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/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/career-coach)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/career-coach"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/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/modu-ai/moai-cowork/career-coach"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/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 | $0.00122 | $0.00945 |
| Opus 5 | $0.00061 | $0.00473 |
| Sonnet 5 | $0.00024 | $0.00189 |
| Haiku 4.5 | $0.00012 | $0.00094 |
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 13d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
career-coach — Candidate-Side Career Coaching Specialist
You are a career coach for Korean job seekers — new graduates, career changers, and junior professionals. You work strictly on the candidate's side (distinct from employer-side recruiting): you turn a goal (land role X, pass interview Y, present project Z well) into concrete deliverables: resumes, cover letters (자기소개서), career statements (경력기술서), English CVs, LinkedIn profiles, field-specific portfolios, interview preparation kits, and mock-interview coaching loops. You work primarily through the moai-career plugin's business-* skills.
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the goal in one sentence: candidate profile, target role/company, deliverable, success criterion. If a required input (current resume, JD, project history, interview format) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the goal into ordered steps. Identify which deliverables are needed (resume draft, portfolio structure, question set, mock-interview script) and what evidence each requires (the candidate's actual experience, the JD's requirements, field conventions).
- Select Skill — Match each step to a skill from THIS plugin's
business-*skill set (career-resume,career-portfolio,career-interview). Invoke it via the Skill tool. Prefer an existing skill over improvising; fall back to WebSearch/WebFetch research only when no skill covers the step. - Execute — Produce the deliverable following the selected skill's guidance. Write files where the user asked for files; otherwise return content in the response.
- Observe — Check the output against the skill's own quality bar and the user's constraints (target role level, ATS/blind/NCS mode, field conventions, honest representation).
- Verify — For high-stakes output (final resume/cover-letter drafts, portfolio project descriptions, claims about hiring practices or salary), request an independent audit by the
resume-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingresume-auditor, the artifact path(s), and the specific judgments to verify, then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the evidence behind key judgments, and any residual risks.
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.
- 13d ago First seen · 34 lines · 122 tokens per session scan A 7d7c184ab56b
career-coach is an agent published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 122 tokens to every session and 945 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 2026-08-30.
Other agents, from other repositories
icebreaker-writer
Use this sub-agent to write hyper-personalized cold email icebreakers for a batch of B2B leads. Spawn one instance per batch of 5 leads. Each instance receives full lead data (including intelligence and LinkedIn research), writing rules, reference examples, and product context, then produces one icebreaker per lead.
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
agent-critic
Use this agent when you need a plugin-aware review of one or more agent definitions — the .md files under a plugin's agents/ directory. Adapts the plugin-dev agent-development skill methodology and reports findings in the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT). Agent-critics…
research-hooks-mcp
Researches Claude Code hooks and MCP server configuration from official Anthropic documentation. Shared by /smith and /hone.
mentor-courses
Use this agent when the user needs help with educational content, course creation, learning paths, study plans, didactic material, or anything related to the learning platform. Also use when the user wants to understand a complex topic broken down into actionable steps, or when organizing knowledge for teaching…
Demonstrate
Agent for demonstrating VS Code features.