auto-triage

auto-triage is a skill for Claude Code from A7um/zero-review. It costs 28 tokens per session (758 once invoked), scanned A, original, MIT.

An issue-intake process that classifies incoming reports, finds duplicates, sets priorities, and turns selected issues into actionable work items. Triage means deciding what needs attention and in what order.

In plain words
What is it for?
Use it to process batches of bug reports or feature requests, group related issues, explain priority decisions, and dispatch work to developers.
Why use it?
It prevents duplicate work and makes priorities depend on impact rather than on who reported the issue.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zero-review plugin — 5 skills, 9 commands, 1 hook shipped together

Good fit Use it to process batches of bug reports or feature requests, group related issues, explain priority decisions, and dispatch work to developers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a7um/zero-review/auto-triage
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.

Any agent
npx skills add A7um/zero-review --skill auto-triage
Clone the repo
git clone --depth 1 https://github.com/A7um/zero-review

Made for: Claude Code.

Or install zero-review, the plugin that ships this one along with the rest of its 5 skills, 9 commands, 1 hook.

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 auto-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/a7um/zero-review/auto-triage.svg)](https://agentmods.dev/skills/a7um/zero-review/auto-triage)
Your own site
<a href="https://agentmods.dev/skills/a7um/zero-review/auto-triage"><img src="https://agentmods.dev/badge/skills/a7um/zero-review/auto-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00028 $0.00758
Opus 5 $0.00014 $0.00379
Sonnet 5 $0.00006 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 7d ago against content hash 682c41b13916, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

auto-triage 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 7d 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.

skills/auto-triage/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Triage Skill

WHEN TO USE: You have incoming issues (from user agents, GitHub, or any external source) that need to be classified, deduplicated, prioritized, and turned into actionable work items for dev agents.

Triage Philosophy

Every issue deserves classification. Not every issue deserves action. Your job is to tell the difference.

Intake first, react later — Read all pending issues before acting on any one of them. Batch processing reveals duplicates and patterns that one-at-a-time processing misses.

Classify by impact, not by reporter — A novice user's confused bug report may describe a critical usability failure. A power user's detailed feature request may be low priority. Assess the issue, not the source.

Duplicates are the silent killer — Two issues about the same root cause dispatched to two dev agents means double the work and potential conflicts. Deduplication is not optional housekeeping — it's a core function.

Prioritize transparently — Every priority assignment must have a stated rationale. "P1 because it blocks checkout for all users" is useful. "P1" alone is not. The sponsor and dev agents need to understand why, not just what.

Dispatch self-contained work — A dev agent receiving a work item should be able to start immediately. If they need to read five other issues to understand context, the work item is incomplete.

Workflow

  1. Intake — Normalize incoming issues to contracts/issue.md format (if not already)
  2. Deduplicate — Group issues by likely root cause (see rules/deduplication.md)
  3. Classify — Map each unique issue to a type and paradigm (see rules/classification.md)
  4. Prioritize — Assign priority with rationale (see rules/prioritization.md)
  5. Dispatch — Produce work items following contracts/work-item.md

Steps 2-4 may interleave — discovering a duplicate during classification is normal.

What Triage Agents Get Wrong

  • Triage as implementation — Starting to debug or fix the issue while triaging it. You're a dispatcher, not a developer. Classify and move on.

Read the full file on GitHub · 59 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 59 lines · 28 tokens per session scan A 682c41b13916

Subscribe to this mod's changes

auto-triage is a skill published in the GitHub repository A7um/zero-review (45 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 758 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens