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/roshaw/claude-translation-agencyWrote 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/roshaw/claude-translation-agency/translate)<a href="https://agentmods.dev/commands/roshaw/claude-translation-agency/translate"><img src="https://agentmods.dev/badge/commands/roshaw/claude-translation-agency/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/commands/roshaw/claude-translation-agency/translate"><img src="https://agentmods.dev/badge/commands/roshaw/claude-translation-agency/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 | $0.00202 | $0.10286 |
| Opus 5.5 | $0.00081 | $0.04114 |
| Sonnet 5.5 | $0.00040 | $0.02057 |
| Haiku 4.5 | $0.00020 | $0.01029 |
Grade A, and why
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 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 — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.
translate
The single entry point for translating anything — a whole codebase's i18n, a WordPress theme/plugin's gettext catalog, a folder of Markdown docs, a batch of JSON files, a subtitle file — into any set of target languages. It drives the three-tier translator panel and applies a domain specialization so terminology is right for the material.
The panel (why three tiers)
- Lead (
translate-lead, Opus) — orchestrates the run, dispatches each batch to a worker, and adversarially reviews every result against a fixed C1–C7 checklist before signing off. Runs the final blind-spot sweeps. Loads the specialization module so its terminology check is domain-aware. - Senior (
translate-senior, Sonnet) — translates domain-prose and any substantive surface. Spawned by the Lead, not directly by this skill. - Junior (
translate-junior, Haiku) — translates only low-risk UI chrome. Spawned by the Lead.
This skill computes the scope + per-batch tier classification, then spawns the Lead once; the Lead handles all worker spawns and reviews. The single final build/verify runs here (Step 6).
Invocation
/translate # translate the changed-since-last-run set into the configured targets
/translate --path <dir> # point at a project/folder on disk, e.g. --path C:\Projects\MyApp
/translate <path> # shorthand for --path <path> (a folder) or --files <path> (a file/glob)
/translate --to <langs> # e.g. --to de,fr,pt-BR (overrides configured targets for this run)
/translate --from <lang> # override the detected/configured source language
/translate --domain <name> # specialization: general | technical | marketing | legal | finance | medical | ecommerce | travel | government | scientific | <custom> (default from config, else general). Layer with a comma-list: --domain technical,finance (first = primary)
/translate --formality <f> # register for the whole run: formal | informal | auto (overrides config.formality; default auto)
/translate --files <glob|paths> # translate an explicit set (a folder, a glob, named files)
/translate --out <mode> # output layout: inplace (default) | tree | catalog (see Step 0.5)
/translate --full # translate the ENTIRE translatable surface, not just the diff
/translate --no-gates # skip the project gates (config.gates) for this run (see Step 6.7)
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 · 579 lines · 202 tokens per session scan A 06e0151112e1
translate is a command published in the GitHub repository roshaw/claude-translation-agency (2 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 10,286 once invoked, about $0.0008 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 2026-09-16.
Other commands, from other repositories
start
Run a parallel persona-swarm brainstorm on a topic. Spawns 4-8 persona-distinct subagents in parallel, synthesizes their outputs into consensus / dissent / open questions / recommended next move.
audit
Audit closed tickets for regressions against today's code (unchanged, evolved, implemented wrong, not implemented), plus duplicate and groupable open ones.
pr
Take the current branch from uncommitted work to an open pull request: commit outstanding changes with the git-commit rules if asked, push with upstream tracking, write the PR title and body with the pr-description skill from the full branch diff, link the issue, and open it with gh against the right base. Confirms…
plan-localization
Plan localisation covering extraction, translation workflow, and the layout and format issues that follow.
support-model
Write a support model as Markdown in the user's repository. Produce designed HTML or PDF only when asked.
design-doc
Write a design doc / RFC as Markdown in the user's repository. Use when invoked as /document-design-system:design-doc. Produce designed HTML or PDF only when asked.