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/Zts0hg/codexspecWrote 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/zts0hg/codexspec/translate-docs)<a href="https://agentmods.dev/commands/zts0hg/codexspec/translate-docs"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/translate-docs/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/zts0hg/codexspec/translate-docs"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/translate-docs.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 | $0.00017 | $0.00301 |
| Opus 5.5 | $0.00007 | $0.00120 |
| Sonnet 5.5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
translate-docs 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.
What it actually says
Repository Document Translator
This is CodexSpec maintainer tooling, not a command distributed to user projects.
User Input
$ARGUMENTS
Workflow
Read internal/references/doc-translation.md in the selected checkout. Follow
its workspace/language/selection rules, shared translation rules, and Translator
execution section. Retain existing site support and select root READMEs with
--readme or an explicit README.md source.
Write the complete selected content as natural target-language technical
documentation. Reorganize sentence structure when useful while preserving all
meaning and protected technical content; obvious translationese requires repair.
Honor explicitly approved wording for its corresponding passage.
Verify the actual outputs for both fidelity and natural expression. Then invoke
/codexspec:check-i18n-semantics for the same selection; report every failed pair.
A preview does not write translations.
/codexspec:translate-docs --readme --lang all
/codexspec:translate-docs user-guide/installation.md --lang ja
/codexspec:translate-docs --lang zh --incremental --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.
- 2d ago Changed · +4 lines 82a471736fdd
- 3d ago Changed · -225 lines · +9 tokens per session 00d9ce4ab61b
- 1mo ago First seen · 255 lines · 8 tokens per session scan A d8c3d4b8041c
translate-docs is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 301 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
chinese
A command that changes Claude Code's interface, loading messages, and spinner text to simplified Chinese.
english
A command that switches Claude Code's interface text, spinner verbs, and tips back to English. Claude Code is a coding assistant that runs in a development environment.
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
app-factory
Create a scalable Flask application using the factory pattern with blueprints and configuration management.
views
Create Django views with proper structure and best practices.
blueprint
Create organized Flask blueprints for modular application structure.