sequential-thinking

sequential-thinking is a skill for Claude Code, Codex from antoinebou12/uml-mcp. It costs 72 tokens per session (610 once invoked), scanned A, original, MIT.

A step-by-step problem-solving guide for complex tasks, planning, and analysis. It encourages ordered reasoning, checking earlier assumptions, and revising the approach when new information appears.

In plain words
What is it for?
Use it when designing a solution, breaking down a difficult task, comparing approaches, or working through a problem that needs several revisions.
Why use it?
It helps keep multi-step work organized when the problem is unclear or likely to change during investigation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when designing a solution, breaking down a difficult task, comparing approaches, or working through a problem that needs several revisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/antoinebou12/uml-mcp/sequential-thinking
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.

Any agent
npx skills add antoinebou12/uml-mcp --skill sequential-thinking
Clone the repo
git clone --depth 1 https://github.com/antoinebou12/uml-mcp

Made for: Claude Code, Codex.

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 sequential-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/sequential-thinking.svg)](https://agentmods.dev/skills/antoinebou12/uml-mcp/sequential-thinking)
Your own site
<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/sequential-thinking"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/sequential-thinking.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 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 $0.00072 $0.00610
Opus 5 $0.00036 $0.00305
Sonnet 5 $0.00014 $0.00122
Haiku 4.5 $0.00007 $0.00061

Measured 7d ago against content hash bccc58119520, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sequential-thinking 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 7d 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.

.skill/skills/sequential-thinking/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sequential Thinking

Break down complex work into ordered steps, revise when needed, and produce one clear answer. Use for multi-step tasks, planning, and problems where scope or approach may change.

When to Use

  • Complex or multi-step tasks
  • Planning and design with room for revision
  • Analysis that might need course correction
  • Problems where the full scope is unclear at the start
  • Tasks that need context carried across steps
  • When irrelevant information must be filtered out
  • When the user asks for step-by-step reasoning

Behavior Without the MCP Tool

  1. Break the task into ordered steps.
  2. State one step at a time; build on the previous step.
  3. Revise earlier steps when you discover they are wrong or incomplete.
  4. Branch or backtrack when exploring alternatives.
  5. Generate a solution hypothesis when appropriate; verify it against the steps.
  6. Repeat until satisfied, then give a single, clear final answer.

Principles: Start with an estimate of how many steps you need and adjust as you go. Express uncertainty. Ignore information that is irrelevant to the current step.

Using the Sequential Thinking MCP Tool

When the sequentialthinking MCP tool is enabled (e.g. user-sequential-thinking server), prefer calling it for hard problems so thoughts are tracked and revisable.

  • Required every call: thought (current step), thoughtNumber, totalThoughts, nextThoughtNeeded.
  • Start with an initial estimate of totalThoughts; increase or decrease as you progress.
  • Set nextThoughtNeeded: true until you are done; set nextThoughtNeeded: false only when you have a satisfactory final answer.
  • Revisions: Set isRevision: true and revisesThought to the thought number you are reconsidering.
  • Branches: Use branchFromThought (thought number) and branchId (e.g. "alt-1") when exploring a different path.
  • More thoughts later: Set needsMoreThoughts: true when you reach what seemed like the end but realize you need more steps.

Read the full file on GitHub · 52 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. 7d ago First seen · 52 lines · 72 tokens per session scan A bccc58119520

Subscribe to this mod's changes

sequential-thinking is a skill published in the GitHub repository antoinebou12/uml-mcp (99 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 610 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 2026-08-30.