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 devforth/adminforth --skill adminforth-i18n-staticgit clone --depth 1 https://github.com/devforth/adminforthWrote 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/devforth/adminforth/adminforth-i18n-static)<a href="https://agentmods.dev/skills/devforth/adminforth/adminforth-i18n-static"><img src="https://agentmods.dev/badge/skills/devforth/adminforth/adminforth-i18n-static/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/devforth/adminforth/adminforth-i18n-static"><img src="https://agentmods.dev/badge/skills/devforth/adminforth/adminforth-i18n-static.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 | $0.00044 | $0.00707 |
| Opus 5.5 | $0.00018 | $0.00283 |
| Sonnet 5.5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
adminforth-i18n-static 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdminForth Static Translations Workflow
How Translations Work
- Every supported language has its own flat JSON file
<translationsDir>/<language code>.json(langs/by default), e.g.langs/uk.json,langs/pt-BR.json. - Keys are original English strings from admin UI, values are translations:
{ "Save": "Зберегти" }. - Empty value means "not translated yet", admin shows the original English key instead.
- Files are read on every request, so edits are visible after page reload without restart.
Workflow
- Sync keys first, so every language file contains all actual keys:
pnpm exec adminforth-i18n-static sync(ornpx adminforth-i18n-static syncfor npm). It prints every language file with counts:total,added,staleanduntranslated. - Fill empty values in language files the user asked for (all non-English files if not specified).
- Run sync again and make sure
untranslatedis 0 for translated files and there is nowrong pluralwarning. Fix every listed plural string.
Translation Rules
- Never change, add or remove keys, only write values. Keep keys order.
- Do not translate
en.json: sync fills its values with the keys (original English strings). Change its values only if the user asks to rephrase English texts. - Do not touch non-empty values unless the user asks to fix them.
- Do not remove stale keys (reported as
stale), the user decides about them. - Keep variables in curly brackets exactly as in the key and do not translate them:
"Hello {name}"→"Привіт {name}", never{ім'я}. - Keys with
|are plural forms. Keep the same number of forms separated by|, except Slavic languages (uk, ru, be, pl, cs, sk, bg, sr, hr, mk, sl) which need 4 forms "zero | singular | 2-4 | 5+", e.g."apple | apples"inuk.jsonbecomes"яблук | яблуко | яблука | яблук". - For codes with region (e.g.
pt-BR) use regional spelling, punctuation and formatting. - Keep translations short: they are UI labels, buttons and messages of an admin panel.
- If meaning of a key is not clear (short words like
Show,of,to,Youror sentence fragments), find where it is used: search for the key in$t('...')/t('...')calls in project custom components and in AdminForth sources (node_modules/adminforth/dist/spa/src,node_modules/@adminforth/*/dist/custom). Translate by context: a button, a label or a part of a sentence glued with other text in the template, then the translation must fit the whole phrase. - Keep JSON valid with 2 spaces indentation.
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 · 41 lines · 44 tokens per session scan A 723be702d5b4
adminforth-i18n-static is a skill published in the GitHub repository devforth/adminforth (394 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
ctx
A project-context tool for recording important lessons about bugs and failure-prone code in nearby AGENTS.md documents. These documents give coding agents repository-specific guidance.
add-backend
Everything about the data layer — pick one of six ready-to-run backend templates (TanStack Start + Drizzle + better-auth, Hono + Drizzle + better-auth, Hono + Prisma + better-auth, Hono + Drizzle + Auth.js/NextAuth, FastAPI + SQLAlchemy + JWT, Supabase) and wire the frontend to it through the Repository + AuthProvider…
scaffold-dashboard
Stand up the dashboard foundation (the platform layer — UI primitives, form system, charts, Repository + adapters, auth seam, theme, routing shell) into a new project as a zero-config runnable app. Run this FIRST when building a dashboard, then compose screens from the add-component catalogue's shapes…
add-component
Add a copy-ready admin UI building block to a dashboard built on the scaffold-dashboard base — forms (form, wizard, combobox, file upload, inline edit), lists & tables (CRUD list, card grid, infinite/virtual, column controls, filter panel, saved views, CSV export/import), rich views (kanban, calendar, tree, timeline…
rebrand
Rebrand the app — change the product name, logo, description, theme, and navigation. Use when porting this template into a new product.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.