Skip to main content
skill CX Codex

error-propagation — Claude Code skill: what it does, how to install

error-propagation finds the depth in a multi-agent tree where a failure started and tracks the chain that carried it up to parent agents.

MIT ★ 1,198 updated 2026-10-23

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-workflows@claude-code-agent-monitor-plugins
Open on GitHub

What error-propagation does

The skill reads the errorPropagation dataset from GET /api/workflows/{sessionId}, which already groups failures by agent depth and records where each one originated and the path it took upward. It cross-checks that against the raw event stream at GET /api/events?session_id={sessionId}, matching entries like APIError, SubagentStop, and failing PostToolUse calls.

The resulting report covers five angles: a count of errors and affected agents, a depth-by-depth breakdown separating failures that originated at a level from ones inherited from child agents, cascade chains such as debugger (depth 2, tool failure) → code-review (depth 1, marked error) → root (depth 0, aborted), a breakdown of error types, and a check on whether a failure stayed contained or dragged a parent down with it. If a session has no errors, the skill says so and stops rather than guessing.

It depends on the Agent Monitor dashboard being up and reachable through those two endpoints; without it running via npm start from the repo root, there's nothing to query.

What it helps with

  • locate the depth where a multi-agent failure originated
  • reconstruct the cascade chain from a failing subagent to its parent
  • separate errors that originated at a level from ones inherited below
  • spot the tool most often involved in failures
  • check whether a failure stayed contained or took down a parent agent

Example prompts for the agent

  • Find out why the last agent session ended in an error
  • Trace how the debugger subagent's failure cascaded up to root
  • Break down error types for session session-42

How to install error-propagation

1Plugin marketplace

/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-workflows@claude-code-agent-monitor-plugins

This installs the whole ccam-workflows plugin with all its skills

2Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill error-propagation -a claude-code

3Manually: put the files in place

~/.claude/skills/error-propagation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/error-propagation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about error-propagation

How to install error-propagation in Claude Code?

Through the marketplace: run /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor, then /plugin install ccam-workflows@claude-code-agent-monitor-plugins.

What does error-propagation do?

It traces failures across a multi-agent session by tree depth, showing where each error started and how it cascaded to parent agents, drawing on the workflow intelligence API and the session's event stream.

What does error-propagation need to run?

It queries a live Agent Monitor dashboard through GET /api/workflows/{sessionId} and GET /api/events?session_id={sessionId}; if the dashboard isn't reachable, it tells you to start it with npm start from the repo root.

Source text

SKILL.md · MIT
---
name: error-propagation
description: >
  Trace error propagation through a multi-agent session by agent depth — where
  failures originated, the depth at which they appeared, and how they cascaded
  up to parent agents — using the Agent Monitor workflow intelligence API and
  the session event stream. Use when a multi-agent run failed and you need to
  find the origin and blast radius of the failure.
---

# Error Propagation

Trace where a multi-agent session's failures started and how far they spread.

## Input

The user provides: **$ARGUMENTS**

A session ID. If empty, fetch `GET /api/sessions?limit=1`, but prefer the most recent session whose `status` is `error` or `abandoned`; state which one you picked.

## Data Sources

| Endpoint | Returns |
|----------|---------|
| `GET /api/workflows/{sessionId}` | The `errorPropagation` dataset: failures grouped by agent depth, with originating depth and cascade paths to parents |
| `GET /api/events?session_id={sessionId}` | The event stream — corroborate with `APIError`, `SubagentStop`, and failing `PostToolUse` events (`event_type`, `tool_name`, `summary`, `timestamp`) |

## Report Sections

### 1. Failure Summary
From `errorPropagation`: total errors, the depth where the first error originated, and how many distinct agents were affected.
`Origin depth: d · Errors: N · Agents affected: M`

### 2. Errors by Depth
| Depth | Errors originated | Errors inherited from children | Net failing agents |
|-------|-------------------|--------------------------------|--------------------|
Show whether failures concentrate deep in the tree (leaf subagents) or shallow (orchestrator).

### 3. Cascade Paths
For each originating failure, the path it propagated along:
`debugger (depth 2, tool failure) → code-review (depth 1, marked error) → root (depth 0, aborted)`
Tie each step to a concrete event from `/api/events` (event_type + tool_name + timestamp) where available.

### 4. Error Taxonomy
Break errors down by type from the event stream: `APIError` vs failing tool calls vs `SubagentStop` with error status. Note the most frequent tool involved in failures.

### 5. Containment Assessment
Whether failures were contained at the depth where they originated or leaked to parents. Name any parent that aborted solely because a child failed — a candidate for better error handling / isolation.

## Output

- Markdown tables for the depth breakdown; a fenced list for cascade paths.
- Timestamps for the first and last error.
- Cite only errors present in `errorPropagation` and the event stream; never invent failures or causes.
- If the session has no errors, say so plainly and stop.
- 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

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set155

The whole set →
concurrency-report 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. CX Codex +1 ★ 1,198repo stars fleet-runs fleet-runs — a skill for Claude Code and Codex that reads Workflow fleet run journals from the Agent Monitor and displays run status with per-agent breakdown. CX Codex +1 ★ 1,198repo stars transcript-replay transcript-replay walks Claude Code session transcripts turn-by-turn from Agent Monitor data, summarizing user prompts, assistant decisions, and tool executions. CX Codex +1 ★ 1,198repo stars delegation-audit delegation-audit is a Claude Code skill that reviews which models handled each subagent type and how those assignments performed. It flags weak results, repeated failures, and possible model mismatches. CX Codex +1 ★ 1,198repo stars issue-triager issue-triager diagnoses Claude Code Agent Monitor failures across the Express API, SQLite store, and hooks, returning concrete remediation steps. CX Codex ★ 1,198repo stars insights-advisor insights-advisor is a Claude Code subagent that examines Agent Monitor data and connects patterns across sessions. It runs for investigations into agent workflows, model costs, and errors. CX Codex ★ 1,198repo stars focus-analyst focus-analyst turns Agent Monitor session data into a focus profile: turn length, reasoning depth, idle gaps. Then it suggests 1–3 deep-work blocks for the week. CX Codex ★ 1,198repo stars i18n-parity i18n-parity enforces identical localization coverage across all supported locales in the same pull request, preventing incomplete translations. CX Codex +1 ★ 1,198repo stars

Project sponsors

Companies that keep this analytics open