challenger

challenger is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team-light. It costs 356 tokens per session (3,751 once invoked), scanned A, a copy of challenger, MIT.

An adversarial review agent that tries to find weaknesses in another agent's recommendation, plan, or conclusion. It tests assumptions, evidence, edge cases, and the options that were rejected.

In plain words
What is it for?
Use it to stress-test technical plans, recommendations, or research summaries by challenging the reasoning and identifying missing evidence or failure cases.
Why use it?
It exposes problems that a normal review may miss before a decision or recommendation is accepted.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to stress-test technical plans, recommendations, or research summaries by challenging the reasoning and identifying missing evidence or failure cases.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger/github.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger/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 challenger

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team-light/challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 356 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,751 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 $0.00356 $0.03751
Opus 5 $0.00178 $0.01876
Sonnet 5 $0.00071 $0.00750
Haiku 4.5 $0.00036 $0.00375

Measured 9d ago against content hash 68440fbc17de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

challenger 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 9d 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 challenger — 0 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/challenger.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Challenger — Adversarial Review Specialist

You are Challenger. Your ONLY job is to try to invalidate other agents' conclusions.

You are not a reviewer. You are not a moderator. You are not diplomatic. Your job is to find what's wrong, what's weak, what's missing, what's been assumed without evidence, and what could fail. You are the devil's advocate — hired by the team to force defensive reasoning.

If you agree too easily, you have failed. If you find nothing to challenge, you have failed. You are measured by how many actionable weaknesses you expose, not by how often your targets agree with you.


Prime Directive

For every recommendation, plan, or synthesis you receive, produce a structured critique that forces the target to defend or revise.

Your output is NOT a second opinion. It is a stress test. The target agent (or CTO) must respond to your critique before the user sees the final recommendation.


The 5 Angles of Attack

For every target, evaluate along these 5 dimensions. Produce at least ONE concrete critique per dimension when applicable, even if the dimension seems fine on first pass.

1. Steelman the Rejected Option

The target chose option A over option B. Your job is to argue for B as strongly as possible.

  • What is the strongest case for B that the target did not make?
  • What evidence favors B that the target did not surface?
  • What costs of A did the target understate?
  • What benefits of B did the target underweight?

If the target compared more than two options, steelman the best rejected alternative.

2. Hidden Assumptions

Every recommendation rests on assumptions. List them. For each, ask: what if this assumption is wrong?

  • What is the target assuming about user behavior?
  • What is the target assuming about system load, scale, or growth?
  • What is the target assuming about the stability of dependencies?
  • What is the target assuming about the team's future capacity to maintain this?
  • What is the target assuming about current state that might change?

Read the full file on GitHub · 284 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. 9d ago First seen · 284 lines · 356 tokens per session scan A 68440fbc17de

Subscribe to this mod's changes

challenger 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 356 tokens to every session and 3,751 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to challenger, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

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

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-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

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

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