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 ariadoss/superskills --skill relationship-designgit clone --depth 1 https://github.com/ariadoss/superskillsWrote 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/ariadoss/superskills/relationship-design)<a href="https://agentmods.dev/skills/ariadoss/superskills/relationship-design"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/relationship-design/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/ariadoss/superskills/relationship-design"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/relationship-design.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 | $0.00046 | $0.00639 |
| Opus 5 | $0.00023 | $0.00319 |
| Sonnet 5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
relationship-design 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic UX Design — Relationship-Centric Interfaces
Design framework for AI-first interfaces that build ongoing partnerships, not isolated session interactions.
Core Shift
Traditional UX optimizes for sessions. Relationship-centric UX optimizes for sustained partnerships.
"Every interaction builds on learned preferences and user history. Systems don't just respond — they develop understanding that compounds over time."
Five Pillars
1. Memory Revolution
Moving beyond static preferences to capture:
- Behavioral patterns across sessions
- Emotional context (frustration, delight, confusion patterns)
- Temporal evolution (how needs change over time)
- Implicit signals (what users skip, ignore, repeat)
Design for: "What would this system know about the user after 3 months?"
2. Trust as Design Material
Three-stage trust model:
- Transparency — system shows all reasoning, asks permission
- Selective Disclosure — system explains only when deviating from expectations
- Autonomous Action — system acts independently with clear recovery paths
Design for: trust that can be inspected, corrected, and rebuilt.
3. Relationship-Centric Architecture
Maintain continuous awareness of:
- User goals (not just current task)
- Communication patterns (terse vs. exploratory)
- Historical preferences
- Outstanding commitments
Design for: context that doesn't reset between sessions.
4. Dynamic Path Planning
Systems that construct workflows aligned with individual objectives:
- "What is this user actually trying to accomplish?"
- Adaptive suggestions based on observed patterns
- Proactive surfacing of relevant information
5. New Success Metrics
Replace traditional metrics with:
- Relationship quality: does the system understand the user better over time?
- Compounding value: does each interaction make future interactions more valuable?
- Context accuracy: is stored understanding correct and current?
- Democratic alignment: does the system serve the user's actual goals, not engagement goals?
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.
- 9d ago First seen · 82 lines · 46 tokens per session scan A 40862c05ca82
relationship-design is a skill published in the GitHub repository ariadoss/superskills (9 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 639 once invoked, about $0.0002 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
user-context
Load or manage Product Design's saved user context. Use when the user asks to set up Product Design, get started, onboard, save product or design sources, see what Product Design remembers, update saved context, or remember Product Design preferences. Examples include product URLs, Figma files, screenshots, reference…
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
ui-craft
Design, build, redesign, or modify browser-visible web interfaces with product-quality composition, visual systems, interaction states, responsive behavior, accessibility, and browser visual QA. Use for HTML, CSS, JavaScript, React, Vue, or Svelte pages and components, landing pages, dashboards, admin tools, settings…
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…
memoire-design-tooling
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
design-memory
Use at project start and completion to OBSERVE and record how the user designs — the decisions they make, the styles they reach for, their habits and inclinations across projects. This is a descriptive record (a mirror), NOT a controller — it is never fed back to steer the work. Per-project direction comes from…