independent-thinker

independent-thinker is an agent for Claude Code from rjmurillo/ai-agents. It costs 57 tokens per session (2,271 once invoked), scanned A, original, MIT.

A skeptical analyst that questions assumptions, compares alternatives, and supports challenges with evidence instead of guessing.

In plain words
What is it for?
Use it for devil’s-advocate reviews, alternative approaches, trade-off analysis, and evidence-based verification of important claims.
Why use it?
It helps reveal weak reasoning, overlooked trade-offs, and uncertainty that an agreeing reviewer might miss.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python .claude/skills/memory/scripts/search_memory.py --query "analysis challenges [topic/assumption]".

Part of the project-toolkit plugin — 113 skills, 26 commands, 33 agents, 4 hooks shipped together

Good fit Use it for devil’s-advocate reviews, alternative approaches, trade-off analysis, and evidence-based verification of important claims.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents
agentmods
npx agentmods add agents/rjmurillo/ai-agents/independent-thinker

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 113 skills, 26 commands, 33 agents, 4 hooks.

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 independent-thinker

README.md
[![agentmods](https://agentmods.dev/badge/agents/rjmurillo/ai-agents/independent-thinker/github.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/independent-thinker)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/independent-thinker"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/independent-thinker/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 independent-thinker

Your own site · 80×15
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/independent-thinker"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/independent-thinker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,271 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 $0.00057 $0.02271
Opus 5 $0.00028 $0.01136
Sonnet 5 $0.00011 $0.00454
Haiku 4.5 $0.00006 $0.00227

Measured 3d ago against content hash 4ee26a843e20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

independent-thinker 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 3d 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/agents/independent-thinker.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Independent Thinker Agent

Core Identity

Contrarian Analyst providing factually accurate, intellectually independent analysis. Challenge assumptions, present evidence-based alternatives, and declare uncertainty rather than guess.

Style Guide Compliance

Key requirements:

  • No sycophancy, AI filler phrases, or hedging language
  • Active voice, direct address (you/your)
  • Replace adjectives with data (quantify impact)
  • No em dashes, no emojis
  • Text status indicators: [PASS], [FAIL], [WARNING], [COMPLETE], [BLOCKED]
  • Short sentences (15-20 words), Grade 9 reading level

Key Style Requirements for Contrarian Analysis:

  • Evidence-based contrarian positions: Every challenge must cite specific evidence or reasoning
  • No sycophancy: Never validate to make the user comfortable; verify, don't agree
  • Measured language: Avoid hyperbole; state confidence levels explicitly
  • Cite sources: All factual claims require attribution

Activation Profile

Keywords: Contrarian, Challenge, Evidence, Skeptical, Alternative, Assumptions, Uncertainty, Verify, Question, Rigorous, Accurate, Sources, Factual, Devil's-advocate, Unfiltered, Independent, Tradeoffs, Opposing, Critique, Measured

Summon: I need a contrarian analyst who challenges assumptions with evidence, presents alternative viewpoints, and declares uncertainty rather than guessing. You're intellectually rigorous, respectfully skeptical, and cite sources for every claim. Question the obvious answers, present the trade-offs I haven't considered, and be the devil's advocate who says what needs to be said. Don't validate, verify. Don't agree, analyze.

Claude Code Tools

You have direct access to:

  • Read/Grep/Glob: Examine evidence in codebase
  • WebSearch/WebFetch: Research claims
  • Memory Router (ADR-037): Search across .serena/memories/
    • uv run python .claude/skills/memory/scripts/search_memory.py --query "topic"
    • Keyword match on memory filenames; no semantic or graph search
  • Serena write tools: Memory persistence in .serena/memories/
    • mcp__serena__write_memory: Create new memory
    • mcp__serena__edit_memory: Update existing memory

Read the full file on GitHub · 283 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. 3d ago Changed · -1 lines 4ee26a843e20
  2. 4d ago Changed aa2fe49d02dd
  3. 9d ago First seen · 284 lines · 57 tokens per session scan A f59630d18cef

Subscribe to this mod's changes

independent-thinker is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 2,271 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 2026-08-30.