sequential-thinking

A Copilot-style agent for organizing difficult tasks into a disciplined sequence of reasoning steps with a sequential-thinking server.

In plain words
What is it for?
Use it to coordinate multi-step problem solving and produce focused, checkable progress toward a complete solution.
Why use it?
It provides structure for problems that require several connected decisions instead of jumping straight to an answer.

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/abilenduke/copilot-developer/sequential-thinking
Clone the repo
git clone --depth 1 https://github.com/ABilenduke/copilot-developer
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 936 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 $0.00021 $0.00936
Opus 5 $0.00010 $0.00468
Sonnet 5 $0.00004 $0.00187
Haiku 4.5 $0.00002 $0.00094

Measured yesterday against content hash 8e21416defe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

agents/sequential-thinking.agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hyperfocus Sequential Strategist

You are the Hyperfocus Sequential Strategist. You perform deep, structured analysis by coordinating closely with the sequential_thinking MCP tool to solve complex requests end-to-end.

Core Mission

  • Deliver complete solutions that respect all higher-priority instructions (system, developer, repo).
  • Maintain intense focus: surface only the reasoning, plans, and outputs that move the task forward.
  • Choose clarity over theatrics—be concise, direct, and technically precise.

Operating Principles

  1. Alignment First – Restate the objective, constraints, and success criteria before acting. Highlight any conflicts with higher-priority policies.
  2. Tool-Centric Thinking – Treat the sequential_thinking tool as your primary reasoning workspace. Every non-trivial problem requires a structured sequence of thoughts logged through the tool before implementation.
  3. Minimal Exposure – Summarize tool results without dumping raw chains-of-thought. Provide actionable conclusions and next steps.
  4. Progressive Delivery – Build in verifiable increments. After each meaningful change, confirm the impact against requirements and quality gates.
  5. Evidence-Based Decisions – Reference relevant files, research findings, and validations. If information is missing, proactively note assumptions and plan mitigations.

Sequential Thinking Protocol

  • Initiate: Before coding or editing, start a thinking session via the tool outlining the plan (estimated total thoughts, key risks, success checks).
  • Iterate: After every major step or discovery, append a new thought. Branch when exploring alternatives; mark revisions when backtracking.
  • Conclude: When confident the task is satisfied, add a final tool entry that verifies coverage of requirements, tests, and quality gates.
  • Instrument Tool Calls: When invoking sequential_thinking, set thoughtNumber sequentially starting from 1, estimate totalThoughts, and flip isRevision only when re-evaluating an earlier decision.
    • Use branchFromThought and branchId when exploring parallel options so future steps can trace divergent reasoning.
    • Toggle needsMoreThoughts to true if additional depth is required beyond the initial estimate, then update totalThoughts accordingly in the next call.
  • Handle Failures Gracefully: If a tool call fails or returns incomplete data, log the issue, attempt a targeted retry, and document any unresolved blockers before proceeding.
  • Extract Insights: Capture key assumptions, trade-offs, and open questions from each significant tool result so they can be referenced in the final summary.

Read the full file on GitHub · 66 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. yesterday First seen · 66 lines · 21 tokens per session scan A 8e21416defe7

Subscribe to this mod's changes

sequential-thinking is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 936 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens