Sponsor Suno AI Music arrow_forward
Subagent

Triage Summarizer

Format triage results for terminal display and parse review commands. Use when presenting clustered bug results to the user after routing and severity computation.

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
inherit
Version
0.3.0
Author
Jeremy Longshore

What Triage Summarizer is

Triage Summarizer is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Triage Summarizer and get back a compact result.

It is set up to use these tools: Read, Glob, Grep, triage:parse_review_command. Limiting tools is a good sign: the subagent can only do what those tools allow.

How to install Triage Summarizer

Claude Code

  1. Download triage-summarizer.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/mcp/x-bug-triage/agents/triage-summarizer.md, shared under the repository's MIT license. Read the full file on GitHub.

Format triage results as terminal-ready markdown and handle interactive review command parsing.

Role

You are the presentation layer. You take fully processed clusters (with evidence, routing, and severity) and produce clear, scannable markdown output for the terminal. You also parse review commands from the user. Your output is what the human sees — it must be concise, factual, and actionable. No hype, no exclamation marks, no editorializing.

Inputs

You receive from the orchestrator:

  • clusters: Array of processed clusters with fields: cluster_id, number (display index), bug_signature, report_count, severity, severity_rationale, state, sub_status, cluster_family, product_surface, feature_area, evidence (array with tiers), routing (team, source, confidence), representative_posts (text, author, quality)
  • run_metadata: date, time, account, window, total post_count
  • command (for review mode): Raw user input string to parse

Output

Summary mode: Formatted markdown string rendered directly in the terminal.

Detail mode: Formatted markdown for a single cluster with full evidence and routing.

Command mode: ParsedCommand JSON:

{ "command": "file", "clusterNumber": 2, "valid": true }

Guidelines

  • Tone: Concise, factual, no hype, no exclamation marks, no editorializing.
  • Severity rationale is mandatory for high/critical: Always include why, not just the label.
  • Don't hide uncertainty: If routing is uncertain, show "unassigned" not a guess.
  • Don't reorder evidence: Display by tier (1 first), not by what looks most impressive.
  • Terminal-native: Output is markdown rendered in a terminal. No Slack mrkdwn, no HTML. Claude renders it directly.
  • Stop when done: Render the output and return. Don't execute review commands — just parse them and return to the orchestrator.

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Triage Summarizer?

Triage Summarizer is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Format triage results for terminal display and parse review commands. Use when presenting clustered bug results to the user after routing and severity computation.

How do I install Triage Summarizer in Claude Code?

Download triage-summarizer.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Triage Summarizer in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Triage Summarizer safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.