optimize-ai-setup SKILL.md skillA

optimize-ai-setup from mgiovani/cc-arsenal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mgiovani/cc-arsenal/optimize-ai-setup@git:20261005.b620662

Pins git:20261005.b620662 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mgiovani/cc-arsenal
Path
skills/optimize-ai-setup/SKILL.md
Versions recorded
3
Latest version
git:20261005.b620662, committed Oct 5, 2026
First version recorded
Sep 25, 2026
Size
7,059 bytes
Repository stars
8
License
MIT

Audits the AI coding setup on this machine (Claude Code, Codex CLI and app, Cursor, Antigravity, Gemini CLI, Claude Desktop) for token waste and quality drag, then ranks the fixes. A deterministic local script measures real session logs and configs (startup context size, prompt-cache hit rate and rebuilds, oversized CLAUDE.md/AGENTS.md, duplicate or unused skills, plugins and MCP servers, stale env settings, model and effort mix) without reading message content or secrets, so the audit itself…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Optimize AI Setup

Measure first, then advise. A local script collects every number from configs and session logs; the model reads only its compact report plus the catalog entries for the findings that fired.

## Token rules for this skill

- Run the collector once per audit. Do not open transcripts, session logs, SQLite stores, or whole config files: the script already read them, safely and with size caps.
- Read `references/checks.md` only by ID (the `awk` range below), only for findings being presented.
- Answer with a short snapshot and a ranked fix table. Do not restate the whole report.

## Step 1: Collect evidence

From the user's project directory, run the collector (`<skill-dir>` is this skill's directory):

```bash
uv run <skill-dir>/scripts/collect.py --days 14
```

Without `uv`, use `python3 <skill-dir>/scripts/collect.py` (Python 3.11+). Flags: `--days N` (lookback window), `--project PATH`, `--all` (every finding, not just the top 15), `--json`.

- `no harness detected`: say so and stop.
- A harness line showing `error:`: mention it and continue with the others.

## Step 2: Explain the top findings
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mgiovani/cc-arsenal/optimize-ai-setup@sha256:e5c02d3df79192c5

The line at the top of this page pins the label git:20261005.b620662, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wfq5mnpb5swkjc3s.svg)](https://markdownregistry.com/a/art_wfq5mnpb5swkjc3s)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 25, 2026 and Oct 5, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261005.b620662 latest2026-10-05 b620662 7,059 BA view · diff
git:20260930.1cc75182026-09-30 1cc7518 7,174 BA view · diff
git:20260925.69567812026-09-25 6956781 6,816 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7059 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

mgiovani/cc-arsenal · 8 stars · license MIT · pushed 2026-10-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wfq5mnpb5swkjc3s
GET https://markdownregistry.com/api/v1/resolve?ref=mgiovani/cc-arsenal/optimize-ai-setup
GET https://markdownregistry.com/api/v1/blob/e5c02d3df79192c5247d6a4c342d95754d1391d2262de4a610356e1fe0d40ce0

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from mgiovani/cc-arsenal

AGENTS.md AGENTS.md file
mgiovani/cc-arsenal · AGENTS.md
git:20261005.b0bf138 · audit A · 8 stars
CLAUDE.md CLAUDE.md file
mgiovani/cc-arsenal · CLAUDE.md
git:20260924.a80f9cd · audit B · 8 stars
CLAUDE.md@examples/claude-md/bash CLAUDE.md file
mgiovani/cc-arsenal · examples/claude-md/bash/CLAUDE.md
git:20260925.ca015cc · audit A · 8 stars
CLAUDE.md@examples/claude-md/fastapi CLAUDE.md file
mgiovani/cc-arsenal · examples/claude-md/fastapi/CLAUDE.md
git:20260925.ca015cc · audit A · 8 stars
CLAUDE.md@examples/claude-md/nodejs CLAUDE.md file
mgiovani/cc-arsenal · examples/claude-md/nodejs/CLAUDE.md
git:20260925.ca015cc · audit A · 8 stars
CLAUDE.md@examples/claude-md/reactjs CLAUDE.md file
mgiovani/cc-arsenal · examples/claude-md/reactjs/CLAUDE.md
git:20260925.ca015cc · audit A · 8 stars
llms.txt@scripts/tests/fixtures/anything_to_skill/web llms.txt file
mgiovani/cc-arsenal · scripts/tests/fixtures/anything_to_skill/web/llms.txt
git:20260930.e89382d · audit A · 8 stars
agent-browser SKILL.md skill
mgiovani/cc-arsenal · skills/agent-browser/SKILL.md · Headless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and…
git:20261005.b620662 · audit A · 8 stars
anything-to-skill SKILL.md skill
mgiovani/cc-arsenal · skills/anything-to-skill/SKILL.md · Turns a docs site, local folder, PDF or book, YouTube video, playlist or channel, or a topic into a source-grounded…
git:20261005.b620662 · audit A · 8 stars
ci-generate SKILL.md skill
mgiovani/cc-arsenal · skills/ci-generate/SKILL.md · Generate a production-ready CI/CD pipeline config (GitHub Actions,
v1.0.0 · audit A · 8 stars
ci-local SKILL.md skill
mgiovani/cc-arsenal · skills/ci-local/SKILL.md · Run the checks a GitHub Actions workflow would run, locally, when Actions
git:20261005.b620662 · audit A · 8 stars
clotho-research SKILL.md skill
mgiovani/cc-arsenal · skills/clotho-research/SKILL.md · Find what a change will actually touch before planning it — the existing
v1.0.0 · audit A · 8 stars

Every file in mgiovani/cc-arsenal

Browse by kind, by grade A, or by owner.