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 agentmods add commands/zts0hg/codexspec/check-i18n-semanticsgit 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/check-i18n-semantics)<a href="https://agentmods.dev/commands/zts0hg/codexspec/check-i18n-semantics"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/check-i18n-semantics.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.01038 |
| Opus 5 | $0.00006 | $0.00519 |
| Sonnet 5 | $0.00002 | $0.00208 |
| Haiku 4.5 | $0.00001 | $0.00104 |
Grade A, and why
check-i18n-semantics 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Consistency Check
Language Preference
IMPORTANT: Before proceeding, read the project's language configuration from .codexspec/config.yml.
- If
language.outputis set to a language other than "en", respond and generate all content in that language - If not configured or set to "en", use English as default
- Technical terms (e.g., API, JWT, OAuth) may remain in English when appropriate
- All user-facing messages, questions, and generated documents should use the configured language
User Input
$ARGUMENTS
Instructions
You are a Translation Quality Reviewer. Your task is to analyze translated documentation for semantic consistency with the source English content.
Steps
-
Parse Arguments
source_file: Optional specific file to check (e.g.,user-guide/getting-started.md)--lang <lang>: Target language code (e.g.,zh,ja,ko). If not specified, check all languages--strict: Enable strict mode (fail on any semantic drift)
-
Load Configuration
- Read
.codexspec/config.ymlfor project settings - Read
docs/i18n/glossary.ymlfor terminology guidelines (CodexSpec maintainer-only path)
- Read
-
Identify Files to Check
- If
source_filespecified: Check only that file across target languages - If no file specified: Check all markdown files in
docs/<lang>/
- If
-
Perform Semantic Analysis
For each source-target file pair:
a. Read both files
- Source:
docs/en/<path> - Target:
docs/<lang>/<path>
b. Compare semantic elements:
- Heading hierarchy: Same structure and meaning
- Key concepts: All important terms present
- Code examples: Identical functionality
- Links: Valid and correctly translated
- Warnings/Notes: Same severity and meaning
c. Identify issues:
- Missing content: Sections or paragraphs omitted
- Added content: Extra information not in source
- Semantic drift: Meaning changed in translation
- Inconsistent terminology: Not following glossary
- Unnatural phrasing: Translation mirrors English word-order or grammar instead of reading as native prose (see Translation Methodology in translate-docs)
- Source:
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.
- 5d ago First seen · 141 lines · 12 tokens per session scan A 18cd1964f301
check-i18n-semantics is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 1,038 once invoked, about $0.0001 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 commands, from other repositories
chinese
切换 Claude Code 为简体中文（界面、spinner 动词与提示）.
english
Switch Claude Code back to English (UI, spinner verbs and tips).
zh
切换 Claude Code 为简体中文（/chinese 的短别名）.
growth-localization
Localization strategy and international expansion.
sync-linear
Sync current work with Linear ticket status.
media-extract-frames
Gemini-only command that identifies visually significant video frames and describes each as a storyboard entry.