Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/adaptocms/adapto-cms-agent-skillsnpx agentmods add skills/adaptocms/adapto-cms-agent-skills/adapto-translateWrote 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/adaptocms/adapto-cms-agent-skills/adapto-translate)<a href="https://agentmods.dev/skills/adaptocms/adapto-cms-agent-skills/adapto-translate"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-translate/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/adaptocms/adapto-cms-agent-skills/adapto-translate"><img src="https://agentmods.dev/badge/skills/adaptocms/adapto-cms-agent-skills/adapto-translate.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 | $0.00064 | $0.02544 |
| Opus 5 | $0.00032 | $0.01272 |
| Sonnet 5 | $0.00013 | $0.00509 |
| Haiku 4.5 | $0.00006 | $0.00254 |
Grade A, and why
adapto-translate 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adapto:translate
Translates existing content into another already-enabled language, linked to the source via
translation_of_id. A structural-parity gate prevents broken translations (lost paragraphs, dropped
markup/media, mangled placeholders). Works single-item or across a corpus.
Model tier (hard rule): the translation step runs at the top tier (Opus-class) — lower tiers silently destroy meaning (§7 / sub-agents.md). If the current session/sub-agent can't run at the top tier, warn and stop; never translate at a lower tier.
When to use
- "Translate this article/page into
<lang>", "localize my site into<lang>", "translate the blog corpus". - After source content exists (e.g. from
adapto:content-seed) and the target language is enabled on the tenant.
When not to use
- Adding/enabling a new language — that's
adapto project update --languages(a project setting, and a replace-not-append one — conventions §5), not this skill. Translate only into already-enabled codes. - Creating source content →
adapto:content-seed. - Just checking the environment →
adapto:doctor.
Inputs
- Source item(s) by id or slug (
get/get-by-slug/list). - Source + target language. The target must be enabled on the tenant — discover via
adapto auth orgs --json; an unsupported target → stop and offer to enable it as a separate, confirmed step (adapto project update --languages <existing + new>— conventions §5). Never enable one mid-run. - Glossary
_adapto_glossaryif present (cache to.adapto/glossary.md) — its terms/brand names are preserved verbatim. Optional; proceed without if absent (note it wasn't applied). - Project context (
.adapto/project.md/_adapto_project_config) for voice consistency. - Mode: single-item (
<type>+ id/slug) or corpus (<type>+ filter, e.g.--status published).
Outputs
- Translated entries created via
create-translation(linked bytranslation_of_id,slug = source slug). - A local per-language draft at
.adapto/drafts/<YYYY-MM-DD>-<slug>.<lang>.md(frontmatter withlanguage+translation_of, and the translated body) — the reviewable file artifact, matching howcontent-createwrites originals so a translation isn't reviewable only in the CMS. - For pieces that have one, a target-language
_adapto_seoitem (meta/OG/JSON-LD localized), and the ledger updated (pieces[].translations[<lang>]). - A report of written + skipped (with parity-failure reasons). Article translations carry
ai_generatedprovenance. - Next step: suggest reviewing the per-language drafts (the local md or the dev server), then
adapto:publishto take them live. Offer to translate into another enabled language too.
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.
- 10d ago First seen · 145 lines · 64 tokens per session scan A 32651f110487
adapto-translate is a skill published in the GitHub repository adaptocms/adapto-cms-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,544 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
paper-translation
Use when translating academic papers (PDF to Chinese Markdown), extracting PDFs with MinerU API, or needing to preserve LaTeX formulas/images/tables through a translation workflow.
hreflang-international
International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…
zh-tw
Rewrite the previous reply in Traditional Chinese.
invest
First-time fork users: run the invest-setup skill first to initialize. The main flow lives in this skill (the AI agent uses the CLI/MCP to view the portfolio / run the committee / replay decision history). The Web GUI has been retired (2026-07) — every capability is exposed via CLI subcommands / MCP tools. The backend…
invest-setup
A first-time setup workflow for openInvest, a system for tracking investments and running portfolio analysis.
okf-frontmatter
Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schemasource, documents); schema details link…