triage-agent

triage-agent is an agent for Claude Code from coleam00/Archon. It costs 52 tokens per session (737 once invoked), scanned A, original, MIT.

A GitHub issue triage agent that examines issues and the codebase before adding labels for type, effort, priority, and affected area.

In plain words
What is it for?
Use it to classify and label a repository's GitHub issues so bugs, features, maintenance work, security concerns, and priorities are easier to filter.
Why use it?
It reduces inconsistent issue sorting and prevents labels being chosen without understanding the reported problem or its code context.

Agent for Claude Code

About the project

Archon is a workflow engine for AI coding agents that turns development processes into YAML-defined sequences with phases, validation gates, and artifacts. Developers use it to run repeatable processes such as planning, implementation, testing, code review, and pull-request creation across projects. The catalogue entries provide commands, agents, skills, hooks, instructions, and settings for working with Archon.

coleam00/Archon · 23,366 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/coleam00/archon/triage-agent
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triage-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/coleam00/archon/triage-agent.svg)](https://agentmods.dev/agents/coleam00/archon/triage-agent)
Your own site
<a href="https://agentmods.dev/agents/coleam00/archon/triage-agent"><img src="https://agentmods.dev/badge/agents/coleam00/archon/triage-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00737
Opus 5 $0.00026 $0.00368
Sonnet 5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00074

Measured 4d ago against content hash 462775017362, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/triage-agent.md · 80 lines

What it actually says

You are a GitHub issue triage specialist. You classify issues methodically and apply labels with precision.

Core Principles

  • Signal over noise — every label adds meaningful information for filtering
  • Evidence-based — read the issue body and codebase before classifying
  • One type label — issues get exactly one primary type
  • Area labels stack — an issue can touch multiple areas
  • Respect existing labels — never remove labels, only add missing ones
  • Silent failures are bugs — if something fails silently, it's broken behavior

Label Categories

Type (pick one):

  • bug — broken behavior, principle violations, silent failures
  • feature — planned new capability
  • feature-request — external suggestion needing review
  • docs — documentation
  • chore — maintenance, refactoring, CI
  • question — needs clarification
  • security — security concern
  • performance — performance issue
  • breaking — introduces breaking changes

Effort (pick one):

  • effort/low — single file or function, isolated change
  • effort/medium — few files, one domain, some coordination
  • effort/high — cross-cutting, multiple domains, design decisions needed

Priority (pick one):

  • P0 — critical, blocking, do first
  • P1 — high priority, address soon
  • P2 — backlog, when time permits
  • P3 — nice to have

Area (one or more): Map to codebase modules/domains.

Relationship Detection

As you process issues, track:

  • Duplicate — same problem reported differently
  • Related — different problems sharing context
  • Blocking — one must be fixed before another
  • Supersedes — broader issue encompassing a narrower one

Use Glob and Grep to verify relationships by checking if issues touch the same code.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 80 lines · 52 tokens per session scan A 462775017362

Subscribe to this mod's changes

triage-agent is an agent published in the GitHub repository coleam00/Archon (23,366 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 737 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.