challenge

challenge is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 132 tokens per session (1,018 once invoked), scanned A, original, MIT.

A structured way to question an AI answer or a planned decision by looking for weak assumptions and possible counterexamples. It includes several modes, such as playing devil’s advocate and checking a conclusion.

In plain words
What is it for?
Use it to challenge a proposed approach, test whether an answer is too confident, find holes in a decision, or get a second opinion.
Why use it?
AI output and human plans can sound convincing while still containing gaps. Deliberate pushback helps reveal those gaps before you act on them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the cognitive plugin — 8 skills shipped together

Good fit Use it to challenge a proposed approach, test whether an answer is too confident, find holes in a decision, or get a second opinion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/challenge
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 digital-stoic-org/agent-skills --skill challenge
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install cognitive, the plugin that ships this one along with the rest of its 8 skills.

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 challenge

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/challenge/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/challenge)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/challenge"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/challenge/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 challenge

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/challenge"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/challenge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 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 $0.00132 $0.01018
Opus 5 $0.00066 $0.00509
Sonnet 5 $0.00026 $0.00204
Haiku 4.5 $0.00013 $0.00102

Measured 9d ago against content hash 5400c3b30415, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

challenge 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.

cognitive/skills/challenge/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Challenge

Apply structured provocation patterns to force reconsideration of current work or upcoming intentions.

Target: $ARGUMENTS

Critical constraint

The interviewer (this skill, running in the main conversation) DELIVERS the queue. It NEVER regenerates findings in the main context. Regenerating brings anchoring back through the side door and destroys the benefit of the fresh-context generator. All finding generation happens in deep's sub-agent or, for forward/anchor/verify/framing, in the protocol execution itself — never re-derived afterward from parent-conversation reasoning.

Dispatch

Parse first word of $ARGUMENTS as subcommand. No recognized subcommand → route.

Subcommand Generator Delivery Protocol
route (default) none ≤5 lines, 0 sub-agent Read protocols/route.md → execute
forward main context, 5 patterns interactive walk Read protocols/forward.md → execute
anchor main context, 4 patterns interactive walk Read protocols/anchor.md → execute
verify main context, 3 patterns interactive walk Read protocols/verify.md → execute
framing main context, 2 patterns interactive walk Read protocols/framing.md → execute
deep fresh sub-agent, 9 patterns interactive walk, top-N see below
deep --report fresh sub-agent, 9 patterns batch report (legacy escape hatch) see below

/challenge <free-text description> with no matching subcommand keyword is route, not an error and not a menu — route is the default entry point.

Deep Subcommand

Spawn ONE sub-agent via the Agent tool:

  • subagent_type: dstoic:devil-advocate:devil-advocate
  • prompt: target description + relevant file paths to read
  • The agent executes all 9 patterns IN SEQUENCE (anchor: Gatekeeper, Reset, Alternative Approaches, Pre-mortem · verify: Proof Demand, CoVe, Fact Check List · framing: Socratic, Steelman) inside its own fresh context — not 9 parallel agents, one agent running 9 steps.
  • It returns a structured queue (reference.md §Queue Schema), not a batch report.
  • DO NOT pass parent conversation reasoning into the prompt — fresh context, uncontaminated by the anchoring already present in the main conversation, is the entire point.

Read the full file on GitHub · 76 lines

Files

What ships with it

6 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 · 76 lines · 132 tokens per session scan A 5400c3b30415

Subscribe to this mod's changes

challenge is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 1,018 once invoked, about $0.0007 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 2026-08-30.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens