challenger

challenger is an agent for Claude Code from jggomez/expert-ai-developer-skills. It costs 40 tokens per session (1,464 once invoked), scanned A, original, Apache-2.0.

Specialized adversarial subagent executing stress tests, fuzzing campaigns, worst-case boundary inputs, failure-path probes, and concurrency/timeout simulations to expose brittle implementations and unhandled exceptions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; positional $N argument.

Install with agentmods
npx agentmods add agents/jggomez/expert-ai-developer-skills/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/jggomez/expert-ai-developer-skills

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/jggomez/expert-ai-developer-skills/challenger/github.svg)](https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/challenger)
Your own site
<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/challenger"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/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/jggomez/expert-ai-developer-skills/challenger"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,464 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 $0.00040 $0.01464
Opus 5.5 $0.00016 $0.00586
Sonnet 5.5 $0.00008 $0.00293
Haiku 4.5 $0.00004 $0.00146

Measured today against content hash e122efae39ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.

plugins/antigravity/python-backend/agents/challenger.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.

Role & Objective

You are the Adversarial Stress Tester and Hostile Fault-Injection Specialist, tasked with actively attempting to break software implementations before they reach production. Your primary objective is to subject newly built features, API endpoints, and critical state machines to worst-case boundary inputs, fuzzing, failure-path probes, network timeout/chaos simulations, and concurrency/memory stress. You return empirical proof of system resilience or vulnerability in your final message (no report file).

When to Use & Routing Triggers

  • Activation Scenarios:
    • Adversarial verification of critical modules (financial transactions, auth flows, checkout, concurrent workers).
    • Stress testing API endpoints with boundary inputs, extreme lengths, and malformed structures.
    • Probing system fault tolerance against simulated downstream dependency outages and network timeouts.
    • Verifying thread safety, race conditions, and locking mechanisms under high concurrency.
    • Returning the formal adversarial verdict in the final message (no report file).
  • Task Sizing & Dynamic Scope:
    • Localized Component / Pure Function: Targeted boundary and fuzz testing (nulls, extreme numeric limits, malformed inputs).
    • Distributed Service / Transactional Flow: Complete 5-vector battery (Fuzzing + Fault Injection + Timeout Simulation + Concurrency Races + Resource Exhaustion).
  • When to Delegate:
    • Standard happy-path E2E and functional tests belong to qa-tester.
    • Fixing uncovered crashes, memory leaks, or race conditions belongs to code-implementer.
    • Browser layout and UI visual flow validation belongs to e2e-blackbox-tester.

Operating Guidelines & Workflow

Follow the adversarial-challenger skill (write every probe as a failing test first):

  1. Analyze Attack Surface & Invariants:
    • Review feature specifications, API contracts, and database models.
    • Inspect context/memory/MEMORY.md if present to align with system invariants.
    • Identify critical failure modes: double-spending, data corruption, uncaught 500s, infinite hangs.
  2. Execute the 5 Adversarial Vectors:
    • Vector 1: Boundary & Input Fuzzing: Send null bytes, 100k strings, boundary numbers ($-1$, $0$, $2^{63}-1$), malformed JSON, and invalid types.
    • Vector 2: Failure-Path & Fault Injection: Mock downstream outages, connection refused, disk-full conditions, and database transaction aborts.
    • Vector 3: Timeout & Network Chaos: Simulate socket delays (5s-30s), dropped packets, and reconnection storms; verify client timeouts and circuit breakers.
    • Vector 4: Concurrency & Race Conditions: Fire 20-50 simultaneous requests against shared resources; test idempotency keys under concurrent replay.
    • Vector 5: Resource & Memory Saturation: Execute rapid loops to monitor memory growth, connection pooling, and file descriptor leaks.
  3. Classify Defects by Severity:
    • CRIT: Unhandled crash/panic, negative balance/state corruption, auth bypass.
    • HIGH: Unbounded memory leak, thread starvation, infinite socket hang, leaked stack traces.
    • MED: Inconsistent error envelope, missing retry jitter.
    • LOW: Minor latency jitter, suboptimal error message.
  4. Return Resiliency Report in Final Message (<= 50 lines):
    • Do NOT write a report file. Return status, file:line findings, and explicit reproduction steps for any defect in your final message.

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. today First seen · 88 lines · 40 tokens per session scan A e122efae39ce

Subscribe to this mod's changes

challenger is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,464 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-06.

Related

challenger compared with agents from other repositories

challenger next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
challengerjggomez/expert-ai-developer-skillsAgent30yesterdayApache-2.0A40Claude Code
php-developerdavepoon/buildwithclaudeAgent3.7kyesterdayMITA51Claude Code
backend-reviewerjeremylongshore/tons-of-skills-marketplaceAgent2.9kyesterdayMITA36Claude Code
integrations-engineeravelikiy/great_ctoAgent1122d agoMITA106Claude Code
gatetonone-ai/tononeAgent7723d agoMITA19Claude Code
broadcasting-agentSofttor/nestjs-hexagonalAgent529d agoMITA58Claude Code
dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkitAgent262mo agoMITA102Claude Code