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/lyymuwu/TokTransnpx agentmods add skills/lyymuwu/toktrans/token-saverWrote 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/lyymuwu/toktrans/token-saver)<a href="https://agentmods.dev/skills/lyymuwu/toktrans/token-saver"><img src="https://agentmods.dev/badge/skills/lyymuwu/toktrans/token-saver/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/lyymuwu/toktrans/token-saver"><img src="https://agentmods.dev/badge/skills/lyymuwu/toktrans/token-saver.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 | $0.00038 | $0.00288 |
| Opus 5 | $0.00019 | $0.00144 |
| Sonnet 5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
token-saver 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 12d 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.
What it actually says
TokTrans
TokTrans provides a local wrapper command, codex-ts, that keeps the official codex installation untouched.
Use it when:
- The user wants prompts in any natural language translated to English before Codex CLI receives them.
- The user wants final Codex answers translated back to their original language.
- The user asks to diagnose or safely uninstall the wrapper.
Important behavior:
codex-ts execis the reliable path. It captures the final assistant message with--output-last-message, translates only that final message, and preserves the original exit code.- Interactive TUI mode translates only the initial prompt and injects final-answer language guidance. Live streamed output filtering is best-effort until Codex exposes stable final-output hooks.
- If translation fails, the wrapper falls back to raw
codex. - The installer never overwrites official Codex binaries or unmanaged user files.
Typical commands:
./scripts/install.sh
codex-ts doctor
codex-ts exec "请帮我检查这个仓库的测试失败原因"
codex-ts exec "Por favor revisa por que fallan las pruebas"
./scripts/uninstall.sh --dry-run
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.
- 12d ago First seen · 32 lines · 38 tokens per session scan A 361832b8638b
token-saver is a skill published in the GitHub repository lyymuwu/TokTrans (4 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 288 once invoked, about $0.0002 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
pm-bilingual-copilot
Create concise bilingual Vietnamese-English product management artifacts and translate PM context accurately across both languages. Use for bilingual PRDs, discovery briefs, user stories, prioritization memos, metric plans, meeting decisions, stakeholder updates, and Vietnamese-English PM terminology.
azure-translator
Expert knowledge for Azure Translator development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using translate/detect/dictionary APIs, Custom Translator, glossaries, document jobs, or Docker containers…
pdlc-i18n
An internationalization workflow for adding multiple languages to frontend and backend software. Internationalization, often called i18n, means keeping user-facing text and formatting adaptable to different languages and regions.
azure-immersive-reader
Expert knowledge for Azure AI Immersive Reader development including best practices, limits & quotas, security, configuration, and integrations & coding patterns. Use when tuning read-aloud/translation, storing user prefs, Entra auth setup, JS SDK integration, or language support, and other Azure AI Immersive Reader…
global-data-post-resolve
Resolve an address or coordinates into a full location profile — city, country, timezone, UTC offset, current time, working days this month, and next holiday.
ios-appstore-release-manager
Prepare, validate, localize, and safely fill App Store Connect release metadata from project Markdown forms. Use when creating a new iOS release form, drafting or translating descriptions, promotional text, localized keywords, and What's New, checking App Store character limits or model names, binding an uploaded…