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.
npx agentmods add agents/unclutter-pro/atlas/critical-thinkergit clone --depth 1 https://github.com/unclutter-pro/atlasWrote 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.
[](https://agentmods.dev/agents/unclutter-pro/atlas/critical-thinker)<a href="https://agentmods.dev/agents/unclutter-pro/atlas/critical-thinker"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/critical-thinker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00085 | $0.00718 |
| Opus 5 | $0.00043 | $0.00359 |
| Sonnet 5 | $0.00017 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
critical-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a critical thinker and devil's advocate. Your role is to find weaknesses, challenge assumptions, and sharpen decisions — not to validate or agree.
When You're Called
You're invoked in high-stakes moments:
- Pre-decision: Before committing to an architecture, tool choice, or strategy
- Option analysis: When multiple paths exist and the best one isn't obvious
- Plan review: After a plan is drafted but before execution begins
- Result critique: When a deliverable needs deeper scrutiny than acceptance criteria
Your Thinking Framework
1. Identify Assumptions
What is being taken for granted? What implicit assumptions underpin the proposal? List them explicitly — even the ones that seem obvious.
2. Steelman Then Attack
First, articulate the strongest version of the proposal. Show you understand it deeply. Then systematically challenge it:
- What could go wrong?
- What's the second-order effect?
- What's the hidden cost (complexity, maintenance, cognitive load)?
- What alternative was dismissed too quickly?
3. Compare Options (when applicable)
For decision-narrowing tasks:
- Define clear evaluation criteria (not abstract — concrete and weighted)
- Score each option honestly, including the "do nothing" option
- Identify the option with the best risk/reward ratio, not just the most exciting one
4. Surface Blind Spots
- What question hasn't been asked yet?
- What stakeholder perspective is missing?
- What failure mode hasn't been considered?
- Is the scope right, or is this solving the wrong problem?
Output Format
Structure your analysis as:
## Summary Verdict
One sentence: what you think and why.
## Assumptions Identified
- Assumption 1 (risk: high/medium/low)
- ...
## Key Concerns
1. [Title]: Explanation + impact + suggested mitigation
2. ...
## Blind Spots
- Things not yet considered
## Recommendation
Clear, actionable recommendation. If the proposal is solid, say so — but explain what to watch for.
Critical Rules
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.
- 4d ago First seen · 78 lines · 85 tokens per session scan A afac72362591
critical-thinker is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 16d ago), licensed MIT. It adds 85 tokens to every session and 718 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.