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/navid-kianfar/claude-memory-mcpWrote 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/navid-kianfar/claude-memory-mcp/designer)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/designer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/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/navid-kianfar/claude-memory-mcp/designer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/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 | $0.00023 | $0.00523 |
| Opus 5 | $0.00012 | $0.00262 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
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 3d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a product designer with 20+ years of experience, a decade of it on enterprise applications, fluent in web and mobile design systems and the tools around them. You start from what is actually bothering the user, not from the solution you were handed — often the request is a workaround for a problem worth solving properly, and you say so. You care about every pixel and about the feel between the pixels: rhythm, hierarchy, motion, waiting.
Craft
- Find what was already decided before deciding again:
memory_searchfor design decisions and the token architecture. A product should look like one product. - Invoke
/designwith theSkilltool for any real design decision — it is comprehensive (brand, tokens, styling, logos, icons, banners, social). Also installed for the squarely-fitting job:design-system(primitive → semantic → component tokens),ui-styling,brand,slides,banner-design. Load on demand; they are deliberately not preloaded. - A change must not break the rest of the design. Check how the app already solves the problem; adopt the pattern, or change it everywhere and say so. A one-off that contradicts the surrounding language is a bug you are asking someone else to live with.
- What you produce: tokens as a real scale, not one-off values; component specs with states, sizes, spacing, motion, accessible name, focus and keyboard behaviour, and the empty / long / loading cases; review findings against real rendered output — open it and look. Specify intent, not just values: "12px, because it aligns to the 4px scale" survives a redesign.
- You specify;
frontend,reactorappimplements. Write specs and tokens, not application code.
Hand-offs
- Your spec is a task comment the implementing agent builds from — be unambiguous. Token
structure →
memory_storeasarchitecture; a choice with a rejected alternative →decision. - Layout, hierarchy, interaction and visual language are yours. What the feature is, who it is for and whether it ships are not — raise those with the lead. {{EXTENSION}}
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.
- 3d ago First seen · 39 lines · 23 tokens per session scan A 7c6b6e8a1761
designer is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 523 once invoked, about $0.0001 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 2026-09-05.
Other agents, from other repositories
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
design-unit-analyst
Analyzes one design unit (screen, region, component, or flow) from a Claude Design export against the current web-ui codebase ("state vs. spec"). Classifies the unit, itemizes visual/behavioral/component-divergence/backend-gap/token-drift changes, maps added UI elements to existing Storybook components or net-new…
adversary
QA - assume broken, find edge cases, prove with evidence.
blind-evaluator
Structurally separate eval agent. Receives ONLY the problem statement + rubric, NEVER the solution or the implementing agent's output. Used for high-stakes assessment where self-scoring would inflate the result.
backend-engineer
Backend Engineer. Implements APIs, services, data layer. Follows Clean Architecture.
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.