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 agentmods add skills/lenxism/ives/tacticsnpx skills add lenxism/ives --skill tacticsgit clone --depth 1 https://github.com/lenxism/ivesWrote 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/lenxism/ives/tactics)<a href="https://agentmods.dev/skills/lenxism/ives/tactics"><img src="https://agentmods.dev/badge/skills/lenxism/ives/tactics.svg" alt="Measured on agentmods" 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 | $0.00127 | $0.01054 |
| Opus 5 | $0.00063 | $0.00527 |
| Sonnet 5 | $0.00025 | $0.00211 |
| Haiku 4.5 | $0.00013 | $0.00105 |
Grade A, and why
tactics 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tactics
Practical workflow tactics for executing design projects effectively.
The No-Stress Design Process
Don't start with a blank canvas and pray. Follow this:
-
Ask questions. Anything you can't confidently explain about the project means you're not equipped to design it. Know the stakeholders, who has final call, colors off-limits, what they hate about current design.
-
Determine direction. Based on what you've learned, experiment with typefaces, color moods, adjectives. Mock up the same component in 3-4 different type treatments. Typography sets the tone for everything.
-
Focus on components, not pages. Design the navigation, a card, a button, a header background — in abstract. Not a full homepage. These pieces establish the visual language without the pressure of a complete layout.
-
Have conversations, not presentations. Share early and often. "Here's a direction we could take" beats "here's the final design." Get gut reactions. Paint a picture of what could be, not what is.
This builds trust incrementally and avoids the terrifying big reveal that risks total rejection.
Low Fidelity Design
When to wireframe
- Project is big and complex with lots of moving parts
- Team is large with multiple stakeholders
- Functionality isn't clear yet
- You need developer input on feasibility before investing in visual design
When NOT to wireframe
- Solid UI foundation already exists (you're extending, not creating)
- Functionality is straightforward
- You're doing a visual refresh on existing structure
- Time is extremely limited and the scope is clear
How to do it well
- Call them "low fidelity designs" not "wireframes" — less baggage
- Use a vanilla system: one typeface, black/white/gray/one blue accent
- Make primary actions unmistakable (blue, bold, black borders if needed)
- Focus on layout, functionality, and flow — save typography/color/style for later
- Spend as little time as possible while gaining ground on functionality decisions
- Transition to high fidelity once the team agrees on what the thing does
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.
- 4d ago First seen · 100 lines · 127 tokens per session scan A 6a3b6bf38804
tactics is a skill published in the GitHub repository lenxism/ives (5 stars, last pushed 6mo ago), licensed MIT. It adds 127 tokens to every session and 1,054 once invoked, about $0.0006 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
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
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.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.