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.
npx agentmods add skills/davey2waveyy/gitgauge/skillnpx skills add Davey2Waveyy/gitgauge --skill skillgit clone --depth 1 https://github.com/Davey2Waveyy/gitgaugeWhat 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 | $0.00069 | $0.01383 |
| Opus 5 | $0.00034 | $0.00691 |
| Sonnet 5 | $0.00014 | $0.00277 |
| Haiku 4.5 | $0.00007 | $0.00138 |
Grade A, and why
gitgauge 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitGauge
Score GitHub repos for authenticity. Mirrors the GitGauge Chrome extension algorithm exactly.
The GitGauge output line is the announcement — no separate announce needed. Run the scorer first, then engage with the repo.
When to run
| Trigger | Output mode |
|---|---|
| GitHub URL appears passively in conversation | Compact one-liner, then continue |
| User asks to review / analyze a repo | Compact score + brief breakdown, then review |
User runs /gitgauge owner/repo |
Full report: sub-scores, flags, metadata |
Do not run on:
- GitHub profile URLs, org pages, gist links, issue links, PR links, or commit links
- npm package references (
@scope/package), file paths, or bareowner/repowith no GitHub URL context - Repos already scored in the current conversation
Running the scorer
python ~/.claude/skills/gitgauge/scripts/score.py owner/repo
# macOS / Linux: use python3 instead of python
With a token (removes rate limit):
python ~/.claude/skills/gitgauge/scripts/score.py owner/repo --token ghp_yourtoken
For the full report mode (parse JSON to build structured output):
python ~/.claude/skills/gitgauge/scripts/score.py owner/repo --json
Pass full GitHub URLs too — the script strips the github.com/ prefix automatically.
Output formats
Compact (passive trigger)
GitGauge: 🟢 4.1/5.0 — Likely Authentic
Standard (review / analyze trigger)
GitGauge: 🟢 4.1/5.0 — Likely Authentic
⭐ 2,400 stars 🍴 310 forks 👁 47 watchers 🐛 18 issues
Fork ratio: 12.9% | Watcher ratio: 1.96% | Issue ratio: 0.75%
Full report (/gitgauge command)
Use --json output. Show score, label, all ratios, sub-scores, flags, and metadata (language, description, topics).
Score labels
| Score | Label | Emoji |
|---|---|---|
| 1.0–1.4 | Likely Fake | 🔴 |
| 1.5–2.4 | Suspicious | 🟠 |
| 2.5–3.4 | Mixed Signals | 🟡 |
| 3.5–4.4 | Likely Authentic | 🟢 |
| 4.5–5.0 | Highly Authentic | ✅ |
What ships with it
1 file 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.
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.
- 2d ago First seen · 136 lines · 69 tokens per session scan A e573b1f5167d
gitgauge is a skill published in the GitHub repository Davey2Waveyy/gitgauge (4 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,383 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
opendia
Drive the user's real browser through OpenDia MCP (logged-in sessions, cookies, wallets, bookmarks, history). Use when automating Chrome/Firefox for social posts, form fills, multi-tab research, local webapp testing, or any task that needs the user's existing browser profile — not a disposable cloud browser.
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
browser-relay
Control the Chrome the user already has open and logged in through the Browser Relay CLI, without launching a separate automation browser or taking over the foreground tab. Use when an agent needs to work with existing sessions, cookies, extensions, SSO or intranet pages, or a browser on another machine. Prefer the…
a11y-keyboard-playwright
Write keyboard-only test variants and focus management checks using Playwright: navigation patterns, focus expectations, helpers, and file structure conventions.
parallel-subagents
When a task decomposes into independent slices — separate files, OR separate sections of ONE file — fan it out: write job files to the subagent queue and the host runs real parallel Codex workers for you. For a single file, extract per-section slice files into the queue's work/ zone, let workers polish them in…