A task-triage workflow for classifying a coding request before other agents work on it. It estimates complexity, affected systems, and verification needs, then writes the result to a workspace JSON file.

Use it at the start of a team task to classify bugs, features, refactors, or exploration work, trace likely impact, and choose a verification strategy.

It limits the initial investigation and gives later work a consistent basis for choosing phases, agents, and checks.

triage — Skill for Claude Code by dyCuong03/unity-agent-team

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/dyCuong03/unity-agent-team

agentmods

npx agentmods add skills/dycuong03/unity-agent-team/triage

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/triage/github.svg)](https://agentmods.dev/skills/dycuong03/unity-agent-team/triage)

Your own site

<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/triage"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/triage"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,865 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.01865
Opus 5.5	$0.00018	$0.00746
Sonnet 5.5	$0.00009	$0.00373
Haiku 4.5	$0.00004	$0.00186

Measured 11d ago against content hash e0b4a40b84ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 11d 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/skills/triage/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Skill

The triage agent runs ONCE per /team invocation, before any other agent. It is the only agent that always runs. Everything downstream is derived from its output.

Goal

Produce workspace/triage.json matching .claude/schemas/triage.schema.json in under 8 file reads.

Inputs

<intent> from the user (bug | feature | refactor | explore)
<depth> from the user (quick | normal | deep — default normal)
<task description> free text
CRG MCP (code-review-graph) — preferred
ai-game-developer MCP — optional

Procedure

CRG first. No file reads until graph evidence exists.
- get_architecture_overview if domain unknown
- trace_execution_flow from task keywords
- get_impact_radius → seed systems_affected and files_touched_estimate
Fingerprint up to 5 touched files for API evidence (see .claude/docs/rules/api-fingerprinting-system.md).
- Compute DOTS_score / Unity_score / Hybrid_score (see .claude/docs/rules/domain-scoring-engine.md).
- Classify domain. If Ambiguous → confidence_score ≤ 0.5.
Classify complexity using the rubric below.
Pick verification strategy:
- bundle — tiny: deterministic verification bundle, no agent
- verifier — small/medium: verifier agent runs the bundle
- tester — large/critical: full tester agent
- stepgated — refactor only
Partition ownership when the pipeline has more than one writer (data-tool plus unity-dev, or stepgated refactor). Use repo-root-relative globs. When in doubt: assign only unity-dev (no parallelism).
Emit workspace/triage.json via python .claude/scripts/triage.py. That helper writes a schema-valid file; do not hand-write the JSON.

Complexity Rubric

Complexity	Files	Systems	Blast radius	Pipeline (default)
tiny	1	1	isolated	`[unity-dev]`
small	1–3	1	local	`[unity-dev, verifier]`
medium	2–5	1–3	local / multi-system	`[architect, unity-dev, verifier]`
large	5–15	3–6	multi-system	`[architect, unity-dev, tester]`
critical	>15 OR save/multiplayer/economy/world-init	any	cross-cutting	`[architect, unity-dev, data-tool, tester]`

Read the full file on GitHub · 170 lines

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.

11d ago First seen · 170 lines · 44 tokens per session scan A e0b4a40b84ca

Subscribe to this mod's changes

triage is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,865 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Planning

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens