benchmark

A command for measuring how an API endpoint responds under repeated requests. An API endpoint is a specific web address and method that software uses to request or submit data.

In plain words
What is it for?
Use it to test an endpoint with concurrent requests, inspect minimum and percentile response times, group errors by status code, compare results with service targets, and save the raw data.
Why use it?
It replaces guesswork about speed and reliability with measurements such as response times, throughput, and error rates. Warmup requests and connection reuse make the test closer to typical use.

Command

Part of the api-benchmarker plugin — 1 command shipped together

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/rohitg00/awesome-claude-code-toolkit/benchmark
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Or install api-benchmarker, the plugin that ships this one along with the rest of its 1 command.

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 295 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 $0.00000 $0.00295
Opus 5 $0.00000 $0.00148
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00030

Measured 3d ago against content hash 6978226bf945, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchmark 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 3d 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.

plugins/api-benchmarker/commands/benchmark.md · 32 lines

What it actually says

/benchmark - Benchmark API Endpoints

Run performance benchmarks against API endpoints.

Steps

  1. Ask the user for the target endpoint URL and HTTP method
  2. Configure the request: headers, authentication, request body, query parameters
  3. Run a warmup phase: 10 requests to prime caches and connections
  4. Execute the benchmark with configurable parameters:
    • Concurrent connections (default: 10)
    • Total requests (default: 1000)
    • Duration-based (alternative to request count)
  5. Capture per-request metrics: response time, status code, response size
  6. Calculate statistics: min, max, mean, median, p95, p99 response times
  7. Calculate throughput: requests per second, bytes per second
  8. Record error rate and categorize errors by status code
  9. Detect performance degradation over the benchmark duration
  10. Compare against SLA targets if defined
  11. Save raw results in JSON format for further analysis
  12. Present a formatted summary with key metrics and pass/fail status

Rules

  • Always include a warmup phase before measuring
  • Use keep-alive connections to simulate realistic client behavior
  • Record and report all HTTP status codes, not just 200s
  • Include connection time separately from response time
  • Do not benchmark production endpoints without explicit permission
  • Run from a network location representative of actual users
  • Report the server and client environment for reproducibility
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. 3d ago First seen · 32 lines · 0 tokens per session scan A 6978226bf945

Subscribe to this mod's changes

benchmark is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,578 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 295 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.