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/tiltely/lens/usabilitynpx skills add Tiltely/lens --skill usabilitygit clone --depth 1 https://github.com/Tiltely/lensWhat 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 | $0.00068 | $0.00901 |
| Opus 5 | $0.00034 | $0.00451 |
| Sonnet 5 | $0.00014 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
usability 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 2d 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.
The Lens of Usability
Read first: ${CLAUDE_PLUGIN_ROOT}/core/protocol.md and ${CLAUDE_PLUGIN_ROOT}/core/dossier.md. Dossier rules: read it, skip answered questions WITH skip lines, append your outputs.
Mode selection
- Explicit argument wins ("audit" / "design").
- Otherwise infer: planning a new page/flow → design; reviewing one already built → audit. Confirm your inference in one line.
Question battery — design mode
Tier 1 — framing (always)
- Walk me through how the user ACTUALLY ends up on this page — from where, in what state of mind, on what device? (If the walk-through stalls, that IS the finding.)
- What does the user want to leave with — and how many steps does that take today?
Tier 2 — flow and navigation
- From this page, where can the user go next — and is every likely "next" reachable without using the browser back button?
- What is missing: is there an action users will look for here that has no button? (The test: narrate the user's inner monologue — "ok, and now how do I…?")
- For each async action: what does the user see while waiting, on success, and on failure? (loading / success feedback / error recovery — name all three.)
- First-time user vs returning user: do both make sense of this page? Does the first-timer need an empty state that teaches?
Tier 3 — reach (only when triggered)
- Real users speak multiple languages → do we need i18n here, and in which languages? Who maintains translations? (Per Tiltely: neutral tú-form Spanish when Spanish.)
- Feature exists on web AND mobile → does the flow match on both? Intentional divergences documented? (This question is the seed of the future parity lens.)
- Forms → can it be completed one-handed on a phone? Are inputs the right keyboard type?
Output contract — design mode
decisions[] · risks[] · open[] · blast-radius notes (e.g., "i18n decision touches email templates too"). Append to dossier.
Question battery — audit mode (critique the built flow)
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.
- 2d ago First seen · 78 lines · 68 tokens per session scan A 2dab1246f315
usability is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 23d ago), licensed MIT. It adds 68 tokens to every session and 901 once invoked, about $0.0003 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
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.