# Concurrency Report

Report concurrency and parallelism for a session, how many agents ran in parallel...

- Repository: https://github.com/hoangsonww/Claude-Code-Agent-Monitor (1136 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-10-31
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -g -a claude-code -y`
Codex: `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -g -a codex -y`
Cursor: `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -g -a cursor -y`
Gemini CLI: `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor`

## Description

Report concurrency and parallelism for a session, how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes), using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Concurrency Report

Report on parallel execution for one Claude Code session: lanes, peak width, utilization, and where work serialized.

## Input

The user provides: **$ARGUMENTS**

A session ID. If empty, fetch `GET /api/sessions?limit=1` and report on the most recent session, stating which one.

## Data Sources

| Endpoint | Returns |
|----------|---------|
| `GET /api/workflows/{sessionId}` | The `concurrency` dataset (overlapping agent execution lanes with start/end timing) and the `complexity` dataset (numeric score from depth, breadth, and tool diversity) |

## Report Sections

### 1. Parallelism Summary
From `concurrency`: number of distinct lanes, peak parallel width (max agents running simultaneously), and total agents. Pair with the `complexity` score to judge whether the parallelism matched the work's size.
`Lanes: N · Peak parallel: M · Agents: K · Complexity: S`

### 2. Lane Timeline
A per-lane list of the agents that occupied each lane in order:
`Lane 1: explore (0, 12s) → code-review (12, 48s)`
`Lane 2: debugger (5, 30s)`
Show overlapping windows so simultaneity is visible.

### 3. Utilization
| Lane | Busy time | Idle time | Utilization % |
|------|-----------|-----------|---------------|
Plus an overall utilization figure (busy lane-time / total lane-time).

### 4. Serialization Bottlenecks
Identify sequential chains where one agent waited on the previous despite no apparent dependency, candidates to run as parallel lanes. State the chain and the wall-clock time it cost. Only flag chains the `concurrency` timing data actually shows as sequential.

## Output

The rest: https://github.com/hoangsonww/Claude-Code-Agent-Monitor/blob/HEAD/plugins/ccam-workflows/skills/concurrency-report/SKILL.md