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.
git clone --depth 1 https://github.com/shuchitajain/awesome-ai-setupWrote 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.
[](https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/diagnose-and-setup)<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/diagnose-and-setup"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/diagnose-and-setup/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.
<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/diagnose-and-setup"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/diagnose-and-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.02782 |
| Opus 5.5 | $0.00011 | $0.01113 |
| Sonnet 5.5 | $0.00006 | $0.00556 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
diagnose-and-setup 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose AI Setup
You are diagnosing the current AI development setup for this repository and producing a short, prioritized action plan.
The output is a numbered list of agents to run - specific to what's missing in this project, in the right order. Nothing more.
Step 1 - Check for Existing AI Setup Files
Check whether each of these files exists. Read the ones that do.
Global instruction files (read if present):
CLAUDE.md(root) — Claude Code.github/copilot-instructions.md— GitHub Copilot.cursor/rules/global.mdc— Cursor (current path).cursorrules— Cursor (legacy path — if found butglobal.mdcis absent, note as stale)
Architecture and context files (read if present):
ARCHITECTURE.md(root)CONTEXT.md(root)MEMORY.md(root)
Scoped instruction files:
.github/instructions/- list any.instructions.mdfiles present (GitHub Copilot).claude/rules/- list any.mdfiles present (Claude Code).cursor/rules/- list any.mdcfiles present (Cursor)
Tooling — MCP config:
Check project-level first, then user-level as fallback:
| Tool | Project-level path | User-level path |
|---|---|---|
| GitHub Copilot | .vscode/mcp.json |
~/.config/github-copilot/intellij/mcp.json (JetBrains/Android Studio) |
| Claude Code | .mcp.json (root) |
~/.claude.json (contains mcpServers key) |
| Cursor | .cursor/mcp.json |
~/.cursor/mcp.json |
For each tool detected as in use, report MCP status as one of:
- Project-level —
[path]present ✓ - User-level only — no project config found, but
[user path]exists (servers apply globally, not project-specifically — flag as a gap) - Missing — no config at either level ✗
Agentic:
AGENTS.md- note if presentworkflows/- list any workflow files present
README:
- Read
README.mdif present. Assess whether it contains real, project-specific content or is auto-generated / template boilerplate (e.g. scaffolded by a CLI tool, contains only installation placeholders, generic "Getting Started" sections with no project-specific detail, or identical to a framework's default README).
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.
- 2mo ago First seen · 238 lines · 28 tokens per session scan A 0112d73c78a0
diagnose-and-setup is an agent published in the GitHub repository shuchitajain/awesome-ai-setup (5 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 2,782 once invoked, about $0.0001 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 2026-08-31.
diagnose-and-setup compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagnose-and-setupshuchitajain/awesome-ai-setup | Agent | 5 | 5mo ago | MIT | A | 28 | Claude Code |
| apm-expertmicrosoft/apm | Agent | 4.3k | yesterday | MIT | A | 39 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 22 | Claude Code |
| Prompt Buildergithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 24 | Claude Code |
| react18-class-surgeongithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 81 | Claude Code |
| Custom Agent Foundrygithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 17 | Claude Code |
| gem-implementergithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 22 | Claude Code |