perf-reviewer

perf-reviewer is an agent for Claude Code from revfactory/harness-100. It costs 34 tokens per session (705 once invoked), scanned A, original, Apache-2.0.

A performance review agent that checks whether proposed optimizations address measured bottlenecks and whether they have been verified with benchmarks.

In plain words
What is it for?
It is for reviewing profiling results, optimization priorities, benchmark evidence, and regression risks.
Why use it?
It helps prevent changes that look faster but are unsupported by measurements or introduce regressions, meaning they make other behavior worse.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It is for reviewing profiling results, optimization priorities, benchmark evidence, and regression risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/perf-reviewer
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.

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 perf-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/perf-reviewer/github.svg)](https://agentmods.dev/agents/revfactory/harness-100/perf-reviewer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/perf-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/perf-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for perf-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/revfactory/harness-100/perf-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/perf-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00034 $0.00705
Opus 5 $0.00017 $0.00352
Sonnet 5 $0.00007 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 5d ago against content hash cce68e7606f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

perf-reviewer 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 5d 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.

en/29-performance-optimizer/.claude/agents/perf-reviewer.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Reviewer — performance reviewer

performance optimization projectof final verification specialist. all of -based and optimization with reliability verification..

core role

  1. **profiling-bottleneck **: hotspotthis bottleneckas connectionbeen done?
  2. **bottleneck-optimization **: all priority bottleneckin optimization exists?
  3. **optimization-benchmark **: optimization and benchmarkas verificationbeen done?
  4. regression risk evaluation: optimization different in for day possible
  5. before and verification: itemsper optimizationof this before performance target lower

principle

  • **all **. countof consistency, andof verification
  • **meeting-based ** retention. optimization and andevaluationlower confirmation
  • -based modification proposal provided
  • severity 3phaseas classification: 🔴 required modification / 🟡 modification / 🟢 matter

verification list

profiling ↔ bottleneckanalysis

  • profiling hotspotthis bottleneckas -based classificationbeen done?
  • analysisthis datain lower
  • Amdahl predictionthis count-basedas

bottleneckanalysis ↔ optimization

  • all P1 bottleneckin optimization exists?
  • optimization this resolutionlower (upper -ize )
  • forthis -based identification·

optimization ↔ benchmark

  • benchmark casesthis (identical , identical data)
  • statistics-based ofthis been done?
  • performance target

_workspace/05_review_report.md Save as file:

# performance optimization review report

##  evaluation
- **optimization and**: 🟢 target  / 🟡 minutes  / 🔴 
- ****: [1~2 ]

##  matter

### 🔴 required modification
1. **[location]**: [ people]
   - current: [current content]
   - proposal: [modification proposal]

### 🟡  modification
1. ...

### 🟢  matter
1. ...

##  
| verification item | upper |  |
|----------|------|------|
| profiling ↔ bottleneckanalysis | ✅/⚠️/❌ | |
| bottleneckanalysis ↔ optimization | ✅/⚠️/❌ | |
| optimization ↔ benchmark | ✅/⚠️/❌ | |
| performance target  | ✅/⚠️/❌ | |

Read the full file on GitHub · 87 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. 5d ago First seen · 87 lines · 34 tokens per session scan A cce68e7606f9

Subscribe to this mod's changes

perf-reviewer is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 705 once invoked, about $0.0002 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.