coverage-gaps

coverage-gaps is a command for Claude Code from vishnu2kmohan/mcp-server-langgraph. It costs 18 tokens per session (3,886 once invoked), scanned A, original, MIT.

A dashboard workflow that examines automated test coverage, meaning which parts of the code are exercised by tests, and displays missing coverage as an ASCII heatmap.

In plain words
What is it for?
Use it to run coverage analysis, review results by module and file, and identify testing gaps that need attention.
Why use it?
It makes areas with too few tests easier to find and rank by risk instead of relying on one overall percentage.

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-gaps
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-gaps

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/coverage-gaps.svg)](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/coverage-gaps)
Your own site
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/coverage-gaps"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/coverage-gaps.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,886 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 $0.00018 $0.03886
Opus 5 $0.00009 $0.01943
Sonnet 5 $0.00004 $0.00777
Haiku 4.5 $0.00002 $0.00389

Measured 4d ago against content hash f76fbb95fa37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coverage-gaps 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-gaps.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coverage Gaps Dashboard

You are tasked with generating a visual coverage gaps dashboard for the mcp-server-langgraph project. This command provides an at-a-glance view of coverage health with ASCII heatmaps and prioritization.

Project Coverage Context

Current Coverage: 60-65% combined (unit + integration) Target Coverage: 80% Test Suite: 437+ tests Strategy: Prioritize by risk and criticality

Your Task

Step 1: Run Coverage Analysis

  1. Run pytest with coverage:

    uv run --frozen pytest tests/ --cov=src/mcp_server_langgraph --cov-report=term --cov-report=html --quiet
    
  2. Parse coverage output to extract:

    • Overall coverage percentage
    • Per-module coverage
    • Per-file coverage
    • Line counts (total, covered, missed)

Step 2: Generate Visual Coverage Heatmap

Create an ASCII heatmap showing coverage by module:

Heatmap Legend:

  • 🟢 Green (80-100%): Good coverage
  • 🟡 Yellow (60-79%): Needs improvement
  • 🟠 Orange (40-59%): Poor coverage
  • 🔴 Red (0-39%): Critical gap

Example Heatmap Output:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  COVERAGE HEATMAP - mcp-server-langgraph
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

  Module                     Coverage  Status  Lines    Missing
  ──────────────────────────────────────────────────────────────
  📦 core/
    ├─ agent.py              ████████  82%   🟢  456     82
    ├─ config.py             ██████░░  73%   🟡  234     63
    └─ feature_flags.py      ████████  91%   🟢  127     11

  🔐 auth/
    ├─ middleware.py         ███████░  78%   🟡  312     69
    ├─ jwt.py                ████████  88%   🟢  198     24
    ├─ rbac.py               ██░░░░░░  25%   🔴  267    200  ⚠️
    └─ keycloak.py           ███░░░░░  35%   🔴  189    123  ⚠️

  💾 session/
    ├─ store.py              ███████░  76%   🟡  345     83
    ├─ distributed.py        ███░░░░░  38%   🔴  402    249  ⚠️
    └─ checkpointing.py      ████████  84%   🟢  278     44

  🔧 tools/
    ├─ calculator_tools.py   ████████  95%   🟢  156     8
    ├─ filesystem.py         ██████░░  62%   🟡  289    110
    └─ search_tools.py       ███████░  72%   🟡  201     56

  🌐 mcp/
    ├─ stdio_server.py       ███████░  77%   🟡  423    97
    ├─ protocol.py           █████░░░  58%   🟠  378    159  ⚠️
    └─ handlers.py           ████████  81%   🟢  234     44

  📊 observability/
    ├─ telemetry.py          ████████  86%   🟢  412     58
    ├─ logging.py            ███████░  79%   🟡  267     56
    └─ metrics.py            ████████  89%   🟢  334     37

  ──────────────────────────────────────────────────────────────
  TOTAL                      ██████░░  65%   🟡  6,302  1,573
  ──────────────────────────────────────────────────────────────

  Legend: ████ = covered | ░░░░ = missing | ⚠️ = critical gap

Read the full file on GitHub · 394 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 · 394 lines · 18 tokens per session scan A f76fbb95fa37

Subscribe to this mod's changes

coverage-gaps is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 11d ago), licensed MIT. It adds 18 tokens to every session and 3,886 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.