agent-performance-triage

agent-performance-triage is a skill for Claude Code, Codex from microsoft/cat-agent-skills. It costs 104 tokens per session (2,238 once invoked), scanned A, original, MIT.

A review process for a live Microsoft Copilot Studio agent, Microsoft’s tool for building conversational business agents. It uses usage data and conversation transcripts to find where the agent is failing and creates a ranked list of improvements.

In plain words
What is it for?
Investigating unanswered questions, weak resolutions, escalations, abandoned sessions, and knowledge gaps, then preparing a practical improvement backlog and tracking changes over time.
Why use it?
Passing pre-launch tests does not show why an agent may perform poorly with real users. This helps connect low resolution or engagement to specific topics, information sources, or tools.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Good fit Investigating unanswered questions, weak resolutions, escalations, abandoned sessions, and knowledge gaps, then preparing a practical improvement backlog and tracking changes over time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/cat-agent-skills/agent-performance-triage
About the project

microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.

microsoft/cat-agent-skills · 64 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.

Any agent
npx skills add microsoft/cat-agent-skills --skill agent-performance-triage
Clone the repo
git clone --depth 1 https://github.com/microsoft/cat-agent-skills

Made for: Claude Code, Codex.

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 agent-performance-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/agent-performance-triage.svg)](https://agentmods.dev/skills/microsoft/cat-agent-skills/agent-performance-triage)
Your own site
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/agent-performance-triage"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/agent-performance-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,238 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00104 $0.02238
Opus 5 $0.00052 $0.01119
Sonnet 5 $0.00021 $0.00448
Haiku 4.5 $0.00010 $0.00224

Measured 8d ago against content hash 254239bf6f6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-performance-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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cluster_queries.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

submissions/agent-performance-triage/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Performance Triage

An agent that passed its test plan can still fail in production, and the failure modes look nothing like test failures. Analytics tell you that something is wrong; this skill works out what and where, and hands back a backlog an owner can actually execute.

Run it two weeks after launch, then monthly.

Scope

In scope: metric interpretation, root-cause diagnosis, unanswered-question mining, topic and knowledge gap analysis, prioritized backlog, trend tracking across runs, stakeholder readout.

Out of scope: editing the agent, publishing changes, reading production transcripts that have not been de-identified or that the user is not authorized to share, cost analysis (a separate concern), pre-launch test design.

Step 1 — Collect the evidence

Ask for whatever is available. The skill degrades gracefully — say which conclusions are weakened by missing inputs rather than guessing.

Minimum viable input: the Copilot Studio analytics summary for a stated period (engagement rate, resolution rate, escalation rate, abandon rate, total sessions, CSAT if collected) plus the top unresolved or unanswered queries list.

Better input, in order of value:

  1. Session transcripts export for the period — the single highest-value input
  2. Per-topic breakdown: sessions, resolution, escalation, abandonment by topic
  3. The agent's topic list with trigger phrases, and the knowledge source inventory
  4. Tool and action failure telemetry
  5. Comparison period, so trends can be read rather than just levels
  6. Any human-channel data the agent deflects into (ticket volumes, live chat handovers)

Before you read transcripts: confirm they are de-identified or that the user is authorized to share them. If they contain personal data and no de-identification has happened, stop and say so — sample counts and query clusters can often be produced without exposing message bodies.

Step 2 — Read the metrics as a funnel, not a scorecard

Levels in isolation mean little. Read them as a chain, and find the first link that breaks — fixing a downstream metric while an upstream one is broken wastes a sprint.

Read the full file on GitHub · 200 lines

Files

What ships with it

3 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. 8d ago First seen · 200 lines · 104 tokens per session scan A 254239bf6f6b

Subscribe to this mod's changes

agent-performance-triage is a skill published in the GitHub repository microsoft/cat-agent-skills (64 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 2,238 once invoked, about $0.0005 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

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens