coverage-trend

coverage-trend is a command for Claude Code from vishnu2kmohan/mcp-server-langgraph. It costs 9 tokens per session (2,891 once invoked), scanned A, original, MIT.

A command that examines how automated test coverage changes over time. Test coverage measures which parts of the code are exercised by tests.

In plain words
What is it for?
Use it to measure current coverage, compare it with historical data, inspect module-level results, detect regressions, and create a trend visualisation.
Why use it?
It helps reveal falling coverage, uncovered modules, and changes that may indicate a testing gap.

Command 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 commands/vishnu2kmohan/mcp-server-langgraph/coverage-trend
Clone the repo
git clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraph

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 coverage-trend

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/coverage-trend.svg)](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/coverage-trend)
Your own site
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/coverage-trend"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/coverage-trend.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,891 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 $0.00009 $0.02891
Opus 5 $0.00005 $0.01445
Sonnet 5 $0.00002 $0.00578
Haiku 4.5 $0.00001 $0.00289

Measured 4d ago against content hash ce3b96c08e54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coverage-trend 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 4d 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.

.claude/commands/coverage-trend.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coverage Trend Analysis

Usage: /coverage-trend or /coverage-trend --days 30

Purpose: Track test coverage trends over time and identify patterns

Features 🆕:

  • Historical coverage tracking
  • Trend visualization
  • Module-level breakdown
  • Coverage delta analysis
  • Regression detection

📊 What This Command Does

Analyzes test coverage evolution over time by:

  1. Running current coverage measurement
  2. Reading historical coverage data
  3. Computing trends and changes
  4. Identifying coverage gaps
  5. Generating trend visualization

🚀 Execution Steps

Step 1: Run Current Coverage

Execute coverage measurement:

# Run combined coverage (unit + integration)
make test-coverage-combined

# This generates:
# - htmlcov-combined/index.html (HTML report)
# - coverage.xml (XML report)
# - .coverage (raw data)

Step 2: Extract Coverage Metrics

Parse coverage results:

# Total coverage percentage
CURRENT_COV=$(grep -oP 'Total coverage: \K[0-9.]+' coverage.xml || \
              coverage report --format=total 2>/dev/null || \
              echo "unknown")

# Module-level coverage
coverage report --format=markdown > /tmp/coverage_by_module.md

# Or parse HTML
grep -A 5 "Total" htmlcov-combined/index.html

Step 3: Load Historical Data

Read stored coverage history:

# Coverage history stored in .coverage-history/
# Format: YYYY-MM-DD,coverage_percentage,modules_covered

# Create if doesn't exist
mkdir -p .coverage-history

# Append current measurement
echo "$(date +%Y-%m-%d),$CURRENT_COV" >> .coverage-history/trend.csv

Step 4: Calculate Trends

Analyze coverage evolution:

# Last 7 days average
tail -7 .coverage-history/trend.csv | awk -F',' '{sum+=$2; count++} END {print sum/count}'

# Last 30 days average
tail -30 .coverage-history/trend.csv | awk -F',' '{sum+=$2; count++} END {print sum/count}'

# Trend direction
# Compare last 7 days vs previous 7 days

Step 5: Generate Visualization

Read the full file on GitHub · 486 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. 4d ago First seen · 486 lines · 9 tokens per session scan A ce3b96c08e54

Subscribe to this mod's changes

coverage-trend is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 11d ago), licensed MIT. It adds 9 tokens to every session and 2,891 once invoked, about $0.0000 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.