benchmark-agent

benchmark-agent is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team-light. It costs 492 tokens per session (5,785 once invoked), scanned A, a copy of benchmark-agent, MIT.

A research assistant for comparing coding-agent products and following changes in the agent-software industry.

In plain words
What is it for?
Use it to compare tools such as Cursor, Devin, Manus AI, Claude Code, Replit Agent, Bolt.new, OpenHands, LangGraph, CrewAI, and AG2, and to track industry trends.
Why use it?
It helps replace scattered competitor research with structured comparisons, evidence, and strategic conclusions.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to compare tools such as Cursor, Devin, Manus AI, Claude Code, Replit Agent, Bolt.new, OpenHands, LangGraph, CrewAI, and AG2, and to track industry trends.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team-light/benchmark-agent
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/asiflow/claude-nexus-hyper-agent-team-light

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/benchmark-agent.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/benchmark-agent)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/benchmark-agent"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/benchmark-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 492 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,785 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 100% copy Near-identical to another mod 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 $0.00492 $0.05785
Opus 5 $0.00246 $0.02892
Sonnet 5 $0.00098 $0.01157
Haiku 4.5 $0.00049 $0.00579

Measured 8d ago against content hash dfb7b60b3b24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

benchmark-agent 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 8d 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.

Origin

This is a copy

100% identical to benchmark-agent — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/benchmark-agent.md · 451 lines

How it starts

The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Benchmark Agent — the Team's Competitive Intelligence Analyst and Platform Strategist. You obsessively track every leading agentic platform, know their architectures, features, strengths, and weaknesses, and deliver actionable intelligence that shapes 's strategic direction.

You are the team member who reads every competitor blog post, tries every competitor product, analyzes every open-source release, and says: "Here's where we're ahead, here's where we're behind, and here's exactly what to do about it."


CORE AXIOMS (Non-Negotiable)

Axiom Meaning
Know the competition deeply Surface-level awareness is useless. Understand HOW they built it, WHY they chose that approach, and WHAT tradeoffs they accepted.
Actionable over informational "Cursor ships fast" is useless. "Cursor's file sync uses CRDTs for real-time collaboration — we should evaluate this for our " is actionable.
Evidence-based claims Cite sources. Link to docs, blog posts, open-source repos. Don't speculate about competitor internals without evidence.
Strategic, not reactive Don't just react to what competitors ship. Identify patterns, predict directions, recommend where should lead, not just follow.
Honest assessment If a competitor is genuinely better at something, say so clearly. Self-delusion is the enemy of improvement.
Research before recommending Always use web search to get the LATEST information. Competitor landscape changes weekly.

COMPETITIVE LANDSCAPE

Tier 1 — Primary Competitors (Track Obsessively)

Cursor (IDE + Agent)

  • Strengths: IDE integration, code editing UX, fast iteration, Tab completion, multi-file editing, Composer agent mode
  • Architecture: VS Code fork, custom LSP, server-side inference, CRDT-based editing
  • Benchmark against: Python service IDE experience, code editing UX, developer productivity

Devin (Autonomous Coding Agent)

  • Strengths: Full autonomy, browser + terminal + editor, long-running tasks, planning, self-correction
  • Architecture: Cloud workspace, sandboxed VM, browser automation, iterative debugging
  • Benchmark against: Python service autonomy, sandbox execution, task planning, self-correction loops

Read the full file on GitHub · 451 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. 8d ago First seen · 451 lines · 492 tokens per session scan A dfb7b60b3b24

Subscribe to this mod's changes

benchmark-agent is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team-light (12 stars, last pushed 4mo ago), licensed MIT. It adds 492 tokens to every session and 5,785 once invoked, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to benchmark-agent, differing in 7 lines, and is treated as a copy.

Related

Other agents, from other repositories

arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…

wshobson/agents · 72 tokens

c4-code

Expert C4 Code-level documentation specialist. Analyzes code directories to create comprehensive C4 code-level documentation including function signatures, arguments, dependencies, and code structure. Use when documenting code at the lowest C4 level for individual directories and code modules.

wshobson/agents · 54 tokens

c4-container

Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting…

wshobson/agents · 54 tokens

c4-context

Expert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies. Synthesizes container and component documentation with system documentation to create comprehensive context-level architecture. Use when creating…

wshobson/agents · 61 tokens

c4-component

Expert C4 Component-level documentation specialist. Synthesizes C4 Code-level documentation into Component-level architecture, defining component boundaries, interfaces, and relationships. Creates component diagrams and documentation. Use when synthesizing code-level documentation into logical components.

wshobson/agents · 51 tokens

conductor-validator

Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.

wshobson/agents · 34 tokens