strands-sglang: Command for Claude Code

.claude/commands/run-integration-tests.md

run-integration-tests is a command for Claude Code from strands-rl/strands-sglang. It costs 0 tokens per session (349 once invoked), scanned A, original, Apache-2.0.

A test command that creates an isolated Python environment with uv, installs the project and its development dependencies, and runs integration tests. Integration tests check how multiple parts work together and require a running SGLang server.

In plain words
What is it for?
Use it to run integration tests with a chosen SGLang server URL and parser, with optional extra test arguments.
Why use it?
It keeps test dependencies separate from the active environment while allowing the test suite to use the correct server address and tool-parser format.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is strands-rl/strands-sglang's own configuration. It tells Claude Code how to work on strands-sglang 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 strands-sglang configures →

Reuse

Borrowing it

Nothing to install: this file belongs to strands-rl/strands-sglang. 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/strands-rl/strands-sglang/main/.claude/commands/run-integration-tests.md
Clone the repo
git clone --depth 1 https://github.com/strands-rl/strands-sglang

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 run-integration-tests

README.md
[![agentmods](https://agentmods.dev/badge/commands/strands-rl/strands-sglang/run-integration-tests.svg)](https://agentmods.dev/commands/strands-rl/strands-sglang/run-integration-tests)
Your own site
<a href="https://agentmods.dev/commands/strands-rl/strands-sglang/run-integration-tests"><img src="https://agentmods.dev/badge/commands/strands-rl/strands-sglang/run-integration-tests.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 349 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 5.1 $0.00000 $0.00349
Opus 5 $0.00000 $0.00175
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 6d ago against content hash fc8e105e785d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

run-integration-tests 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 6d 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/run-integration-tests.md · 24 lines

What it actually says

Run integration tests in an isolated temporary venv created with uv.

Integration tests require a running SGLang server. Before running any commands, ask the user:

  1. "What is the SGLang server base URL?" — offer these options:

    • http://localhost:30000 (default — assumes local or SSH-tunneled server)
    • Let the user provide a custom URL
  2. "Which tool parser?" — offer these options:

    • hermes (default — for Hermes/Qwen models)
    • qwen_xml (XML format for Qwen models)
    • glm (GLM models)

Then proceed:

  1. Create a temporary venv at /tmp/strands-sglang-test-venv using uv venv /tmp/strands-sglang-test-venv --python 3.12 -q
  2. Install the package with dev dependencies: uv pip install -e . --group dev --python /tmp/strands-sglang-test-venv/bin/python -q
  3. Run integration tests with the confirmed URL and tool parser: /tmp/strands-sglang-test-venv/bin/python -m pytest tests/integration/ -v --tb=short --sglang-base-url=<URL> --tool-parser=<PARSER> $ARGUMENTS

VLM tests are automatically skipped if the server is running a text-only model (auto-detected via PretrainedConfig). No extra dependencies (torch, torchvision) are needed.

IMPORTANT: Never use the active shell's python/pytest — it may point to a different venv. Always use the temporary venv's python.

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. 6d ago First seen · 24 lines · 0 tokens per session scan A fc8e105e785d

Subscribe to this mod's changes

run-integration-tests is a command published in the GitHub repository strands-rl/strands-sglang (78 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 349 tokens. 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 2026-08-30.