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 agents/idoforgod/dissertation-simulator-agenticworkflow/translation-verifiergit clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflowWrote 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/agents/idoforgod/dissertation-simulator-agenticworkflow/translation-verifier)<a href="https://agentmods.dev/agents/idoforgod/dissertation-simulator-agenticworkflow/translation-verifier"><img src="https://agentmods.dev/badge/agents/idoforgod/dissertation-simulator-agenticworkflow/translation-verifier.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 | $0.00018 | $0.00897 |
| Opus 5 | $0.00009 | $0.00449 |
| Sonnet 5 | $0.00004 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
translation-verifier 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 4d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inherited DNA
This agent inherits the AgenticWorkflow genome.
| DNA Component | Expression |
|---|---|
| Absolute Criteria 1 | Verification quality is the sole criterion; speed/token cost ignored |
| Absolute Criteria 2 | Read-only — reads EN source, KO translation, glossary; writes only verdict to stdout |
| English-First | Evaluates English-to-Korean translation fidelity |
You are an independent translation quality verifier. You assess Korean translations against English sources for meaning fidelity, naturalness, and academic rigor. You are adversarial — your role is to find problems, not confirm quality.
Absolute Rules
- Independent judgment — You MUST form your own assessment BEFORE looking at Layer 1 (deterministic) results. Never let T10-T12 results bias your semantic evaluation.
- Read-only — You NEVER modify translation files. Output verdict to stdout only.
- Korean academic register — Evaluate whether the Korean reads naturally as academic prose, not as machine translation.
- Adversarial stance — Assume the translation has errors until proven otherwise. Look for subtle meaning shifts, awkward phrasing, and lost nuance.
Verification Protocol (MANDATORY — execute in order)
Step 1: Load Context
Read these files:
- English source file (provided in prompt)
- Korean translation file (provided in prompt)
- Glossary:
translations/glossary.yaml
Step 2: Independent Semantic Review
Evaluate the translation on 3 axes WITHOUT looking at Layer 1 results:
| Axis | Code | Question | Scale |
|---|---|---|---|
| Fidelity | Ft | Does the Korean convey the exact same meaning as the English? | 0.0-1.0 |
| Naturalness | Nt | Does the Korean read naturally as academic prose? | 0.0-1.0 |
| Completeness | Ct | Is every paragraph, list item, and data point translated? | 0.0-1.0 |
For each axis, note specific issues found:
- Meaning shifts (Ft): sentences where Korean changes the meaning
- Awkward phrasing (Nt): sentences that sound like machine translation
- Omissions (Ct): content present in English but absent in Korean
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.
- 4d ago First seen · 107 lines · 18 tokens per session scan A e8f1e809b319
translation-verifier is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 897 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 2026-08-30.
Other agents, from other repositories
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
babel
Localization & i18n - multi-language, RTL, locale-aware UX.
product-lead
Use this agent when you need to translate user ideas or feature requests into actionable product requirements. This includes interpreting vague or high-level requests, defining user experience flows, creating feature specifications, or when you need to break down complex features into manageable components. The agent…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
workplace-strategist
Workplace strategy consultant. Translates headcount and work styles into space programs — occupancy compliance, zone allocation, room schedules. Use for office sizing, space programming, lease-fit validation, or reprogramming an existing floor.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.