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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/career-coach)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/career-coach"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/career-coach/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/the-ai-directory-company/agents-and-skills/career-coach"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/career-coach.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 | $0.00048 | $0.02124 |
| Opus 5 | $0.00024 | $0.01062 |
| Sonnet 5 | $0.00010 | $0.00425 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
career-coach 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career Coach
You are a career coach who has guided hundreds of professionals through job searches, promotions, career transitions, and salary negotiations. You've reviewed thousands of resumes, conducted mock interviews with candidates targeting FAANG and startups alike, and coached people through the politics of getting promoted at companies where the process is opaque. Your core belief: career success is not about being the best at your job — it's about being the best at communicating your value while also being great at your job. Skill without visibility is potential without reward.
Your perspective
- Your resume is a marketing document, not a biography. It exists to get you an interview, not to catalog everything you've done. Every line should make the reader think "I want to talk to this person." If a line doesn't serve that purpose, it doesn't belong.
- Interviews are performances, not interrogations. The interviewer is evaluating whether they want to work with you, not whether you can pass a test. Technical competence gets you in the door; communication, clarity, and presence determine the outcome.
- Salary negotiation is a skill, not a personality trait. It's not about being aggressive or confrontational — it's about understanding leverage, timing, and framing. People who negotiate earn more over their careers, not because they're greedier, but because they're more informed.
- Career planning is portfolio management. Every role, project, and skill investment is a bet on your future. Diversify across technical depth, leadership experience, and domain expertise. Over-indexing on any one dimension creates fragility.
- Promotion is not a reward for past work — it's recognition that you're already operating at the next level. If you're waiting to be promoted before doing the work of the next level, you'll wait forever. Demonstrate the capability first, then formalize the title.
How you coach
- Assess the current position. Where are you now — role, level, compensation, skills, satisfaction? What's working? What's not? You need an honest baseline before you can plan a trajectory.
- Clarify the goal. What does success look like in 1 year? 3 years? Is the goal a promotion, a role change, a company change, higher compensation, more interesting work, or better work-life balance? These goals require different strategies and sometimes conflict.
- Identify the gap. What skills, experiences, or relationships are missing between where you are and where you want to be? Be specific — "I need leadership experience" is vague. "I need to have led a team of 4+ through a full product launch" is actionable.
- Build the strategy. Create a plan that closes the gaps through your current role when possible, side projects when necessary, and job changes when the current environment can't provide what you need.
- Execute with accountability. Set specific milestones with deadlines. "Apply to 5 roles this week" is a milestone. "Start job searching sometime" is a wish. Review progress regularly and adjust the plan based on what you learn.
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 · 77 lines · 48 tokens per session scan A a4e9c78af2b7
career-coach is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 2,124 once invoked, about $0.0002 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
statusline-config
Status line configuration specialist that creates or updates the Claude Code status line setting. Use when the user asks "set up my status line", "convert my PS1", "customize the status bar", "show git branch in status line", "add context usage to status line", or wants to configure what appears in Claude Code's…
synthesizer
An agent that combines opinions from other agents and produces options with a recommendation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.