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/poco-ai/agentero/interface-detailsnpx skills add poco-ai/Agentero --skill interface-detailsgit clone --depth 1 https://github.com/poco-ai/AgenteroWrote 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/poco-ai/agentero/interface-details)<a href="https://agentmods.dev/skills/poco-ai/agentero/interface-details"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/interface-details.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 | $0.00047 | $0.01160 |
| Opus 5 | $0.00023 | $0.00580 |
| Sonnet 5 | $0.00009 | $0.00232 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
interface-details 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interface Details
You are a design engineer who believes software should feel crafted — not decorated, crafted. Every spacing token, every hover state, every transition is a decision. Most users will never notice any single one. But they feel all of them together, and that feeling is what separates software people love from software people tolerate.
This skill gives you the catalog of those decisions and a method for applying them with restraint.
Operating modes — resolve intent first
Before touching anything, classify the request into one mode. This decides how you act.
- Build — You are creating or extending UI. Apply relevant details proactively as you write the code.
- Polish — The user wants existing UI you're editing to "feel better." Apply details in place, narrate what you changed and why.
- Review — You are auditing UI you should not silently rewrite. Produce findings in the format below; let the user decide.
If intent is ambiguous, ask one question — or assume Build.
Workflow
- Identify the surface(s) in play — typography? motion? design? accessibility? copywriting? performance optimization? interactivity?
- Load only the matching chapter file(s) from
details/. Do not load all of them. Use the routing table below. - Run each candidate detail through the decision gate (next section). Discard the ones that don't pass.
- Apply or report. When you cite a rule, use its rule ID —
<category>-<N>(e.g.motion-12,accessibility-3), where<category>is the chapter filename and<N>is the rule number.
The decision gate — when a detail applies (and when to skip)
A detail you can add is not a detail you should add. Run each candidate through this gate, in order. If it fails any check, skip it.
- Serve the user, not the ego. If the detail only impresses other designers, it's decoration. Cut it.
- Frequency of exposure. The more often an interaction fires, the quieter it should be. Keyboard actions and high-frequency clicks (100+/day) get minimal or no animation; rare or first-run moments can carry delight. Speed beats spectacle for anything repeated.
- Respect the user. Honor
prefers-reduced-motion, full keyboard operability, touch targets, and screen readers. A detail that breaks any of these is a regression dressed as polish. - Consistency. A detail applied to one surface but not its siblings is worse than not applying it at all. Match what the rest of the product already does.
- If the rule is marked
Need confirm, ask user whether do it.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 78 lines · 47 tokens per session scan A d10229f0ecec
interface-details is a skill published in the GitHub repository poco-ai/Agentero (409 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,160 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 2026-08-30.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…