Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/younnieCutler/japan-career-agentnpx agentmods add skills/younniecutler/japan-career-agent/mock-interviewerWrote 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/skills/younniecutler/japan-career-agent/mock-interviewer)<a href="https://agentmods.dev/skills/younniecutler/japan-career-agent/mock-interviewer"><img src="https://agentmods.dev/badge/skills/younniecutler/japan-career-agent/mock-interviewer/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/skills/younniecutler/japan-career-agent/mock-interviewer"><img src="https://agentmods.dev/badge/skills/younniecutler/japan-career-agent/mock-interviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.02783 |
| Opus 5 | $0.00064 | $0.01392 |
| Sonnet 5 | $0.00026 | $0.00557 |
| Haiku 4.5 | $0.00013 | $0.00278 |
Grade A, and why
mock-interviewer 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 today.
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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mock-interviewer — Japanese Interview Stress-Test Agent
Overview
This skill acts as a realistic, critical Japanese interviewer. It tests whether a candidate can defend their resume, 退職理由, 志望動機, and achievements through standard Japanese 深掘り (adaptive deep-dive questioning).
The goal is not to encourage, but to find weak points, undefendable metrics, and "AI-generated Tatemae" before a real interviewer catches them.
Execution Gate (check before starting a session)
If <career_status> reports unchecked action items for the company being practised for, do not run
the mock interview yet. Show the items and ask the user to complete them first
(python3 scripts/check_action.py <slug> <id>). Practising around an unfinished checklist rehearses
the same gap the checklist was written to close.
Read data/rules.yml if present. Any status: active rule is a phrase the user has already decided
never to say — treat a violation during practice as a finding, quoting the rule verbatim.
When CAREER_VAULT is set, read confirmed career_context from career-agent context before practice.
Otherwise read data/self_analysis_profile.yml only when career_context_confirmed: true. Missing or
unconfirmed context is not a reason to invent a value; continue with facts the user states in-session.
Ground the practice in confirmed evidence
python skills/career-agent/career_agent.py evidence-pool --vault "$CAREER_VAULT"
That returns confirmed work events grouped under their projects. When the user is practising for a
specific company, data/pipeline.yml already records what they chose to lead with —
primary_project_ids, primary_experience_ids, supporting_experience_ids. Build the questions
around those: the point of practice is the answer they will actually give.
Ask about what is recorded. "이 프로젝트에서 본인이 직접 한 일은?" is a question the evidence can answer; a question about a project they never recorded only teaches them to improvise.
The same rules apply here as anywhere else evidence is reused:
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/japan-market-probes.md 2.4 KB
- tests/eval.md 4.1 KB
- tests/fixtures/behavior/adaptive-breadth.json 376 B
- tests/fixtures/behavior/career-contradiction.json 374 B
- tests/fixtures/behavior/counterexample-probe.json 487 B
- tests/fixtures/behavior/defensible-core.json 525 B
- tests/fixtures/behavior/document-provenance.json 418 B
- tests/fixtures/behavior/qualitative-ready.json 518 B
- tests/fixtures/behavior/unsupported-metric.json 511 B
- tests/fixtures/behavior/user-exit.json 448 B
- tests/test_contract.py 2.1 KB runs code
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.
- today Changed · +19 lines a7b3594fd8b9
- 12d ago First seen · 222 lines · 129 tokens per session scan A 20591605958d
mock-interviewer is a skill published in the GitHub repository younnieCutler/japan-career-agent (6 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 2,783 once invoked, about $0.0006 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.