# audit-scoring-wasp-drone

The audit-scoring-wasp-drone subagent turns audit findings into rollup scores and fills an XLSX scorecard. Run it after the applicable Wave-5 and Wave-6 checks finish.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/website-audit-tools/agents/audit-scoring-wasp-drone.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/audit-scoring-wasp-drone

## What it does

The subagent rolls submitted findings from leaf checks into sub-audit, category, and final scores. Its calculations use weighted formulas that account for items marked as not applicable. A critical security finding can also cap the final grade.

It writes `scoring/audit-scorecard.xlsx` and `scoring/findings-register.csv`, then populates the branded XLSX scorecard. The subagent handles arithmetic and workbook output; it does not produce the customer-facing report or replace an upstream domain judgement.

Run it only after the relevant Wave-5 or Wave-6 Drones have written their findings. A finding without evidence or justification is sent back to its originating Drone instead of being scored.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install website-audit-tools@wasp-nest
```

2. **Manually: put the files in place**
- File: `.claude/agents/audit-scoring-wasp-drone.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/audit-scoring-wasp-drone.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/audit-scoring-wasp-drone.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/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/website-audit-tools/agents/audit-scoring-wasp-drone.md

## When to use it
- roll leaf findings into sub-audit scores
- calculate category and final audit results
- account for findings marked not applicable
- cap the grade after a critical security score
- populate the XLSX scorecard and findings register

## Example prompts
- Run `audit-scoring-wasp-drone` after the applicable Wave-5 and Wave-6 Drones finish their findings.
- Write the calculated results to `scoring/audit-scorecard.xlsx` and `scoring/findings-register.csv`.
- Reject any leaf finding that lacks evidence or justification instead of scoring it.

## Similar
- [lead-scoring](https://affpapa.org/en/nevibecode/skills/lead-scoring.md) — skill · 26900 installs
- [DoorVault IDEAL Scoring](https://affpapa.org/en/nevibecode/mcp/doorvault-ideal-scoring.md) — MCP server · 3646 installs
- [cvss-scoring](https://affpapa.org/en/nevibecode/skills/cvss-scoring.md) — skill · 304 installs
- [music-supervision-scoring](https://affpapa.org/en/nevibecode/skills/music-supervision-scoring.md) — skill · 263 installs
- [lead-scoring-model](https://affpapa.org/en/nevibecode/skills/lead-scoring-model.md) — skill · 253 installs
- [code-quality-scoring](https://affpapa.org/en/nevibecode/skills/code-quality-scoring.md) — skill · 206 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 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
