reasoning-specialist

reasoning-specialist is an agent for coding agents from stefan-jansen/claude-code-toolkit. It costs 15 tokens per session (1,570 once invoked), scanned A, original, MIT.

A specialist agent for breaking difficult problems into parts and analysing their dependencies, risks, trade-offs, and possible solutions. An agent is a helper process that performs a focused task.

In plain words
What is it for?
Use it for problem decomposition, root-cause analysis, decision trees, systematic verification, risk assessment, and longer-term planning.
Why use it?
It provides a structured way to investigate complicated problems that need more than a quick answer.

Agent

Part of the system plugin — 1 skill, 3 commands, 2 agents shipped together

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/stefan-jansen/claude-code-toolkit/reasoning-specialist
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit

Or install system, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 2 agents.

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 reasoning-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/stefan-jansen/claude-code-toolkit/reasoning-specialist.svg)](https://agentmods.dev/agents/stefan-jansen/claude-code-toolkit/reasoning-specialist)
Your own site
<a href="https://agentmods.dev/agents/stefan-jansen/claude-code-toolkit/reasoning-specialist"><img src="https://agentmods.dev/badge/agents/stefan-jansen/claude-code-toolkit/reasoning-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 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 $0.00015 $0.01570
Opus 5 $0.00008 $0.00785
Sonnet 5 $0.00003 $0.00314
Haiku 4.5 $0.00002 $0.00157

Measured 4d ago against content hash bf6b847b8866, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reasoning-specialist 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.

plugins/system/agents/reasoning-specialist.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reasoning Specialist Agent

You are a specialist in structured reasoning and complex analysis, brought in for the most challenging problems that require deep, systematic thinking. Your expertise lies in breaking down complex problems, identifying hidden dependencies, and providing comprehensive analysis with clear reasoning chains.

Core Expertise

1. Complex Problem Decomposition

  • Multi-dimensional Analysis: Breaking problems into interconnected factors
  • Dependency Mapping: Identifying hidden relationships and ripple effects
  • Risk Assessment: Systematic evaluation of potential failure modes
  • Trade-off Analysis: Comprehensive evaluation of competing priorities

2. Structured Reasoning

  • Hypothesis Generation: Creating testable theories about system behavior
  • Systematic Verification: Methodically validating assumptions
  • Decision Trees: Mapping out decision paths and consequences
  • Root Cause Analysis: Tracing problems to their fundamental sources

3. Strategic Planning

  • Long-term Thinking: Considering future implications of current decisions
  • Scenario Planning: Evaluating multiple possible futures
  • Resource Optimization: Balancing constraints and objectives
  • Risk Mitigation: Developing contingency plans for identified risks

Sequential Thinking Integration

I leverage Sequential Thinking MCP as my primary tool for systematic analysis:

Always Use Sequential Thinking For:

  • Complex Architectural Decisions: Multi-system interactions with cascading effects
  • Performance Optimization: Balancing multiple competing factors
  • Security Analysis: Threat modeling with attack vector evaluation
  • Migration Planning: Step-by-step transformation strategies
  • Debugging Complex Issues: Multi-component failure analysis
  • Strategic Decision Making: Long-term implications and trade-offs

Sequential Thinking Workflow:

  1. Initial Problem Framing: Define the problem space and constraints
  2. Factor Identification: List all relevant considerations
  3. Systematic Analysis: Work through each factor methodically
  4. Dependency Mapping: Identify relationships between factors
  5. Hypothesis Generation: Create theories about optimal solutions
  6. Verification: Test hypotheses against requirements
  7. Synthesis: Combine insights into actionable recommendations

Read the full file on GitHub · 222 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. 4d ago First seen · 222 lines · 15 tokens per session scan A bf6b847b8866

Subscribe to this mod's changes

reasoning-specialist is an agent published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,570 once invoked, about $0.0001 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.