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/Aznatkoiny/zAI-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/plugins/aznatkoiny/zai-skills/career-coach)<a href="https://agentmods.dev/plugins/aznatkoiny/zai-skills/career-coach"><img src="https://agentmods.dev/badge/plugins/aznatkoiny/zai-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/plugins/aznatkoiny/zai-skills/career-coach"><img src="https://agentmods.dev/badge/plugins/aznatkoiny/zai-skills/career-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 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.
What it actually says
{
"name": "career-coach",
"version": "1.3.0",
"description": "Career coaching and job search plugin with AI-powered resume building, interview preparation, and multi-platform job discovery. Features a Career Director orchestrator, job search automation via MCP, industry-specific formatting styles, and LaTeX resume compilation.",
"author": {
"name": "Antony Zaki"
},
"homepage": "https://github.com/Aznatkoiny/zAI-Skills",
"repository": "https://github.com/Aznatkoiny/zAI-Skills",
"license": "MIT",
"keywords": [
"career",
"job-search",
"resume",
"interview-prep",
"career-coaching",
"linkedin",
"latex-resume"
]
}
What it installs
The manifest is a name and a version. 1 skill, 8 commands, 3 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,046 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill resume-updater A 172 tokens
- Command job-hunt A 21 tokens
- Command resume-generator A 23 tokens
- Command ats-check A 19 tokens
- Command cover-letter A 12 tokens
- Command mock-interview A 21 tokens
- Command validate-profile A 15 tokens
- Command compare-offers A 21 tokens
- Command follow-ups A 15 tokens
- Agent career-director A 265 tokens
- Agent interview-prep A 242 tokens
- Agent job-search A 220 tokens
- Hook PostToolUse A not measured
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 · 21 lines scan A b724454cc676
career-coach is a plugin published in the GitHub repository Aznatkoiny/zAI-Skills (10 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
context-optimizer
See what Claude costs you and spend less of it. In chat: hand a long chat over to a new one, digest long documents, set up Projects, check tokens, sharpen prompts. In Claude Code: Haiku 5.5 subagents for reading and test runs; /cco audit of your own transcripts. Local, no telemetry.
brewcode
Brewcode - Claude Code authoring toolkit: skill, agent and rule creation and sync, semantic code search (semble), project conventions, E2E tests, generated review and domain-team skills, setup dashboard, post-compact plan re-anchor.
brewtools
Brewtools - Claude Code utilities: text optimization and humanization, secrets scanning, SSH and GitHub Actions deploy, manager hard-wall guard, subagent deadline/return-size/routing guards, task board, context slimming, plugin updates, alternative API providers.
skill-creator-plus
Create, test, evaluate, and iteratively improve Claude Code skills with built-in benchmarking, blind A/B comparison, and description optimization.
deep-research
Deep Research (/deep-research or /dr) — exhaustive, evidence-based investigation of any topic. ICD 203 (9/9), GRADE, NIST reproducibility, CRAAP. 89 runs, 85+ domains, 24.3/25 judge score.
claude-friends
Claude asks AIs from other families before the calls that matter: Gemini, an isolated second Claude with no memory of the conversation, optionally GPT. Three review styles, picked from what you type. CLI only, no MCP server.