sycophancy-challenger

sycophancy-challenger is a skill for Claude Code from cnfeat/top-pm-skills. It costs 67 tokens per session (1,924 once invoked), scanned A, original, MIT.

A critique mode that challenges an idea, decision, plan, assumption, or pitch instead of mainly agreeing with it.

In plain words
What is it for?
Use it to produce adversarial critiques, steelmanned counterarguments, and the strongest case against your position.
Why use it?
It exposes the strongest objections and possible weaknesses before you commit to a high-stakes choice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pm-cross plugin — 7 skills shipped together

Good fit Use it to produce adversarial critiques, steelmanned counterarguments, and the strongest case against your position.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cnfeat/top-pm-skills/sycophancy-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.

Any agent
npx skills add cnfeat/top-pm-skills --skill sycophancy-challenger
Clone the repo
git clone --depth 1 https://github.com/cnfeat/top-pm-skills

Made for: Claude Code.

Or install pm-cross, the plugin that ships this one along with the rest of its 7 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 sycophancy-challenger

README.md
[![agentmods](https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/sycophancy-challenger/github.svg)](https://agentmods.dev/skills/cnfeat/top-pm-skills/sycophancy-challenger)
Your own site
<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/sycophancy-challenger"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/sycophancy-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 sycophancy-challenger

Your own site · 80×15
<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/sycophancy-challenger"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/sycophancy-challenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,924 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 $0.00067 $0.01924
Opus 5 $0.00034 $0.00962
Sonnet 5 $0.00013 $0.00385
Haiku 4.5 $0.00007 $0.00192

Measured 9d ago against content hash fcc3e74f57b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sycophancy-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.

参考skill/pm-claude-skills-main/pm-claude-skills-main/plugins/pm-cross/skills/sycophancy-challenger/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sycophancy Challenger

Claude defaults to validating. You bring a decision, it finds three reasons your instinct is solid, and you leave more confident but not more right. That's actively dangerous when the stakes are high — a hiring call, a pricing change, a strategy pivot, a public commitment. This skill flips the default: Claude argues against your idea first, holds its position under pushback, and only concedes when you give it new evidence. Not when you express displeasure.

Credit: Originally created by Joel Salinas (Leadership in Change) — adapted and extended for this library.


Required Inputs

Input Format Notes
Your idea, decision, plan, or assumption Describe it in plain language More context = sharper challenge. Include reasoning if you have it.

No other setup required. Activating the skill is enough — describe your idea and Claude will challenge it immediately.


Output Structure

Every response in this mode follows this exact format:

## Strongest Case AGAINST This

[The single most damaging criticism of the idea. Not a list of concerns — the
one argument that, if true, would kill this. Stated directly, without softening.]


## The Weakest Element

[The specific part of the idea most likely to fail, be wrong, or break under
real-world conditions. Named precisely. Not "execution risk" — the actual thing.]


## What You'd Need to Prove to Make This Work

[The assumptions that must be true for this idea to succeed. Written as testable
claims, not as encouragement. If an assumption can't be tested, that's noted.]


## What I Can't Find Fault With

[Only appears when a genuine search finds nothing damaging. States clearly what
holds up and why — doesn't invent weak praise to fill the section. If everything
is actually fine, says so plainly and explains why the challenge came up short.]

No additional sections. No summary. No "overall, this is a solid idea." The format ends when the four sections are complete.

Read the full file on GitHub · 165 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 · 165 lines · 67 tokens per session scan A fcc3e74f57b3

Subscribe to this mod's changes

sycophancy-challenger is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 1,924 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