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 Ljhhhhhh/user-facing-only-skill --skill user-facing-onlygit clone --depth 1 https://github.com/Ljhhhhhh/user-facing-only-skillWrote 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/ljhhhhhh/user-facing-only-skill/user-facing-only)<a href="https://agentmods.dev/skills/ljhhhhhh/user-facing-only-skill/user-facing-only"><img src="https://agentmods.dev/badge/skills/ljhhhhhh/user-facing-only-skill/user-facing-only.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 5.1 | $0.00064 | $0.00521 |
| Opus 5 | $0.00032 | $0.00260 |
| Sonnet 5 | $0.00013 | $0.00104 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
user-facing-only 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 7d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-Facing Only
Build the latest authorized deliverable for its intended users. Construction instructions may guide implementation, but do not become user-facing content.
Method
- Identify the finished artifact, its intended audience, the audience's task, the intended use context, and the latest authorized requirements.
- Separate target content from construction context. README notes, seed or fixture data, mock mechanisms, presenter guidance, implementation constraints, and test setup do not become product copy merely because they are true.
- Build or review only the authorized target. Implement constraints as behavior instead of narrating them in the artifact.
- Inspect the result as an intended user in the intended use context who never saw the construction conversation. Do not substitute an arbitrary recipient, detached screenshot, or hypothetical misuse for the authorized audience and context.
Disclosure gate
A visible disclosure is authorized only when at least one of these is established:
- the user or current product requirement explicitly requests it;
- a concrete legal or safety obligation requires it; or
- omitting it would materially mislead the intended audience in the intended use context.
Provenance alone does not authorize visible attribution. In particular, knowing that data, identities, endpoints, or workflows are seeded, mocked, fictional, or prepared for a demonstration does not by itself justify labels such as demo, sample data, mock, or fictional in the product or export. When the authorized target is a realistic prototype or simulation, preserving the real business presentation is part of the target.
Before reporting a missing-disclosure finding, identify the authorizing requirement or obligation, the affected intended audience, and the concrete material harm caused by omission. If those cannot be established, do not report the absence as a defect. Do not promote developer-facing README statements, fixture metadata, or implementation facts into user-facing requirements.
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.
- 7d ago First seen · 34 lines · 64 tokens per session scan A eef5346e34d1
user-facing-only is a skill published in the GitHub repository Ljhhhhhh/user-facing-only-skill (2 stars, last pushed 7d ago), licensed MIT. It adds 64 tokens to every session and 521 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
control-ui
Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. Use for UI regressions, screenshots, accessibility snapshots, visual diffs, focus, keyboard, scrolling, resize, console, network, performance, or heap checks. Do not use for backend-only changes or for a screenshot without…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
blocked-page-recovery
Use when a fetch fails: 403/429, paywall, WAF, bot wall.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…