Borrowing it
Nothing to install: this file belongs to spideynolove/sequential-thinking-mcp-v2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spideynolove/sequential-thinking-mcp-v2/main/CLAUDE.mdgit clone --depth 1 https://github.com/spideynolove/sequential-thinking-mcp-v2Wrote 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/instructions/spideynolove/sequential-thinking-mcp-v2/claude-md)<a href="https://agentmods.dev/instructions/spideynolove/sequential-thinking-mcp-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/spideynolove/sequential-thinking-mcp-v2/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/spideynolove/sequential-thinking-mcp-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/spideynolove/sequential-thinking-mcp-v2/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00700 | $0.00700 |
| Opus 5.5 | $0.00280 | $0.00280 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
sequential-thinking-mcp-v2 CLAUDE.md 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 2mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code when working in this repository.
Current State
This repository is still the older markdown-only implementation of sequential-thinking-mcp-v2. The approved direction is now documented in:
docs/plans/2026-03-08-agent-memory-reasoning-architecture-design.mddocs/plans/2026-03-08-agent-memory-architecture.md
When repository behavior and these design docs disagree, treat the design docs as the target architecture and the codebase as transitional.
Development Notes
Historical docs reference:
uv sync
uv run main.py
Use those commands only if the dependency manifest exists in the checkout you are working from. Do not assume pyproject.toml is present.
Target Architecture Boundaries
Memory Layers
- Markdown is canonical human truth.
qmdowns retrieval for canonical docs and document collections.Zvecowns retrieval for promoted memory artifacts and non-doc semantic artifacts.- A small structured metadata store owns lifecycle state such as confidence, evidence, promotion status, staleness, scope, and sync state.
- Cloud memory is an optional overlay for continuity, never the source of truth.
Reasoning Rules
- Scratch reasoning is ephemeral and bounded.
- Checkpoint summaries are recovery artifacts.
- Promoted conclusions are the only durable machine memory.
- Raw chain-of-thought should not be stored as long-term memory by default.
- Promotion requires evidence, sufficient confidence, and likely reuse value.
Retrieval Rules
- Retrieval is on demand and scoped to the active task.
- Do not preload the whole codebase into context.
- Pass handoff bundles and summaries between agents, not raw transcripts.
- Token ceilings like
64Kactive context and45Kcompaction triggers are policy defaults, not universal facts.
qmd Indexing Policy
Treat qmd indexing as a controlled workflow. Do not automatically spam indexing/update commands on every small change, and do not modify qmd's database directly. Queue or batch indexing work instead.
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.
- 2mo ago First seen · 91 lines · 700 tokens per session scan A 6021438592ce
sequential-thinking-mcp-v2 CLAUDE.md is an instructions file published in the GitHub repository spideynolove/sequential-thinking-mcp-v2 (9 stars, last pushed 7mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0028 per session on Opus 5.5. 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.
sequential-thinking-mcp-v2 CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sequential-thinking-mcp-v2 CLAUDE.mdspideynolove/sequential-thinking-mcp-v2 | Instructions file | 9 | 7mo ago | MIT | A | 700 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |