# final-round-panel

final-round-panel — a subagent for Claude Code simulates a final-round interview using a rebuilt resume and portfolio. It tests the candidate’s grasp of their work and discusses system design for a project.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 73 repo stars
- Author: Jerome Hardaway, Vets Who Code
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/final-round-panel.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/final-round-panel

## What it does

The subagent runs a mock final interview based on a rebuilt resume and portfolio material. Three panelists select prominent resume claims and ask follow-up questions to find how well the candidate can explain the work behind them.

A staff engineer then leads a 15-minute system design discussion about the candidate’s own project, examining scale and bottlenecks after a constraint changes. A product partner asks about tradeoffs among speed, quality, and user impact. In the debrief, each resume claim gets a Defended, Thin, or Cut label, followed by a suggested fix and topics to rehearse. It needs the rebuilt resume and portfolio material, and uses the Read tool.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add Vets-Who-Code/ai-era-job-kit
```
In the agent chat (not a shell):
```text
/plugin install ai-era-job-kit@ai-era-job-kit
```

2. **Manually: put the files in place**
- File: `.claude/agents/final-round-panel.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/final-round-panel.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/final-round-panel.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/final-round-panel.md

## When to use it
- rehearse answers about claims in a resume
- spot portfolio claims that need stronger evidence
- discuss system design for a personal project
- decide which resume lines to revise or remove

## Example prompts
- Run a mock final interview using my rebuilt resume and portfolio.
- Review my project as a final-round panel and discuss its system design bottlenecks.
- I lost a final interview. Probe my resume claims and list topics to rehearse.

## Similar
- [hr-round](https://affpapa.org/en/nevibecode/skills/hr-round.md) — skill · ★ 345 repo stars
- [phase-10i-transcript-recovery-final-re-review](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-recovery-final-re-review.md) — prompt · ★ 1497 repo stars
- [fcp-mcp — Final Cut Pro MCP Server](https://affpapa.org/en/nevibecode/mcp/fcp-mcp-final-cut-pro-mcp-server.md) — MCP server · ★ 16 repo stars
- [comic-panel-generation](https://affpapa.org/en/nevibecode/skills/comic-panel-generation.md) — skill · 915 installs
- [30x-growth-marketing-panel](https://affpapa.org/en/nevibecode/skills/30x-growth-marketing-panel.md) — skill · 880 installs
- [reader-panel](https://affpapa.org/en/nevibecode/skills/reader-panel.md) — skill · 448 installs

From the same set: [vets-who-code/ai-era-job-kit](https://affpapa.org/en/nevibecode/by/vets-who-code/ai-era-job-kit.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
