excel-mcp: Command for Claude Code

.claude/commands/rapid-development/experimental/prp-analyze-run.md

prp-analyze-run is a command for Claude Code from mort-lab/excel-mcp. It costs 0 tokens per session (4,843 once invoked), scanned A, original, MIT.

A command that reviews the results of an implementation created from a PRP, a detailed implementation plan. It records metrics, successful patterns, failures, causes, and suggestions for improving future PRP templates.

In plain words
What is it for?
Use it after a PRP-driven feature is implemented to examine time, token use, iterations, test failures, code quality, validation, and reusable practices.
Why use it?
It turns one implementation's problems and lessons into documented guidance for later work.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is mort-lab/excel-mcp's own configuration. It tells Claude Code how to work on excel-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything excel-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mort-lab/excel-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mort-lab/excel-mcp/main/.claude/commands/rapid-development/experimental/prp-analyze-run.md
Clone the repo
git clone --depth 1 https://github.com/mort-lab/excel-mcp

Made for: Claude Code.

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 prp-analyze-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/mort-lab/excel-mcp/prp-analyze-run.svg)](https://agentmods.dev/commands/mort-lab/excel-mcp/prp-analyze-run)
Your own site
<a href="https://agentmods.dev/commands/mort-lab/excel-mcp/prp-analyze-run"><img src="https://agentmods.dev/badge/commands/mort-lab/excel-mcp/prp-analyze-run.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 4,843 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.04843
Opus 5 $0.00000 $0.02422
Sonnet 5 $0.00000 $0.00969
Haiku 4.5 $0.00000 $0.00484

Measured 8d ago against content hash da8b7f373153, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prp-analyze-run scanned grade A with 1 finding 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 8d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

git_files = subprocess.check_output(['git', 'log', '--name-only', '--pretty=format:', '--since=2 hours ago']).decode().strip().split('\n')
.claude/commands/rapid-development/experimental/prp-analyze-run.md · 651 lines

How it starts

The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze PRP Results

PRP File: $ARGUMENTS

Post-execution analysis of a PRP implementation to capture lessons learned, success metrics, and template improvements.

Analysis Process

  1. Execution Metrics Collection

    • Measure actual vs estimated token usage
    • Track implementation time and iterations
    • Document test failures and fixes
    • Analyze code quality metrics
  2. Success Pattern Analysis

    • Identify what worked well
    • Extract reusable patterns
    • Document effective context elements
    • Capture successful validation strategies
  3. Failure Pattern Learning

    • Document encountered issues
    • Analyze root causes
    • Create prevention strategies
    • Update known gotchas database
  4. Template Improvement Recommendations

    • Identify context gaps
    • Suggest validation enhancements
    • Recommend documentation updates
    • Propose new anti-patterns
  5. Knowledge Base Updates

    • Add new failure patterns to database
    • Update success metrics
    • Enhance similar feature detection
    • Improve confidence scoring

Analysis Framework

Metrics Collection

# Collect implementation metrics
echo "Collecting execution metrics..."

# Get git statistics
COMMITS_DURING_IMPL=$(git rev-list --count HEAD --since="2 hours ago")
FILES_CHANGED=$(git diff --name-only HEAD~$COMMITS_DURING_IMPL HEAD | wc -l)
LINES_ADDED=$(git diff --shortstat HEAD~$COMMITS_DURING_IMPL HEAD | grep -o '[0-9]* insertion' | grep -o '[0-9]*' || echo 0)
LINES_DELETED=$(git diff --shortstat HEAD~$COMMITS_DURING_IMPL HEAD | grep -o '[0-9]* deletion' | grep -o '[0-9]*' || echo 0)

# Get test results
TEST_RESULTS=$(pytest tests/ --tb=no -q 2>&1 | tail -n 1)
TEST_COUNT=$(echo "$TEST_RESULTS" | grep -o '[0-9]* passed' | grep -o '[0-9]*' || echo 0)
TEST_FAILURES=$(echo "$TEST_RESULTS" | grep -o '[0-9]* failed' | grep -o '[0-9]*' || echo 0)

# Get code quality metrics
RUFF_ISSUES=$(ruff check . 2>&1 | grep -c "error\|warning" || echo 0)
MYPY_ERRORS=$(mypy . 2>&1 | grep -c "error:" || echo 0)

echo "📊 Implementation Metrics:"
echo "- Commits: $COMMITS_DURING_IMPL"
echo "- Files changed: $FILES_CHANGED"
echo "- Lines added: $LINES_ADDED"
echo "- Lines deleted: $LINES_DELETED"
echo "- Tests passing: $TEST_COUNT"
echo "- Tests failing: $TEST_FAILURES"
echo "- Ruff issues: $RUFF_ISSUES"
echo "- MyPy errors: $MYPY_ERRORS"

Read the full file on GitHub · 651 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. 8d ago First seen · 651 lines · 0 tokens per session scan A da8b7f373153

Subscribe to this mod's changes

prp-analyze-run is a command published in the GitHub repository mort-lab/excel-mcp (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,843 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.