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/career-agentWrote 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/career-agent)<a href="https://agentmods.dev/skills/younniecutler/japan-career-agent/career-agent"><img src="https://agentmods.dev/badge/skills/younniecutler/japan-career-agent/career-agent/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/career-agent"><img src="https://agentmods.dev/badge/skills/younniecutler/japan-career-agent/career-agent.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 | $0.00076 | $0.03660 |
| Opus 5 | $0.00038 | $0.01830 |
| Sonnet 5 | $0.00015 | $0.00732 |
| Haiku 4.5 | $0.00008 | $0.00366 |
Grade A, and why
career-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career Agent
This is the orchestration layer for the existing eight domain skills. It does not replace them and
does not inject every SKILL.md into every run.
Run
First time, one shot:
python skills/career-agent/career_agent.py setup --track chuto --target-role "LLMOps Engineer"
setup inits a Vault (defaults to ~/.career-agent-vault if --vault/CAREER_VAULT isn't set),
fills in the profile fields given, and runs doctor, returning next so the caller knows whether
to go straight to chat or fill in whatever doctor still flags. It never picks the current working
directory as the Vault — only an explicit --vault, CAREER_VAULT, or the ~/.career-agent-vault
default.
Everything below is the same runtime, spelled out step by step, from the repository root:
VAULT=/path/to/career-agent-vault
python skills/career-agent/career_agent.py init --vault "$VAULT"
# Fill 00-control/career-profile.toml, then verify it.
python skills/career-agent/career_agent.py doctor --vault "$VAULT"
# If an older install warns about pipeline: {companies: ...}, migrate it once:
python skills/career-agent/career_agent.py doctor --vault "$VAULT" --fix
python skills/career-agent/career_agent.py run --vault "$VAULT" --mode chat --message "신졸이고 学チカ 경험을 정리하고 싶어요"
python skills/career-agent/career_agent.py run --vault "$VAULT" --mode heartbeat
python skills/career-agent/career_agent.py run --vault "$VAULT" --mode discover --source postings.json
python skills/career-agent/career_agent.py status --vault "$VAULT"
python skills/career-agent/career_agent.py guided --vault "$VAULT"
python skills/career-agent/career_agent.py approve --vault "$VAULT" --workspace "/path/to/job-search-workspace" <proposal-id> --evidence "resume line 12" --next-action "Prepare interview notes"
python skills/career-agent/career_agent.py restore-state --vault "$VAULT" <version>
python skills/career-agent/career_agent.py index --vault "$VAULT"
python skills/career-agent/career_agent.py context --vault "$VAULT"
python skills/career-agent/career_agent.py propose-context --vault "$VAULT" --source data/self_analysis_profile.yml
What ships with it
60 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.
- approvals.py 3.1 KB runs code
- artifact_store.py 13 KB runs code
- career_agent.py 1.0 KB runs code
- case_store.py 40 KB runs code
- cli_parser.py 30 KB runs code
- command_line.py 4.2 KB runs code
- diagnostics.py 6.7 KB runs code
- dispatch.py 23 KB runs code
- document.py 25 KB runs code
- documents.py 7.9 KB runs code
- execution_plans.py 20 KB runs code
- experiences.py 21 KB runs code
- gui/__init__.py 84 B runs code
- gui/_test_client.py 2.2 KB runs code
- gui/artifacts.py 450 B runs code
- gui/cases.py 4.1 KB runs code
- gui/DESIGN.md 8.8 KB
- gui/import_text.py 3.3 KB runs code
- gui/judgment_copy.py 8.5 KB runs code
- gui/judgments.py 6.3 KB runs code
- gui/monthly_copy.py 9.6 KB runs code
- gui/security.py 3.5 KB runs code
- gui/server.py 40 KB runs code
- gui/static/__init__.py 33 B runs code
- gui/static/app/app.css 153 KB
- gui/static/app/app.js 447 KB runs code
- gui/static/bootstrap.js 99 B runs code
- gui/tanaoroshi.py 6.9 KB runs code
- gui/templates.py 4.2 KB runs code
- gui/test_cases_artifacts.py 24 KB runs code
- gui/test_design_system.py 16 KB runs code
- gui/test_import_text.py 6.4 KB runs code
- gui/test_product_localization.py 13 KB runs code
- gui/test_projects.py 40 KB runs code
- gui/test_read_parity.py 11 KB runs code
- gui/test_scale_states.py 12 KB runs code
- gui/test_security.py 12 KB runs code
- gui/test_self_analysis.py 5.4 KB runs code
- gui/test_tanaoroshi.py 5.5 KB runs code
- gui/UI-SPEC.md 7.5 KB
- gui/views_read.py 31 KB runs code
- guided_flow.py 21 KB runs code
- guided.py 15 KB runs code
- ingest.py 9.7 KB runs code
- judgments.py 14 KB runs code
- lifecycle.py 27 KB runs code
- localization.py 179 KB runs code
- models.py 20 KB runs code
- monthly.py 5.0 KB runs code
- onboarding.py 6.7 KB runs code
- persistence.py 6.1 KB runs code
- personal_timeline.py 33 KB runs code
- private_store.py 19 KB runs code
- projection.py 23 KB runs code
- proposals.py 35 KB runs code
- references/japan-career-flow.toml 2.2 KB
- references/routing.yml 16 KB
- references/shared-vault-context.md 1.9 KB
- render.py 9.3 KB runs code
- review_policy.py 3.4 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.
- 12d ago First seen · 252 lines · 76 tokens per session scan A 6eb33f259843
career-agent is a skill published in the GitHub repository younnieCutler/japan-career-agent (6 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 3,660 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.