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 joenandez/spectre --skill spectre-uxgit clone --depth 1 https://github.com/joenandez/spectreWrote 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/joenandez/spectre/spectre-ux)<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-ux"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-ux/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/joenandez/spectre/spectre-ux"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01350 |
| Opus 5 | $0.00024 | $0.00675 |
| Sonnet 5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
spectre-ux 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ux
Turn requirements into a behavioral spec — what users see/do and the system response, not visual taste. Align flows, then write ux.md.
Inputs
$ARGUMENTS— explicit feature name/root or descendant requirements artifact.- Requirements — first present, read fully:
{OUT_DIR}/concepts/scope.md(canonical, preferred){OUT_DIR}/specs/prd.md{OUT_DIR}/task_summary.md
- If none exist → ask for scope context or recommend
spectre-scopefirst; do not invent scope.
Working Set (late-bound — read at run-time, never inline)
- Reuse a managed
FEATURE_ROOTonly when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and followSkill(spectre-feature-root)through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged. - Repair stale feature/root metadata in artifacts this workflow touches.
OUT_DIR = FEATURE_ROOT.- Existing UI: one Stage-1
@spectre_patternsdispatch for similar screens/tokens — ≤~2K in-thread, no files.
Method / guardrails
Stage 1 — Flow discovery & alignment (align before specifying).
- Identify user segments: first-time/returning, anon/signed-in, free/paid, role-based.
- Identify goals, entry points, and completion states.
- Narrate each flow: Goal · Entry · User sees → User does → System responds · branches · success · Questions; call out segment divergence.
- Present a take and ask for pushback. Every initial or feedback-revised flow presentation ends with the compact handoff table:
| Handoff | Details |
|---|---|
| 🧭 Current phase | Flow approval. |
| 📦 What was just done | Initial or revised flows. |
| ▶️ Proposed next step | Render resolved action. |
CONTINUATION: Prototype when interaction, layout, visual validation, or stakeholder review materially matters; otherwise Plan when Scope + flows suffice. Renderspectre-prototype {FEATURE_ROOT} FROM_UX=trueorspectre-plan {FEATURE_ROOT}; at most one explicit conditional alternative.- Flows approved: complete {OUT_DIR}/ux.md, then Prototype or Plan with resolved values.
- GATE: Never write
{OUT_DIR}/ux.mdbefore explicit flow approval + selected continuation. Feedback without approval → revise and re-present. Ambiguous approval or missing route authority → ask only the unresolved choice.
What ships with it
1 file 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.
- yesterday Changed · +7 lines · -52 tokens per session 9d17fbac3b27
- 6d ago Changed 862dab2228c4
- 11d ago First seen · 88 lines · 100 tokens per session scan A 4f9354951d74
spectre-ux is a skill published in the GitHub repository joenandez/spectre (161 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,350 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.