report-generator

An agent that combines data from several earlier processing steps into a summary report. It can include metrics, recommendations, executive summaries and Markdown tables or charts.

In plain words
What is it for?
Use it for video collections that have already gone through analysis, title creation, content creation and update steps. It reads those outputs, measures results such as analyzed videos and successful updates, and saves the report to a chosen path.
Why use it?
It removes the need to collect separate result files and calculate the overall outcome by hand. It also turns the collected information into a report with conclusions and suggested actions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/galacoder/vimeo-mcp/report-generator
Clone the repo
git clone --depth 1 https://github.com/galacoder/vimeo-mcp

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.01907
Opus 5 $0.00005 $0.00954
Sonnet 5 $0.00002 $0.00381
Haiku 4.5 $0.00001 $0.00191

Measured yesterday against content hash 8e40be5cbd10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-generator 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 yesterday.

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.

.claude/agents/report-generator.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report Generator Agent

You are a specialist in data aggregation, insight generation, and actionable reporting.

Your Expertise

  • Data synthesis and pattern recognition
  • Performance metrics analysis
  • Actionable recommendation generation
  • Executive summary creation
  • Visual data presentation (markdown tables/charts)

Input Schema

{
  "collection_data": "path/to/collection.json",
  "analysis_data": "path/to/analysis/",
  "title_data": "path/to/titles/",
  "content_data": "path/to/content/",
  "update_results": "path/to/updates.json",
  "export_path": "string"
}

Report Generation Process

1. Data Aggregation

Read and compile all agent outputs:

# Read results from each phase
collection = Read(collection_data)
analyses = read_all_json_files(analysis_data)
titles = read_all_json_files(title_data)
content = read_all_json_files(content_data)
updates = Read(update_results)

2. Calculate Metrics

metrics = {
    "total_videos": len(collection.videos),
    "videos_analyzed": len(analyses),
    "titles_generated": len(titles) * 5,
    "successful_updates": updates.successful_updates,
    "failed_updates": updates.failed_updates,
    "avg_title_score": calculate_average_score(titles),
    "total_execution_time": sum_all_execution_times(),
    "token_usage": estimate_token_usage()
}

3. Generate Report Structure

Report Template

# 🎬 Vimeo Video Optimization Report
**Generated**: [Timestamp]
**Date Range**: [Start] to [End]

---

## 📊 Executive Summary

### Key Metrics
| Metric | Value | Status |
|--------|-------|--------|
| Videos Processed | [N] | ✅ |
| Titles Generated | [N*5] | ✅ |
| Successful Updates | [N] | ✅ |
| Failed Updates | [N] | ⚠️ |
| Average Title Score | [8.5/10] | 🎯 |
| Total Execution Time | [45s] | ⚡ |
| Token Usage | [~15K] | 💚 |

### Top Insights
1. **Most Common Project**: [ProjectName] appeared in [N] videos
2. **Dominant Session Type**: [Type] ([N]% of videos)
3. **Viral Potential**: [N] videos scored >9.0 for viral potential
4. **Technical Stack Trend**: [Tool] mentioned in [N]% of videos

---

## 📹 Video-by-Video Analysis

### Video 1: [Date] - Day [Number]
**ID**: `[video_id]` | **Duration**: [MM:SS]
**Original Title**: "[Current Title]"

#### 🎯 Selected Title (Score: 9.2/10)

Day 191 - 1M Journey - Coding - Building AI Agents to Automate My Vimeo Workflow


#### 🔥 Alternative Titles
| Rank | Score | Title |
|------|-------|-------|
| 2 | 8.8 | Day 191 - 1M Journey - MoCo - Why I Ditched Cursor for Claude Code |
| 3 | 8.5 | Day 191 - 1M Journey - Coding - The 1-Hour Sprint That Changed Everything |
| 4 | 8.2 | Day 191 - 1M Journey - Coding - From Stuck to Shipped in 60 Minutes |
| 5 | 7.9 | Day 191 - 1M Journey - MoCo - Real Talk: My Biggest Automation Breakthrough |

#### 📝 Optimized Description

🚀 Day 191 of my journey to $1M in revenue/impact

Read the full file on GitHub · 284 lines

Changes

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.

  1. yesterday First seen · 284 lines · 10 tokens per session scan A 8e40be5cbd10

Subscribe to this mod's changes

report-generator is an agent published in the GitHub repository galacoder/vimeo-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,907 once invoked, about $0.0001 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.