concurrency-report — Claude Code skill: reports on parallel runs
The concurrency-report skill examines agent concurrency in a session, including lane usage, peak parallel width, and work that ran in sequence. Use it to see how a multi-agent run was scheduled.
MIT ★ 1,198 updated 2026-10-23
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-workflows@claude-code-agent-monitor-pluginsWhat concurrency-report does
For a session, the skill retrieves the concurrency and complexity datasets through the Agent Monitor API. Its report gives the lane and agent counts, the maximum number of agents active at once, and busy and idle time for each lane. A lane-by-lane timeline makes overlapping runs visible.
A separate section calls out sequential chains that show no apparent dependency and estimates their wall-clock cost. It flags a chain only when the API timing data shows sequential execution. If just one agent ran, the report says so. With no session ID, it fetches the latest session using GET /api/sessions?limit=1.
The Agent Monitor dashboard must be reachable. If it is not, the skill tells you to start it with npm start from the repository root; without dashboard access, it cannot retrieve the report data. The skill is available for Claude Code and Codex.
What it helps with
- measure how many agents ran at the same time
- inspect busy and idle time across execution lanes
- visualize where agent runs overlapped
- spot data-backed sequential chains and their wall-clock cost
Example prompts for the agent
- Report concurrency for session
abc123. - Check how parallel work was scheduled in the latest session.
- Show the lane timeline and sequential chains for session
abc123.
How to install concurrency-report
1Plugin marketplace
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor/plugin install ccam-workflows@claude-code-agent-monitor-pluginsThis installs the whole ccam-workflows plugin with all its skills
2Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -a claude-code3Manually: put the files in place
~/.claude/skills/concurrency-report/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/concurrency-report/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -a codex2Manually: put the files in place
.agents/skills/concurrency-report/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -a cursor2Manually: put the files in place
.cursor/skills/concurrency-report/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install hoangsonww/Claude-Code-Agent-Monitor plugins/ccam-workflows/skills/concurrency-report2Manually: put the files in place
.github/skills/concurrency-report/SKILL.md1Skills CLI (Vercel)
npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill concurrency-report -a gemini-cli2Platform CLI
gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-workflows/skills/concurrency-reportManually: put the files in place
.devin/skills/concurrency-report/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about concurrency-report
How do I install concurrency-report in Claude Code?
Add the marketplace with /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor, then install the skill using /plugin install ccam-workflows@claude-code-agent-monitor-plugins.
What does concurrency-report do?
It reports how agents ran in a session, including execution lanes, utilization, peak parallel width, and sequential chains.
What does concurrency-report need to run?
It needs access to the Agent Monitor API. If the dashboard cannot be reached, start it with npm start from the repository root.
Source text
SKILL.md · MIT
---
name: concurrency-report
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.
---
# 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
- Markdown tables for utilization; a fenced list for the lane timeline.
- Durations in human units (e.g. `48s`, `2m 10s`); percentages to whole numbers.
- Use ▲/▼ when comparing utilization against an even-distribution baseline.
- Cite only timing returned by the API; never invent lane overlaps or durations.
- If the session ran a single agent (no concurrency), say so plainly rather than inventing lanes.
- If the dashboard is unreachable, tell the user to start it with `npm start` from the repo root.
© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor