adversarial-prompting

adversarial-prompting is a skill for Claude Code, Codex from Demerzels-lab/elsamultiskillagent. It costs 54 tokens per session (862 once invoked), scanned A, original, MIT.

A structured problem-solving method that creates several possible solutions, challenges their weaknesses, fixes them, and ranks the results.

In plain words
What is it for?
Reviewing technical designs, debugging approaches, architecture choices, and other complex decisions.
Why use it?
It helps expose edge cases, failure modes, and unintended effects before a solution is chosen.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing technical designs, debugging approaches, architecture choices, and other complex decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/demerzels-lab/elsamultiskillagent/adversarial-prompting
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.

Any agent
npx skills add Demerzels-lab/elsamultiskillagent --skill adversarial-prompting
Clone the repo
git clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagent

Made for: Claude Code, Codex.

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 adversarial-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting/github.svg)](https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting)
Your own site
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting/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 adversarial-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/adversarial-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 862 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 $0.00054 $0.00862
Opus 5 $0.00027 $0.00431
Sonnet 5 $0.00011 $0.00172
Haiku 4.5 $0.00005 $0.00086

Measured 9d ago against content hash 2eb542c320b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

adversarial-prompting 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/export_analysis.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

public/skills/abe238/adversarial-prompting/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Prompting

This skill applies a structured adversarial methodology to problem-solving by generating multiple solutions, rigorously critiquing each for weaknesses, developing fixes, validating those fixes, and consolidating into ranked recommendations. The approach forces deep analysis of failure modes, edge cases, and unintended consequences before committing to a solution.

When to Use This Skill

Use this skill when:

  • Facing complex technical problems requiring thorough analysis (architecture decisions, debugging, performance optimization)
  • Solving strategic or business problems with multiple viable approaches
  • Needing to identify weaknesses in proposed solutions before implementation
  • Requiring validated fixes that address root causes, not symptoms
  • Working on high-stakes decisions where failure modes must be understood
  • Seeking comprehensive analysis with detailed reasoning visible throughout

Do not use this skill for:

  • Simple, straightforward problems with obvious solutions
  • Time-sensitive decisions requiring immediate action without analysis
  • Problems where exploration and iteration are more valuable than upfront analysis

How to Use This Skill

Primary Workflow

When invoked, apply the following 7-phase process to the user's problem:

Phase 1: Solution Generation

Generate 3-7 distinct solution approaches. For each solution:

  • Explain the reasoning behind the approach
  • Describe the core strategy
  • Outline the key steps or components
Phase 2: Adversarial Critique

For each solution, rigorously identify critical weaknesses. Show thinking while examining:

  • Edge cases and failure modes
  • Security vulnerabilities or risks
  • Performance bottlenecks
  • Scalability limitations
  • Hidden assumptions that could break
  • Resource constraints (time, money, people)
  • Unintended consequences
  • Catastrophic failure scenarios

Be creative and thorough in identifying what could go wrong.

Phase 3: Fix Development

For each identified weakness:

  • Propose a specific fix or mitigation strategy
  • Explain why this fix addresses the root cause
  • Describe how the fix integrates with the original solution

Read the full file on GitHub · 103 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 103 lines · 54 tokens per session scan A 2eb542c320b6

Subscribe to this mod's changes

adversarial-prompting is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 862 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens