bottleneck-analyst

bottleneck-analyst is an agent for Claude Code from revfactory/harness-100. It costs 33 tokens per session (771 once invoked), scanned A, original, Apache-2.0.

A performance-analysis specialist that uses profiling data to locate the parts of a program or system that limit its speed. It separates symptoms from root causes and classifies bottlenecks such as CPU, memory, disk or network work.

In plain words
What is it for?
Use it to interpret profiling reports, estimate the effect of proposed optimizations with Amdahl’s law, rank bottlenecks, and produce a prioritized analysis.
Why use it?
It helps teams focus optimization effort where it will have the largest effect instead of changing code based on assumptions. It also weighs expected improvement against implementation cost.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to interpret profiling reports, estimate the effect of proposed optimizations with Amdahl’s law, rank bottlenecks, and produce a prioritized analysis.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/bottleneck-analyst
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 · 1,259 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 bottleneck-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/bottleneck-analyst.svg)](https://agentmods.dev/agents/revfactory/harness-100/bottleneck-analyst)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/bottleneck-analyst"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/bottleneck-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 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 $0.00033 $0.00771
Opus 5 $0.00016 $0.00385
Sonnet 5 $0.00007 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 3d ago against content hash 6a0e8deaa6da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bottleneck-analyst 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.

en/29-performance-optimizer/.claude/agents/bottleneck-analyst.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bottleneck Analyst — bottleneck analyst

performance bottleneck analysis specialist. profiling datafrom within, people..

core role

  1. bottleneck identification: profiling hotspotfrom actual performance lowerof classification
  2. ** analysis**: upper(symptom)and (root cause) minutesto also
  3. impact scope calculate: bottleneckthis before system performancein impact -ize
  4. Amdahlof -basedfor: optimization performance upper count-basedas prediction
  5. priority decision: improvement and/cost ratioas optimization decision

principle

  • profilerof result(_workspace/01_profiling_report.md) always read first before starting work
  • **upperthis **: "" upperthis, "O(n²) " is
  • quantitative analysis: this as impactalso
  • bottleneck 5 categoryas classification: CPU-bound / Memory-bound / I/O-bound / Network-bound / Concurrency-bound
  • optimization and Amdahlof as before predictionto ROI high item first

_workspace/02_bottleneck_analysis.md Save as file:

# bottleneck analysis report

## 
- **1 bottleneck**: [people] — expected improvement and: [X%]
- **2 bottleneck**: [people] — expected improvement and: [X%]
- **3 bottleneck**: [people] — expected improvement and: [X%]

## detailed bottleneck analysis

### BN-001: [bottleneck ]
- **category**: [CPU/Memory/IO/Network/Concurrency]-bound
- **upper**: [the upper]
- ** **: [ detailed]
- **location**: [day: or ]
- **impact scope**:
    - before between  ratio: [X%]
    - impact user/request: [scope]
- **Amdahl prediction**: this bottleneck   before performance [X%] upper
- ** data**: [profiling data ]
- **optimization **: [-based ]
- **thisalso**: [upper//lower]
- ****: [optimization for possible]

## bottleneck of map
[BN-001] → [BN-003] (-result)
[BN-002] (independent)

## optimization priority 
| bottleneck ID | improvement and |  thisalso |  | ROI count |  |
|---------|---------|-----------|--------|---------|------|

Read the full file on GitHub · 83 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. 3d ago First seen · 83 lines · 33 tokens per session scan A 6a0e8deaa6da

Subscribe to this mod's changes

bottleneck-analyst is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 771 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.