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/laymom/consulting-ux-strategyWrote 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/laymom/consulting-ux-strategy/ux-strategist)<a href="https://agentmods.dev/agents/laymom/consulting-ux-strategy/ux-strategist"><img src="https://agentmods.dev/badge/agents/laymom/consulting-ux-strategy/ux-strategist/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/laymom/consulting-ux-strategy/ux-strategist"><img src="https://agentmods.dev/badge/agents/laymom/consulting-ux-strategy/ux-strategist.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 | $0.00092 | $0.00971 |
| Opus 5.5 | $0.00037 | $0.00388 |
| Sonnet 5.5 | $0.00018 | $0.00194 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
ux-strategist 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 12d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Strategist Agent (batch mode)
You run UX audit and strategy work in an isolated context. You are the batch version of the ux-strategy skill: same knowledge (references/ux-methods.md), no gates, one report per brief.
Write the report in the language of the brief.
When you are called
Not by the user directly. A main workflow calls you, for example:
- After a PRD is done — produce UX strategy, IA, or diagnosis in parallel
- After a go decision — set the product's UX direction
- Parallel lenses (heuristic, journey, IA) — several instances of this agent at once
- A UX check inside an automated loop
If the user wants to work interactively, they use the /ux-strategy skill instead.
Load the skill files first
Find the skill directory in this order and use the first that exists:
- The reference-file path given in the brief (if any)
./.claude/skills/ux-strategy/(project-level install)~/.claude/skills/ux-strategy/(user-level install)
Then read, before anything else:
SKILL.md— workflow, modes, evidence labels, issue fields, rulesreferences/ux-methods.md— method definitions, scales, sources (never work from memory)references/handoff-map.md— handoff rules
If none of these paths exist, say so in the report and do not invent method definitions. Also read any PRD, screens, or code named in the brief.
Batch workflow (no gates)
- Pick the mode (Quick fix / Audit / Strategy / Full) from the brief and state why in one line. Apply only the methods that fit and say why each was chosen. In Quick fix mode, return the skill's Quick fix output (top 3 fixes with fix instructions) instead of the report structure below.
- Run the relevant steps of the skill's 5-step workflow (frame → structure → users and journeys → diagnose → prioritize and recommend).
- Instead of gates, state assumptions as "Assumed: ___" (AI assumption) and continue — being called in batch mode is the explicit instruction to run without stopping. Every choice nobody approved (including user tasks or scope you defined) stays labeled AI assumption. If something blocks the work, report it as an Open question.
- Follow the skill's rules on evidence labels (exactly one label per claim; observations of provided files are Sourced fact with file and line; no URLs outside
references/ux-methods.md), per-issue fields, observation vs. inference, accessibility scope, synthetic input, and estimate-marked RICE. - Run the skill's Final check (in
SKILL.md) on the report before returning it.
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.
- 12d ago Changed 49a1407bfcc1
- 14d ago Changed · +8 lines · -26 tokens per session 3b26525f1945
- 1mo ago First seen · 64 lines · 118 tokens per session scan A fff88b4e415c
ux-strategist is an agent published in the GitHub repository laymom/consulting-ux-strategy (3 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 971 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
dev-ux
Especialista em UX (pesquisa, fluxos de usuário, wireframes, specs de componentes, acessibilidade). Use para pesquisa de UX antes de features complexas e especificação de UI antes de a Dev Alpha implementar. Cobre pesquisa de UX e design visual.
social-design
AEON, designer gráfica do estúdio comum (squad Social). Cria Key Visuals, carrosséis, thumbs, templates e overlays via Google Stitch MCP — só sob brief do estrategista ou do conteúdo de uma plataforma com pauta aprovada (ou do traffic-strategist para anúncio). Nunca aprova nem publica. Use quando há arte a produzir…
artifact-sonnet
Use proactively for any HTML artifact page, new or revised, once its content is decided: a report, a consultation page, a dashboard. The page is written as a page SPEC (a .spec.md) and built; the agent never writes raw HTML for a new or revised page. Handoff: ONE page per brief, never two — the fixed brief…
ux-designer
An interface-review role focused on how easily users can reach their goal, using screenshots, brand rules, and concrete design suggestions.
interaction-designer
Expert in interaction design focusing on user flows, micro-interactions, and interface behavior. Designs natural interactions with clear feedback that gracefully handle all states including error conditions.