# Aicrew Benchmark

> Run a benchmark to measure skill quality, response time, and token efficiency for aicrew skills.

- **Type:** Skill
- **Install:** `agentstack add skill-aksoftcode-aicrew-aicrew-benchmark`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [AKSoftCode](https://agentstack.voostack.com/s/aksoftcode)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [AKSoftCode](https://github.com/AKSoftCode)
- **Source:** https://github.com/AKSoftCode/aicrew/tree/master/codex-skills/aicrew-benchmark
- **Website:** https://github.com/AKSoftCode/aicrew

## Install

```sh
agentstack add skill-aksoftcode-aicrew-aicrew-benchmark
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# aicrew-benchmark (Codex)

Use when: measuring aicrew skill output quality, latency, or token usage across skills or pipelines.

## Equivalent actions

| Method | Command |
|--------|---------|
| **CLI** | `aicrew benchmark` (planned) |
| **Codex skill** | `aicrew-benchmark` (this skill) |
| **Claude Code slash** | `/benchmark` |

## Default output

Caveman/lean style. See `~/Agents/agents/caveman.md`.

Source of truth:
- `~/Agents/commands/harness-audit.md` (for harness health)

## What to benchmark

Ask the user which dimension to measure:

> What should we benchmark?
> 1. **Skill trigger accuracy** — does the right skill fire for a given prompt?
> 2. **Output quality** — does a skill produce the expected sections/format?
> 3. **Token efficiency** — lean vs normal mode token counts for the same task
> 4. **Pipeline timing** — wall-clock time for each /dev or /fix phase
> 5. **All of the above** (full harness benchmark)

**Wait for answer.**

## Steps per benchmark type

### 1. Skill trigger accuracy
- List all skills and their `description` fields
- For each skill, present a sample prompt and confirm the right skill triggers
- Flag any ambiguous descriptions

### 2. Output quality
- Run a skill against a standard input
- Check required sections are present (e.g. SCOUT: block, HANDOFF: block, phase gates)
- Flag missing or malformed sections

### 3. Token efficiency
- Compare output token count with lean vs normal mode
- Run the same task in both modes; measure diff

### 4. Pipeline timing
- Record start/end of each phase in `/dev` or `/fix`
- Output phase timings as a table

### 5. Full harness
- Run all checks above in sequence
- Output a summary table: skill → trigger ✓/✗ → quality ✓/✗ → tokens → timing

## Output format

```
BENCHMARK:
Skill/Phase   | Trigger | Quality | Tokens | Timing
--------------|---------|---------|--------|-------
aicrew-dev    | ✓       | ✓       | 1200   | 4.2s
aicrew-fix    | ✓       | ✓       | 800    | 2.1s
...
```

## Checkpoint

After each benchmark type completes: report results and ask "Continue with next type?" before proceeding.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [AKSoftCode](https://github.com/AKSoftCode)
- **Source:** [AKSoftCode/aicrew](https://github.com/AKSoftCode/aicrew)
- **License:** MIT
- **Homepage:** https://github.com/AKSoftCode/aicrew

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-aksoftcode-aicrew-aicrew-benchmark
- Seller: https://agentstack.voostack.com/s/aksoftcode
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.