model-stats

75 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By Integralist/agent-skills (GitHub) · coding · 25 stars · scanned at commit 2979675

Chart AI model usage, cost, and effort from local coding-CLI logs as an HTML page. Use when the user wants to see which providers, models, harnesses, or projects use their tokens and money over a period.

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 2 places.

.agents/skills/model-stats/Makefile, line 7@uvx pytest -q -p no:cacheprovider scripts/test_report.py
.agents/skills/model-stats/Makefile, line 10@uvx --with playwright pytest -q -p no:cacheprovider scripts/test_browser.py

Runs commands on your computer

The author does not mention this. Expected for a coding skill.

Found in 4 places.

.agents/skills/model-stats/SKILL.md, line 25python3 <skill-base-dir>/scripts/report.py <period>
.agents/skills/model-stats/scripts/report.py, line 613subprocess.run([opener, name], check=False) # noqa: S603 # fixed opener, own temp file
.agents/skills/model-stats/scripts/test_report.py, line 576with mock.patch("subprocess.run") as run:

Show 1 more

.agents/skills/model-stats/scripts/test_report.py, line 593with mock.patch("subprocess.run") as run:

Connects to the internet

The author does not mention this.

Found in 7 places.

.agents/skills/model-stats/scripts/report.py, line 31import urllib.request
.agents/skills/model-stats/scripts/report.py, line 448with urllib.request.urlopen(PRICES_URL, timeout=15) as resp:
.agents/skills/model-stats/scripts/test_report.py, line 263with mock.patch("urllib.request.urlopen") as urlopen:

Show 4 more

.agents/skills/model-stats/scripts/test_report.py, line 265urlopen.assert_not_called()
.agents/skills/model-stats/scripts/test_report.py, line 273with mock.patch("urllib.request.urlopen", side_effect=OSError("offline")):
.agents/skills/model-stats/scripts/test_report.py, line 280with mock.patch("urllib.request.urlopen", return_value=response):
.agents/skills/model-stats/scripts/test_report.py, line 288with mock.patch("urllib.request.urlopen", return_value=response), mock.patch.object(report, "PRICES_MAX_BYTES", 50):

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'model-stats' ] || [ -L ~/.agents/skills/'model-stats' ]; then echo 'A skill folder named model-stats already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Integralist/agent-skills' "$d" && git -C "$d" checkout --quiet '29796755244a6ede32c118686eb7a6a374055099' -- '.agents/skills/model-stats' && mkdir -p ~/.agents/skills && cp -R "$d"/'.agents/skills/model-stats' ~/.agents/skills/'model-stats' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'model-stats' ~/.claude/skills/'model-stats' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for Integralist/agent-skills shows the score of its lowest-scoring skill.

SkillTrust badge for Integralist/agent-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Integralist/agent-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Integralist/agent-skills/)

Score history

Date	Version	Score
2026-11-12	`2979675`	75
2026-11-08	`9ed9a4c`	75