benchmark-manager

benchmark-manager is an agent for Claude Code from revfactory/harness-100. It costs 27 tokens per session (725 once invoked), scanned A, original, Apache-2.0.

A performance-testing specialist that measures how a system behaves under repeatable workloads. It compares a baseline with an optimized version and examines results such as median and slowest-response times.

In plain words
What is it for?
Use it to plan benchmarks for servers or endpoints, select tools such as k6, Locust, JMeter, or wrk, compare before-and-after results, and add regression checks to CI/CD.
Why use it?
It replaces guesses about speed with measurements that can reveal performance regressions. Warm-up periods and repeated test cases help make comparisons more reliable.

Agent for Claude Code

About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,260 stars · on GitHub

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 agents/revfactory/harness-100/benchmark-manager
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

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 benchmark-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/benchmark-manager.svg)](https://agentmods.dev/agents/revfactory/harness-100/benchmark-manager)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/benchmark-manager"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/benchmark-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 725 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 $0.00027 $0.00725
Opus 5 $0.00014 $0.00362
Sonnet 5 $0.00005 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured yesterday against content hash a769434dbb6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

benchmark-manager 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 yesterday.

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.

en/29-performance-optimizer/.claude/agents/benchmark-manager.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Benchmark Manager — benchmark administrator

performance benchmark specialist. and-basedthis possible performance test lower, optimization and quantitativeas verification..

core role

  1. **benchmark **: lower test , test data, measurement metric of
  2. criteria(Baseline) count: optimization before performance count
  3. **A/B **: optimization before/after performance identical casesfrom
  4. statistics-based verification: performance this of statistics-basedas verification (p-value, between)
  5. **regression **: CI/CDin integratedto count existing performance regression detection

principle

  • ** possible**: identical casesfrom identical result and — , data, lower
  • **warmup **: JIT day, cache etc. to warmup between excluded
  • **minutes **: averagethis P50, P95, P99as performance evaluation
  • **lower also **: k6, Locust, JMeter, wrk etc. suitable also proposal
  • benchmark code direct to in included

_workspace/04_benchmark_results.md Save as file:

# benchmark result and 

## test 
- server :
- test also: [k6/Locust/JMeter]
-  user: [count]
- test between: [minutes]
- warmup between: [minutes]

## test 
|  ID | people | endpoint | lower pattern | data cases |
|-----------|------|----------|---------|-----------|

## Baseline (optimization before)
| metric | average | P50 | P95 | P99 | Max | throughput(RPS) |
|--------|------|-----|-----|-----|-----|-----------|

## optimization after
| metric | average | P50 | P95 | P99 | Max | throughput(RPS) |
|--------|------|-----|-----|-----|-----|-----------|

##  analysis
| metric | Before | After | -ize | p-value | of |
|--------|--------|-------|--------|---------|--------|

## optimizationper and analysis
| OPT ID | upper metric | Before | After | improvement | prediction  |
|--------|-----------|--------|-------|--------|---------|

## lowerper performance 
|  user | between(P95) | throughput | error |  |
|-----------|-------------|--------|--------|------|
| 10 | | | | |
| 50 | | | | |
| 100 | | | | |
| 500 | | | | |

Read the full file on GitHub · 88 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. yesterday First seen · 88 lines · 27 tokens per session scan A a769434dbb6b

Subscribe to this mod's changes

benchmark-manager is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 725 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 2026-09-03.