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/basaltbytes/agentic-tools/translategit clone --depth 1 https://github.com/basaltbytes/agentic-toolsWhat 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 | $0.00017 | $0.01027 |
| Opus 5 | $0.00009 | $0.00513 |
| Sonnet 5 | $0.00003 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
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 yesterday.
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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translation Workflow for i18next
You are running a translation workflow to find and fix hardcoded strings using i18next-cli.
Arguments
$ARGUMENTS- Optional path to app directory (for monorepos), e.g.,apps/mobile
Step 1: Detect Project Structure
First, determine where to run commands:
# If path provided, cd into it
# Otherwise, check current directory for config
find . -maxdepth 3 -name "i18next.config.ts" -o -name "i18next.config.js" -o -name "i18next.config.mjs" 2>/dev/null | head -10
Determine project type:
- Monolith: Config at project root → work from root
- Monorepo: Config in
apps/*orpackages/*→ cd into that directory
If no config found, ask user if they want to create one with npx i18next-cli init.
Step 2: Detect Package Manager
# Check lockfiles to determine package manager
if [ -f "pnpm-lock.yaml" ]; then
echo "pnpm"
elif [ -f "yarn.lock" ]; then
echo "yarn"
else
echo "npm"
fi
Use the appropriate runner:
- pnpm →
pnpm dlx i18next-cliorpnpm i18next-cliif installed - yarn →
yarn dlx i18next-cli - npm →
npx i18next-cli
Step 3: Check Initial Status
Get baseline translation status:
<package-runner> i18next-cli status
Report to user:
- Overall progress per locale (%)
- Number of missing keys
- Which namespaces need attention
Step 4: Self-Verification Loop
Enter the fix-and-verify loop:
4a. LINT - Find Hardcoded Strings
<package-runner> i18next-cli lint
Parse the output to identify:
- File paths with issues
- Line numbers
- The hardcoded text
4b. FIX - Apply Translations
For each hardcoded string found, apply the appropriate fix:
Plain text in JSX:
// ❌ Before
<Text>Welcome back!</Text>
// ✅ After
<Text>{t('welcome_back')}</Text>
Text with interpolation:
// ❌ Before
<Text>Hello {userName}!</Text>
// ✅ After
<Text>{t('hello_user', { name: userName })}</Text>
Rich text with nested elements (use Trans component):
// ❌ Before
<Text>Read our <Link>terms</Link></Text>
// ✅ After
import { Trans } from 'react-i18next';
<Trans i18nKey="read_terms">
Read our <Link>terms</Link>
</Trans>
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.
- yesterday First seen · 174 lines · 17 tokens per session scan A d72a1a2aecba
translate is a command published in the GitHub repository basaltbytes/agentic-tools (2 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 1,027 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
harden
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says "it crashes on empty data" / "there's no loading state"…
ask
Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
ask
数学研究操作系统入口:自动诊断用户意图,路由到思想透镜、数学知识库或设计翻译层。 English: Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
figma-to-code
Translate a Figma design description into Vue 3 + Vuetify 3 component code.
marketing
Command "marketing" from Infrasity-Labs/dev-gtm-claude-skills, covering seo & discoverability, content & copy, demand gen & growth, lifecycle & retention and research & competitive.
checklist
Generate a custom checklist for the current feature based on user requirements.