test-fast

test-fast is a command for Claude Code from vishnu2kmohan/mcp-server-langgraph. It costs 9 tokens per session (2,046 once invoked), scanned A, original, MIT.

A command for running a selected group of tests with less waiting during development. It offers development, core, parallel, and unit-test modes.

In plain words
What is it for?
Use it for quick checks while coding, such as running only core or unit tests, running tests in parallel, or stopping at the first failure.
Why use it?
It reduces feedback time by skipping slow tests or coverage when appropriate, stopping early on failures, and using parallel execution.

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/test-fast
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 test-fast

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/test-fast.svg)](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/test-fast)
Your own site
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/test-fast"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/test-fast.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 2,046 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 $0.02046
Opus 5 $0.00005 $0.01023
Sonnet 5 $0.00002 $0.00409
Haiku 4.5 $0.00001 $0.00205

Measured 4d ago against content hash 6c608ce22a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-fast 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/test-fast.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast Test Iteration

Usage: /test-fast or /test-fast <mode>

Purpose: Execute tests with optimized speed for rapid development iteration

Modes:

  • dev - Development mode (recommended)
  • core - Fastest core tests only
  • parallel - All tests in parallel
  • unit - Unit tests only (no coverage)

🚀 Why Fast Testing?

Standard test execution with coverage can be slow:

  • make test: ~45-60 seconds (with coverage)
  • make test-unit: ~30-40 seconds (with coverage)

Fast testing options provide 40-70% speed improvement for rapid iteration:

  • make test-dev: ~15-20 seconds ⚡
  • make test-fast-core: ~3-5 seconds ⚡⚡
  • make test-fast: ~20-30 seconds ⚡

⚡ Fast Testing Options

Development Mode (RECOMMENDED)

Best for active development - parallel, fast-fail, skip slow tests:

make test-dev
```rust
**Features**:
- ✅ Parallel execution (`pytest -n auto`)
- ✅ Stop on first failure (`-x`)
- ✅ Max 3 failures (`--maxfail=3`)
- ✅ Skip slow tests (`-m "unit and not slow"`)
- ✅ No coverage overhead
- ✅ Short traceback (`--tb=short`)

**Speed**: 40-60% faster than standard tests
**Use case**: Active development, quick feedback loop

**Example output**:

Running tests in development mode (parallel, fast-fail, no coverage)... ✓ Development tests complete

Features: Parallel execution, stop on first failure, skip slow tests

---

### Fastest Core Tests

Minimal test set for ultra-rapid iteration:

```bash
make test-fast-core

Features:

  • ✅ Core unit tests only
  • ✅ Parallel execution
  • ✅ No slow tests
  • ✅ No integration tests
  • ✅ Minimal output (-q)

Speed: Typically < 5 seconds ⚡⚡ Use case: Rapid iteration on critical paths

Example:

⚡ Running core unit tests only (fastest iteration)...
✓ Core tests complete

Use for rapid iteration (typically < 5 seconds)

All Tests (No Coverage)

Run all tests without coverage overhead:

make test-fast
```bash
**Features**:
- ✅ All unit and integration tests
- ✅ Parallel execution
- ✅ No coverage collection
- ✅ Short traceback

Read the full file on GitHub · 407 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 · 407 lines · 9 tokens per session scan A 6c608ce22a52

Subscribe to this mod's changes

test-fast 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 2,046 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.