metrics-analysis

metrics-analysis is a command for GitHub Copilot from rjmurillo/ai-agents. It costs 0 tokens per session (623 once invoked), scanned A, original, MIT.

A command for examining pull request statistics, such as review wait time, changed files, comments, and time from first commit to merge. It uses this information to identify workflow problems.

In plain words
What is it for?
Use it to analyze a CSV of pull request data, compare review timings, and find opportunities to improve the development process.
Why use it?
It helps reveal slow reviews, lengthy review cycles, unusually large changes, and comment patterns that may signal unclear or under-tested work.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

Good fit Use it to analyze a CSV of pull request data, compare review timings, and find opportunities to improve the development process.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rjmurillo/ai-agents/metrics-analysis
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.

Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for metrics-analysis

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjmurillo/ai-agents/metrics-analysis.svg)](https://agentmods.dev/commands/rjmurillo/ai-agents/metrics-analysis)
Your own site
<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/metrics-analysis"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/metrics-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 623 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00623
Opus 5 $0.00000 $0.00311
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured yesterday against content hash 869b086348e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

metrics-analysis 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.

.github/prompts/metrics-analysis.prompt.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Metrics Analysis

You are analyzing pull request metrics to identify opportunities for improving the development workflow.

Context

The CSV data contains PR metrics with these columns:

  • PR: Pull request number
  • Commits: Number of commits in the PR
  • Additions/Deletions: Lines of code changed
  • Changed Files: Number of files modified
  • Time to First Review: Time from PR creation to first review
  • Comments: Number of review comments
  • Participants: Number of people involved
  • Feature Lead Time: Total time from first commit to merge
  • First to Last Review: Duration of the review process
  • First Approval to Merge: Time from approval to merge

Analysis Focus

1. Time to First Review

  • Identify PRs with unusually long wait times
  • Calculate average and median time to first review
  • Flag if average exceeds 4 hours during business days

2. Review Comment Density

  • High comment counts may indicate insufficient pre-review testing, missing documentation, or complex changes without context
  • Target: fewer than 5 comments per PR average

3. First to Last Review Duration

  • Long review cycles suggest scope creep during review, unclear requirements, or insufficient initial feedback
  • Target: Complete reviews within 24 hours

4. First Approval to Merge Time

  • Long delays after approval indicate merge conflicts, CI pipeline issues, or manual merge bottlenecks
  • Target: Merge within 2 hours of approval

5. PR Size Correlation

  • Analyze if larger PRs correlate with more comments, longer review times, or more participants
  • Recommendation threshold: fewer than 500 lines per PR

Required Output Format

Summary Statistics

Metric Value Target Status
Avg Time to First Review HH:MM <4h [PASS]/[WARNING]/[FAIL]
Avg Comments per PR N <5 [PASS]/[WARNING]/[FAIL]
Avg Review Duration HH:MM <24h [PASS]/[WARNING]/[FAIL]
Avg Approval to Merge HH:MM <2h [PASS]/[WARNING]/[FAIL]

Read the full file on GitHub · 88 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 · 88 lines · 0 tokens per session scan A 869b086348e0

Subscribe to this mod's changes

metrics-analysis is a command published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 623 tokens. 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 2026-09-06.