agent-experience-audit

agent-experience-audit is a skill for Claude Code, Codex from Pattyboi101/oats-autonomous-agents. It costs 35 tokens per session (797 once invoked), scanned A, original, MIT.

A review of an MCP server, a service that lets AI agents use external tools, from the agent's point of view.

In plain words
What is it for?
Use it to test search queries, inspect tool responses, check installation details, and evaluate first-time use.
Why use it?
It reveals whether searches return relevant results, tool details are useful, and a new user can understand the service after installing it.

Skill for Claude CodeCodex

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

Good fit Use it to test search queries, inspect tool responses, check installation details, and evaluate first-time use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pattyboi101/oats-autonomous-agents/agent-experience-audit
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 Pattyboi101/oats-autonomous-agents --skill agent-experience-audit
Clone the repo
git clone --depth 1 https://github.com/Pattyboi101/oats-autonomous-agents

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-experience-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit/github.svg)](https://agentmods.dev/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit)
Your own site
<a href="https://agentmods.dev/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit/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.

agentmods 80×15 button for agent-experience-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/agent-experience-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 797 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00035 $0.00797
Opus 5 $0.00017 $0.00398
Sonnet 5 $0.00007 $0.00159
Haiku 4.5 $0.00003 $0.00080

Measured 11d ago against content hash 7ae47aa35f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-experience-audit scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

import urllib.request, json
skills/agent-experience-audit/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Experience Audit — MCP Dept

You audit what AI agents see when they use Your Project's MCP server. Your goal is to ensure every interaction is obviously better than a raw web search.

Before Starting

  • Is production up? Check /health endpoint
  • Is SSH available? Try a quick fly ssh command
  • What's the context? (New registry listing, post-outreach, routine check)

How This Skill Works

Mode 1: Search Quality Audit

Test the top 5 search queries (auth, analytics, payments, email, database). For each: is the top result relevant? Does it have install_command? Is the tagline useful?

Mode 2: Tool Detail Audit

Pick specific tools (e.g. the 13 we emailed) and check their full detail response. Are descriptions accurate? Are migration signals present? Are compatible tools shown?

Mode 3: First-Install Experience

Simulate a developer who just installed from Smithery/Glama. What's their first query? What do they see? Would they keep using us?

Audit Checklist

Per Search Query

Check Pass Fail
Top result is relevant to query? Auth → auth tool Auth → Airflow
Top result has install_command? npm install X Empty
Top result has useful tagline? Describes what it does Truncated or generic
Category is correct? Analytics → Analytics Analytics → AI & Automation
Migration signal present? "14 repos migrated from X" Empty (acceptable if no data)

Per Tool Detail

Check Pass Fail
Description > tagline? Full paragraph Same as tagline
Install command correct? Matches actual package Wrong package entirely
Migration data present? Gaining/losing signals Empty (check sdk_packages mapping)
Verified combos present? "Works with X in N repos" Empty
Trust tier shown? "New/Tested/Verified" Missing

Query via Production

# Search test
~/.fly/bin/fly ssh console -a your-project -C 'python3 -c "
import urllib.request, json
r = urllib.request.urlopen(\"http://localhost:8080/api/tools/search?q={query}&limit=5\")
data = json.loads(r.read())
for t in data.get(\"tools\", []):
    print(t.get(\"slug\") + \": \" + str(t.get(\"migration_signal\", \"no signal\")))
"'

Read the full file on GitHub · 77 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.

  1. 11d ago First seen · 77 lines · 35 tokens per session scan A 7ae47aa35f75

Subscribe to this mod's changes

agent-experience-audit is a skill published in the GitHub repository Pattyboi101/oats-autonomous-agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 797 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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