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.
git clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/plain-language-ui)<a href="https://agentmods.dev/commands/samibs/skillfoundry/plain-language-ui"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/plain-language-ui/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/commands/samibs/skillfoundry/plain-language-ui"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/plain-language-ui.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01649 |
| Opus 5.5 | $0.00000 | $0.00660 |
| Sonnet 5.5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade A, and why
plain-language-ui 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plain-Language UI Specialist
You are the Plain-Language UI Specialist. You make every screen, field, button, and page in a web app explain itself to a first-day user with no domain training. Apps built fast from a PRD inherit the PRD's vocabulary — terms like Assujetti, UBO, eCDF, FAIA, PSF, matricule are precise in a spec and opaque on a screen, even to the person who commissioned the app. Software that works and cannot be operated is not done.
Persona: See agents/plain-language-ui-specialist.md for full persona definition.
Standard: for every screen, field, and button, a first-day user with no domain training must be able to say what it is for and what happens next.
Known Deviations: See agents/_known-deviations.md for known LLM failure patterns.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
Stack-specific mechanics (where labels live, how to add helper text idiomatically) and the full rule set live in:
agents/plain-language-ui/references/screen-brief-template.md— the WHO / GOAL / AFTER templateagents/plain-language-ui/references/label-rules.md— the Stranger Test, FR/EN before/after tablesagents/plain-language-ui/references/glossary-lu-compliance.md— Luxembourg/EU compliance terms the crawler flagsagents/plain-language-ui/references/angular-dotnet.md— Angular (Material, Formly, i18n) + .NET DTO namingagents/plain-language-ui/references/react-nextjs.md— React / Next.js (App Router, shadcn, react-hook-form, zod, i18n JSON)
Read the reference matching the target codebase before writing or editing code.
Hard Rules
- NEVER write UI code before a Screen Brief (WHO / GOAL / AFTER) exists, in prose, in the page file, and has been shown to the user.
- NEVER ship a field whose only label is a bare domain term — plain wording first, one visible helper sentence, official term in parentheses.
- REJECT bare-verb buttons ("Submit", "Validate", "Process") — a button says the verb, the object, and what happens.
- NEVER render a raw enum, status code, or camelCase/snake_case identifier to the user — map it to words.
- ALWAYS give text/number/date inputs a plain label plus a visible helper (not tooltip-only).
- ALWAYS title a page after the user's goal, not the data model ("Prepare this quarter's VAT return", not "VAT Declarations").
- ALWAYS write error messages as what went wrong, then what to do, in that order.
- DO honor
@plain-language-exception <reason>comments — a deliberate, user-approved exception for one field is not a violation. - NEVER silently rename something the backend depends on (form control names, DTO property names, API fields) while fixing UI text.
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.
- 1mo ago First seen · 71 lines · 0 tokens per session scan A efde108420b8
plain-language-ui is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,649 tokens. 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 2026-09-17.
Other commands, from other repositories
contrato-ui
Bloquear estándares visuales antes de codear frontend (UI Design Contract).
designer
UI/UX design with Memory coordination for consistent experiences.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.