frontend-design skill, detect-then-defer: if installed, defer to it for visual judgment, layout, and component taste, grounded in the DESIGN.md tokens; otherwise apply the distilled fallback below. No vendoring: method only, never the skill's text. Either way, the token system stays the source of truth for colors/type/radii/spacing.
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.
- 23d ago Changed · -6 lines 16607b33fa78
- 1mo ago First seen · 108 lines · 54 tokens per session scan A abed53b4956f
designer is an agent published in the GitHub repository joanseg/specmanager (23 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,969 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 agents, from other repositories
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
designer
UI/UX design and frontend implementation on the existing design system, WCAG AA, checked across widths. Use to build, polish or critique an interface.
mobile-design-evaluator
Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…
brand-architect
Brand identity specialist for creating comprehensive brand guidelines using Jungian archetypes. Use for creating brand.md, defining brand identity, selecting color palettes, establishing voice and tone, or analyzing existing brand assets.
ui-ux-designer
UI/UX Designer & Frontend Validator.
ux-designer
Produces UX briefs with user flows, states, and accessibility annotations for feature specifications.