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 skills add parisgroup-ai/imersao-ia-setup --skill project-statsgit clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-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/skills/parisgroup-ai/imersao-ia-setup/project-stats)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/project-stats"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/project-stats/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/skills/parisgroup-ai/imersao-ia-setup/project-stats"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/project-stats.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 | $0.00154 | $0.01656 |
| Opus 5 | $0.00077 | $0.00828 |
| Sonnet 5 | $0.00031 | $0.00331 |
| Haiku 4.5 | $0.00015 | $0.00166 |
Grade A, and why
project-stats 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 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.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Stats Report
Generate a comprehensive, comparable project statistics report. Works on any git project.
How It Works
- Run the bundled collection script to gather raw data
- Save the JSON report to
.claude/reports/ - Find the most recent previous report (if any)
- Compare and present a formatted markdown report with trend indicators
Step 1: Collect Statistics
Run the bundled collection script from the project root:
bash <skill-path>/scripts/collect-stats.sh
Capture the JSON output. The script auto-detects:
- Languages: TypeScript, JavaScript, Python, Go, Rust, PHP, Java, Swift, Kotlin, CSS
- Monorepo: Turborepo, Lerna, Nx, pnpm workspaces
- Frameworks: Next.js, Vite, Nuxt, Angular, SvelteKit, Astro, Expo, FastAPI, Django, Rails
- Tests:
.spec.*,.test.*,test_*.py, E2E files - Git: commits, contributors, branches, tags, velocity, conventional commit types, AI collab ratio
- Dependencies: npm, pip, go modules
- Quality: TODOs, FIXMEs
- i18n: keys, locales
Step 2: Save the Report
Save the JSON output to .claude/reports/project-stats-YYYY-MM-DD.json in the project root. Create the directory if it doesn't exist.
If a report for today already exists, overwrite it (same-day re-runs update rather than duplicate).
Step 3: Find Previous Report
Look in .claude/reports/ for the most recent project-stats-*.json file that is NOT today's report. Read it for comparison.
If the project has a custom metrics script (like pnpm dev:metrics --save or similar), also check those output directories for additional historical data.
Step 4: Format the Report
Present the report in this structure. The comparison column only appears when a previous report exists.
Report Template
# 📊 Project Statistics Report
**Project:** {name}
**Date:** {date}
**Previous report:** {previous_date or "First report"}
---
## Overview
| Metric | Current | Previous | Delta |
|--------|---------|----------|-------|
| Source files | X | Y | ↑ +Z (+N%) |
| Lines of code | X | Y | ↓ -Z (-N%) |
| Test files | X | Y | → 0 |
| Git commits (total) | X | Y | ↑ +Z |
| Contributors | X | | |
## Language Breakdown
| Language | Files | LOC | % of Total |
|----------|-------|-----|------------|
| TypeScript | X | Y | Z% |
| ... | | | |
## Git Activity
| Metric | Value |
|--------|-------|
| Commits today | X |
| Commits this week | X |
| Commits this month | X |
| Branches | X |
| Tags | X |
| Dirty files | X |
| Unpushed commits | X |
### Commit Types (Last 30 days)
| Type | Count | Bar |
|------|-------|-----|
| feat | X | ████████ |
| fix | X | ██████ |
| ... | | |
### AI Collaboration
| Metric | Value |
|--------|-------|
| AI-assisted commits (30d) | X |
| AI collab ratio | X% |
## Weekly Velocity
| Metric | Current | Previous | Delta |
|--------|---------|----------|-------|
| Lines added | X | Y | |
| Lines removed | X | Y | |
| Net lines | X | Y | |
## Testing
| Metric | Current | Previous | Delta |
|--------|---------|----------|-------|
| Unit test files | X | Y | |
| E2E test files | X | Y | |
| Total test files | X | Y | |
## Dependencies
| Source | Production | Dev |
|--------|-----------|-----|
| npm | X | Y |
| Python | X | |
| Go | X | |
## Infrastructure
| Property | Value |
|----------|-------|
| Monorepo | Yes/No |
| Tool | Turborepo / Lerna / etc |
| Workspaces | X |
| Frameworks | Next.js, FastAPI, etc |
| Dockerfiles | X |
| Docker Compose | Yes/No |
## Code Quality
| Metric | Current | Previous | Delta |
|--------|---------|----------|-------|
| TODOs | X | Y | |
| FIXMEs/HACKs | X | Y | |
## i18n (if applicable)
| Metric | Value |
|--------|-------|
| Translation keys | X |
| Locales | pt-BR, en-US, ... |
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.
- 11d ago First seen · 194 lines · 154 tokens per session scan A 01326e863c22
project-stats is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 154 tokens to every session and 1,656 once invoked, about $0.0008 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
commit-message-generator
Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification, and appends the Assisted-by git trailer recording which AI model (Claude, GPT, Gemini, or any…
drupalorg-contribution-helper
Quick help with drupal.org contribution workflows including git commands, branch naming, issue fork setup, and merge request creation. Invoke when user asks "how do I contribute to drupal.org?", "drupal.org git workflow", "issue fork", "drupal merge request", or needs help with git.drupalcode.org commands.
pr-create
Generate a PR description and create a GitHub pull request. Invoke when user wants to create a pull request, says "create a PR", "submit a PR", "open a pull request", or uses /pr-create. Requires user confirmation before creating the PR (irreversible GitHub action). Supports ticket numbers and --concise mode.
pr-release
Generate changelog entries, a deployment checklist, and update a release PR description. Invoke when user asks to prepare a release, generate a changelog, create a deployment checklist, or uses /pr-release. Requires user confirmation before updating the PR (modifies publicly visible content). Supports version numbers…
worktree-manager
Create, list, and tear down git worktrees following Kanopi's branch naming conventions so developers and agents can work multiple tickets in parallel without clobbering each other's working tree. Handles DDEV isolation automatically (folder-derived project name, no pinned ports) for Drupal and WordPress, and plain…
drupal-contribute
Full drupal.org contribution workflow — create an issue and set up a merge request together. Invoke when user wants to contribute to a Drupal module, says "contribute to drupal.org", "create a drupal.org issue and MR", or uses /drupal-contribute. Requires user interaction at two manual steps (CAPTCHA-protected issue…