What is anti-sycophant-ai-agent-skills CLAUDE.md?

A collection of skills and commands that make AI assistants question an idea's assumptions instead of automatically agreeing with it.

It is for pressure-testing ideas, separating hobby projects from businesses, requesting honest user conversations, and running reality checks.

It helps distinguish genuine evidence from enthusiasm, weak validation, or an attractive but unproven business premise.

How machinesoul11/anti-sycophant-ai-agent-skills configures Claude Cod

Reuse

Borrowing it

Nothing to install: this file belongs to machinesoul11/anti-sycophant-ai-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/machinesoul11/anti-sycophant-ai-agent-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/machinesoul11/anti-sycophant-ai-agent-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md/github.svg)](https://agentmods.dev/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/machinesoul11/anti-sycophant-ai-agent-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 497 This file is loaded in full into every session.

When invoked 497 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00497	$0.00497
Opus 5.5	$0.00199	$0.00199
Sonnet 5.5	$0.00099	$0.00099
Haiku 4.5	$0.00050	$0.00050

Measured 2mo ago against content hash c750363e4635, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anti-sycophant-ai-agent-skills CLAUDE.md 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 2mo 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.

CLAUDE.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

anti-sycophant

This repo is a pack of skills designed to get AI assistants — including Claude — to stop agreeing with bad product ideas by default. The skills install as a Claude Code plugin, but the underlying SKILL.md files are portable Markdown and work with any LLM.

What's in here

skills/
  prove-the-premise/     SKILL.md   Pressure-test an idea's premise before any build.
  hobby-or-business/     SKILL.md   Separate project enthusiasm from business reality.
  one-real-conversation/ SKILL.md   Reject validation theater; demand one honest human conversation.

.claude/commands/        Two slash commands: /validate-idea, /reality-check
.gemini/commands/        Same two, as Gemini CLI TOML
docs/                    Per-tool setup guides (Claude Code, Claude.ai, Cursor, Gemini, Codex, others)
.claude-plugin/          Claude Code plugin + marketplace manifests

Conventions

One skill per directory: skills/<kebab-case-name>/SKILL.md. The directory name must match the name: frontmatter field exactly.
Every skill has YAML frontmatter with name and description. The description must include both what the skill does and explicit Use when / Do NOT use when clauses — the model decides whether to load the skill purely from the description.
Every skill has an off-switch. A skill without one becomes a nag and gets ignored.
Skills are short by default in the output they produce, even when the skill body itself is long. "Lead with the verdict, two or three points, offer to expand" is the response shape.

When working in this repo

New skills go in skills/<name>/SKILL.md only. No scripts/ directory unless the skill actually ships a runnable helper.
Don't add hooks, validation pipelines, or test infrastructure unless asked. The repo is intentionally minimal.
Don't soften the tone of existing skills. Bluntness is the point. But never cruelty — that's a tone bug, not toughness.
Cross-reference skills by name rather than duplicating content (e.g. "see one-real-conversation for validation theater").
See docs/skill-anatomy.md for the full format spec and CONTRIBUTING.md for the quality bar.

Read the full file on GitHub · 33 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.

2mo ago First seen · 33 lines · 497 tokens per session scan A c750363e4635

Subscribe to this mod's changes

anti-sycophant-ai-agent-skills CLAUDE.md is an instructions file published in the GitHub repository machinesoul11/anti-sycophant-ai-agent-skills (34 stars, last pushed 3mo ago), licensed MIT. It adds 497 tokens to every session, about $0.0020 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 2026-08-30.

Building agents ai ai-agents claude codex gemini skills

anti-sycophant-ai-agent-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
anti-sycophant-ai-agent-skills CLAUDE.mdmachinesoul11/anti-sycophant-ai-agent-skills	Instructions file	34	3mo ago	MIT	A	497	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

anti-sycophant-ai-agent-skills: Instructions file for Claude Code