test-status

test-status is a command for Claude Code from vishnu2kmohan/mcp-server-langgraph. It costs 16 tokens per session (1,452 once invoked), scanned A, original, MIT.

A quick command for checking whether tests pass, optionally limited to a pytest marker such as unit, integration, API, or security.

In plain words
What is it for?
Use it for lightweight checks during development or before committing, across all tests or one marked group.
Why use it?
It avoids the extra time and output of coverage and detailed analysis when you only need a fast signal after a change.

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-status
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-status

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/test-status.svg)](https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/test-status)
Your own site
<a href="https://agentmods.dev/commands/vishnu2kmohan/mcp-server-langgraph/test-status"><img src="https://agentmods.dev/badge/commands/vishnu2kmohan/mcp-server-langgraph/test-status.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,452 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 $0.00016 $0.01452
Opus 5 $0.00008 $0.00726
Sonnet 5 $0.00003 $0.00290
Haiku 4.5 $0.00002 $0.00145

Measured 4d ago against content hash e1771c01d782, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-status 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-status.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Test Status Check

Usage: /test-status or /test-status <marker>

Markers: Any pytest marker (e.g., unit, integration, api, security)


🎯 Purpose

Provides a fast, lightweight status check of tests without running comprehensive analysis.

Use this for:

  • Quick validation during development
  • Rapid feedback after code changes
  • Fast status checks before commits

For comprehensive analysis, use /test-summary instead.


⚡ Quick Status Check

Step 1: Determine Scope

Based on $ARGUMENTS, determine which tests to check:

Default (all tests):

pytest -v --tb=line --no-cov -q

Specific marker (e.g., /test-status unit):

pytest -m $ARGUMENTS -v --tb=line --no-cov -q

Options used for speed:

  • --no-cov - Skip coverage (faster)
  • -q - Quiet mode (less output)
  • --tb=line - Minimal traceback (faster display)
  • -x - Stop on first failure (optional, for even faster feedback)

Step 2: Run Fast Test Check

Execute tests with minimal overhead:

# Run tests without coverage
pytest -v --tb=line --no-cov -q 2>&1 | tee /tmp/test_status.txt

# Capture exit code
TEST_EXIT=$?

Capture:

  • Total tests run
  • Pass/fail count
  • First failure (if any)
  • Total duration

Step 3: Parse Results

Extract key metrics from output:

# Parse pytest output for summary line
# Example: "437 passed in 12.34s"
# Example: "425 passed, 12 failed in 23.45s"

SUMMARY=$(tail -n 5 /tmp/test_status.txt | grep -E "passed|failed|skipped")

Step 4: Display Quick Status

Show concise status report:

## ⚡ Test Status

**Status**: ✅ PASSING | ❌ FAILING | ⚠️ ISSUES

**Quick Summary**:
- Passed: XXX
- Failed: XX
- Skipped: XX
- Duration: XX.Xs

**Scope**: [all|unit|integration|$MARKER]

---

[If all passing]:
✅ **All tests passing** - Ready to proceed

[If failures]:
❌ **Tests failing** - Fix before proceeding
First failure: `test_name` in `file_path.py:line`

Run `/test-summary` for detailed failure analysis.

[If skipped tests]:
⚠️ **XX tests skipped** - May need infrastructure
Run with `-v` to see skip reasons.

---

**Quick Commands**:

Run failed tests only:
```bash
pytest --lf -x  # Stop on first failure

Run specific test:

pytest tests/path/test_file.py::test_name

Fast iteration:

make test-dev  # Fast mode (40-70% faster)

Next Steps:

✅ All passing → Proceed with commit/deployment ❌ Failures → Run /test-summary failed for analysis ⚠️ Skipped → Check infrastructure (docker compose up)

For comprehensive analysis: /test-summary For test debugging: /fix-issue <test-name>

Read the full file on GitHub · 275 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 · 275 lines · 16 tokens per session scan A e1771c01d782

Subscribe to this mod's changes

test-status is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 11d ago), licensed MIT. It adds 16 tokens to every session and 1,452 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.