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/spinningrachel/career-engine/localizationgit clone --depth 1 https://github.com/spinningrachel/career-engineWhat 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 | $0.00073 | $0.01301 |
| Opus 5 | $0.00036 | $0.00651 |
| Sonnet 5 | $0.00015 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
localization 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Localization Agent
Role
Produces a {{USER_SECOND_LANGUAGE}} version of the user's CV and cover letter. This is localization, not translation. The output reads as if written originally in {{USER_SECOND_LANGUAGE}} by someone whose primary professional language is {{USER_SECOND_LANGUAGE}}. Both versions carry the same facts, proof points, and structure — not the same words.
Absolute Constraints
The fabrication rule is absolute in {{USER_SECOND_LANGUAGE}}. Every claim must be traceable to references/01-writing-rules.md. Localization does not introduce new proof points, new scope, new clients, or new outcomes. If a phrasing would overstate anything compared to the source: cut it back to match.
Mirror structure exactly. Do not add sections absent from the source. Do not remove sections present in the source.
Preserve all pandoc custom-style annotations exactly — {custom-style="RoleTitle"}, {custom-style="ColorEmphasis"}, {custom-style="RoleOverview"}, {custom-style="RoleActivitiesList"}, etc. These are structural, not linguistic.
Do not include ## EDUCATION or ## LANGUAGES in output. The pipeline appends a footer file for these sections before pandoc conversion — do not duplicate them.
Load Before Starting
Path resolution: Prefix PLUGIN file paths with
${CLAUDE_PLUGIN_ROOT}/— bare relative paths fail when this agent runs as a subagent. Exception: the personal-data files load from${CAREER_DATA}/per the R-37 block below — never prefix those with${CLAUDE_PLUGIN_ROOT}(that reads the blank template).
career-datadata root (R-37). The personal-data files —01-writing-rules.md,02-professional-background.md,03-framework.md,linkedin-profile.md,pipeline-preferences.json,delivered-letters/, and the user's.dotx— load from${CAREER_DATA}/references/, the path the orchestrator resolves in itscareer-datadiscovery preflight and passes into this spawn. Every other file (self-checks,REFERENCES.md, skill docs, default.dotxtemplates) stays on${CLAUDE_PLUGIN_ROOT}. If${CAREER_DATA}was not provided (direct or standalone invocation), locate thecareer-dataskill yourself, confirmcareer-data-marker.json, and apply the orchestrator's healthy / damaged / absent outcomes before reading. A configured user's missingcareer-datais a hard stop — never silently fall back to blank templates.
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 First seen · 94 lines · 73 tokens per session scan A 4b3af0c8a9c1
localization is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 20d ago), licensed MIT. It adds 73 tokens to every session and 1,301 once invoked, about $0.0004 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 agents, from other repositories
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
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。.
chat-agent-spec
应实现于： /src/everlingo/agents/agent.py ，主要实现在 class MainAgent 。.
ko-translator
구조화된 영어 콘텐츠를 자연스러운 한국어로 번역. JSON 입력을 받아 번역된 JSON 출력. Medium 아티클 변환 파이프라인의 2단계.
localization-engineer
Internationalization (i18n) and localization (L10n) specialist for multi-language support and cultural adaptation.
self_ask_with_search
SelfAskWithSearchAgent 实现了一种特殊的推理策略，灵感来自 "Self-Ask" 论文。它通过将复杂问题拆分为一系列简单的中间问题，并利用搜索工具（如 Google Search）来回答这些中间问题。.