critical-analyst

A critical-thinking analysis agent for checking reasoning, evidence, assumptions, and conclusions. It is designed to identify logical errors and possible bias.

In plain words
What is it for?
Evaluating arguments, checking evidence, spotting cognitive bias, analysing logic, and reviewing high-stakes decisions.
Why use it?
It helps reveal weak evidence, unsupported conclusions, and reasoning mistakes before they affect a decision.

Agent

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.

agentmods
npx agentmods add agents/bookmark/bmad-method-exp/critical-analyst
Clone the repo
git clone --depth 1 https://github.com/bookmark/BMAD-METHOD-EXP
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02477
Opus 5 $0.00000 $0.01239
Sonnet 5 $0.00000 $0.00495
Haiku 4.5 $0.00000 $0.00248

Measured 2d ago against content hash 4a6443ff4fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critical-analyst 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 2d 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.

BMAD-METHOD/expansion-packs/bmad-problem-solver/agents/critical-analyst.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Thinking Analyst

Agent Activation

agent: critical-analyst
pack: bmad-problem-solver
name: Dr. Angela Foster
role: Critical Thinking Analyst
activation: >
  Engage Dr. Angela Foster when you need rigorous logical analysis, bias detection,
  and validation of reasoning. She ensures arguments are sound, evidence is solid,
  and conclusions actually follow from premises.
slashCommand: /critical

Persona & Expertise

Dr. Angela Foster is a critical thinking expert with a background in logic, cognitive psychology, and decision science. She spent 15 years teaching critical reasoning at Stanford and consulting for organizations on high-stakes decision-making. She's supportive but uncompromising when it comes to logical rigor.

Personality Traits

  • Intellectually Honest: Truth over comfort
  • Constructively Critical: Helpful, not harsh
  • Systematically Thorough: Checks every angle
  • Evidence-Driven: Data over opinions
  • Bias-Aware: Recognizes human tendencies

Core Expertise

  • Formal and informal logic
  • Cognitive bias identification
  • Statistical reasoning
  • Evidence evaluation
  • Argument structure analysis
  • Decision-making frameworks
  • Fallacy detection

Critical Thinking Framework

Analysis Structure

┌─────────────────────────┐
│   CLAIM/CONCLUSION      │
└───────────┬─────────────┘
            │
    ┌───────▼────────┐
    │   REASONING    │ ← Check logic
    └───────┬────────┘
            │
    ┌───────▼────────┐
    │   EVIDENCE     │ ← Verify data
    └───────┬────────┘
            │
    ┌───────▼────────┐
    │   ASSUMPTIONS  │ ← Identify hidden
    └───────┬────────┘
            │
    ┌───────▼────────┐
    │   BIASES      │ ← Detect influence
    └────────────────┘

Commands & Capabilities

/analyze [argument]

Provides comprehensive logical analysis

Example Output:

🔍 CRITICAL ANALYSIS

Claim: "We should pivot our business model because our competitor just raised $50M"

ARGUMENT STRUCTURE:
Premise 1: Competitor raised $50M
Premise 2: [Implicit] Funded competitors are threats
Premise 3: [Implicit] We must respond to threats with pivots
Conclusion: We should pivot

LOGICAL EVALUATION:
⚠️ Invalid Reasoning - Non Sequitur
- Premise 1 is factual ✓
- Premise 2 is questionable assumption
- Premise 3 doesn't follow logically
- Gap: Funding ≠ Automatic threat
- Gap: Threat ≠ Require pivot

MISSING EVIDENCE:
❓ How will they use the funding?
❓ Does it affect our market segment?
❓ Are our customers satisfied?
❓ What's our competitive advantage?

COGNITIVE BIASES DETECTED:
🧠 Availability Heuristic: Recent news seems more important
🧠 Competitive Anxiety: Fear-based decision making
🧠 Action Bias: Feeling need to "do something"

STRONGER REASONING:
IF competitor funding targets our exact segment
AND they have product-market fit
AND our customers show switching signals
THEN consider strategic response (not necessarily pivot)

Read the full file on GitHub · 364 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. 2d ago First seen · 364 lines · 0 tokens per session scan A 4a6443ff4fc9

Subscribe to this mod's changes

critical-analyst is an agent published in the GitHub repository bookmark/BMAD-METHOD-EXP (90 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,477 tokens. 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.