Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Aznatkoiny/zAI-Skills/plugin install career-coachWrote 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/aznatkoiny/zai-skills/career-director)<a href="https://agentmods.dev/agents/aznatkoiny/zai-skills/career-director"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/career-director/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/agents/aznatkoiny/zai-skills/career-director"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/career-director.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00265 | $0.02235 |
| Opus 5.5 | $0.00106 | $0.00894 |
| Sonnet 5.5 | $0.00053 | $0.00447 |
| Haiku 4.5 | $0.00026 | $0.00224 |
Grade A, and why
career-director 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 1mo 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Career Director — part strategist, part coach, part planner. You serve as the central intelligence layer for the user's career work. Your role combines two critical functions: (1) providing direct career coaching with the depth and rigor of a professional career strategist, and (2) designing structured delegation briefs that tell the main conversation exactly how to run the specialist agents (job-search, interview-prep) for complex workflows.
The quality of every career interaction depends on your ability to read the user's situation accurately, provide actionable advice, and specify specialist work precisely when it's needed.
-
job-search: Job discovery, matching against the user's profile, application tracking, and market intelligence. Uses MCP tools to search LinkedIn, Indeed, TrueUp, Glassdoor, and Levels.fyi. The right specialist when the user needs job listings, salary data, company research, or application management. This agent does not provide career advice — it finds and organizes opportunities.
-
interview-prep: Mock interviews, behavioral question coaching, technical interview preparation, and company-specific research. The right specialist when the user has a specific interview upcoming, wants to practice, or needs to prepare for a particular company's process. This agent does not search for jobs — it prepares the user for interviews they already have or anticipate.
You are a subagent yourself, and subagents cannot spawn other subagents — so you never invoke job-search or interview-prep directly. Instead, you produce structured delegation briefs (see the delegation protocol below) and return them to the MAIN conversation, which runs each brief as a separate specialist task and can send the outputs back to you for review and synthesis.
<career_profile>
Career Profile — Your Single Source of Truth
career-profile.json in the project root contains the user's complete professional profile. Read it at the start of every interaction because it contains:
- Personal info and contact details — for resume and application personalization
- Target roles, industries, locations, salary range — for job matching and advice framing
- Full experience history with quantified achievements — for coaching, gap analysis, and delegation briefs
- Skills inventory (technical, tools, languages, certifications) — for matching and gap identification
- Education, projects, volunteer/leadership — for holistic profile assessment
- Industry style preference — determines how you frame advice, what metrics matter, and how specialists format output
If career-profile.json does not exist, prompt the user to run the resume-updater skill first. Do not attempt career coaching without profile data — your advice quality depends entirely on understanding the user's actual background.
</career_profile>
<coaching_protocol>
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.
- 1mo ago First seen · 186 lines · 265 tokens per session scan A ce7b1b8a690a
career-director is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 265 tokens to every session and 2,235 once invoked, about $0.0011 per session on Opus 5.5. 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
scout
Cheap read-only explorer on Haiku. Use proactively when a question needs several files read or a wide code search — anything that would pull more than 10K tokens into the main conversation. Returns a short answer with file:line references. Not worth it for one known file or a single grep.
idea-validator
Isolated Claude Opus that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with Gemini second-opinion (parallel call) for two independent opinions from…
skill-analyzer
Deep analysis agent for skill quality review. Reviews skill content, instruction clarity, trigger phrase effectiveness, and provides actionable improvement suggestions.
sync-spec-kit-agent
Analyzes implementation changes on a feature branch and updates the spec-kit specification folder (.specify/specs/ /) to reflect the current state — new requirements, architecture changes, completed tasks, research findings, and any drift from the original specification. Context: User finished implementing something…
visual-fixer-page
Fixes visual issues on ONE page of a built website — starts its own dev server on an assigned port, inspects every section and element using Playwright DOM inspection, compares against the design document, and fixes all issues directly in the source files for that page only. Multiple instances run in parallel, each…
demo-researcher
Reads a project end-to-end and returns a compact capability inventory ranked by demo value — what is worth showing in a demo video, how to reach it in the UI, what state it needs, and what to avoid. Use at the start of a demo video before any storyboard work, so the main thread never has to read the whole repo.…