# Agentv Trace Analyst

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-entityprocess-agentv-agentv-trace-analyst`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [EntityProcess](https://agentstack.voostack.com/s/entityprocess)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [EntityProcess](https://github.com/EntityProcess)
- **Source:** https://github.com/EntityProcess/agentv/tree/main/skills-data/agentv-trace-analyst
- **Website:** https://agentv.dev

## Install

```sh
agentstack add skill-entityprocess-agentv-agentv-trace-analyst
```

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

## About

# AgentV Trace Analyst

Analyze evaluation traces headlessly using `agentv inspect` primitives and `jq`.

## Primitives

```bash
# List result files (most recent first)
agentv inspect list [--limit N] [--format json|table]

# Show results with trace details
agentv inspect show  [--test-id ] [--tree] [--format json|table]

# Percentile statistics
agentv inspect stats  [--group-by target|suite|test-id] [--format json|table]

# A/B comparison between runs
agentv compare   [--threshold 0.1] [--format json|table]
```

## Analysis Workflow

### 1. Discover results

```bash
agentv inspect list
```

Pick the result file to analyze. Most recent is first.

### 2. Get overview

```bash
agentv inspect stats 
```

Read the percentile table. Key signals:
- **score p50  30s**: Performance bottleneck
- **cost p99 spike**: Outlier cost tests to investigate
- **tool_calls p90 >> p50**: Some tests are much chattier

### 3. Investigate failures

```bash
agentv inspect show  --format json | jq '[.[] | select(.score  --test-id 

# Tree view (if output messages available)
agentv inspect show  --test-id  --tree
```

The tree view shows the agent's execution path — LLM calls interspersed with tool invocations. Look for:
- **Excessive tool calls**: Agent looping or exploring unnecessarily
- **Missing tools**: Expected tool not called
- **Long durations**: Specific tool calls that are slow

### 5. Compare runs

```bash
agentv compare  
```

Look for:
- **Wins vs losses**: Net improvement or regression?
- **Mean delta**: Overall direction of change
- **Per-test deltas**: Which tests regressed?

### 6. Group analysis

```bash
# By target provider
agentv inspect stats  --group-by target

# By suite
agentv inspect stats  --group-by suite
```

Compare providers side-by-side: which is cheaper, faster, more accurate?

## Advanced Queries with jq

All commands support `--format json` for piping to `jq`:

```bash
# Top 3 most expensive tests
agentv inspect show  --format json \
  | jq 'sort_by(-.cost_usd) | .[0:3] | .[] | {test_id, cost: .cost_usd, score}'

# Tests where token usage exceeds 10k
agentv inspect show  --format json \
  | jq '[.[] | select(.token_usage.input + .token_usage.output > 10000) | {test_id, tokens: (.token_usage.input + .token_usage.output)}]'

# Score distribution by suite
agentv inspect show  --format json \
  | jq 'group_by(.suite) | .[] | {suite: .[0].suite, count: length, avg_score: ([.[].score] | add / length)}'

# Tool usage frequency across all tests
agentv inspect show  --format json \
  | jq '[.[].trace.tool_calls // {} | to_entries[]] | group_by(.key) | .[] | {tool: .[0].key, total_calls: ([.[].value] | add)}'

# Find regressions > 0.1 between two runs
agentv compare baseline.jsonl candidate.jsonl --format json \
  | jq '.matched[] | select(.delta  0 is good, but check individual test regressions — a few large losses can hide behind many small wins.

## Accessing reference files

To load a specific reference without pulling the entire skill into context:

```bash
agentv skills get agentv-trace-analyst --ref 
```

Or resolve the skill directory and read files directly:

```bash
cat $(agentv skills path agentv-trace-analyst)/references/.md
```

Use `--full` to retrieve every file in the skill at once.

## Source & license

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

- **Author:** [EntityProcess](https://github.com/EntityProcess)
- **Source:** [EntityProcess/agentv](https://github.com/EntityProcess/agentv)
- **License:** MIT
- **Homepage:** https://agentv.dev

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-entityprocess-agentv-agentv-trace-analyst
- Seller: https://agentstack.voostack.com/s/entityprocess
- 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%.