Borrowing it
Nothing to install: this file belongs to qurihara/scrapbox-cosense-mcp-editable. 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/qurihara/scrapbox-cosense-mcp-editable/main/CLAUDE.mdgit clone --depth 1 https://github.com/qurihara/scrapbox-cosense-mcp-editableWrote 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/qurihara/scrapbox-cosense-mcp-editable/claude-md)<a href="https://agentmods.dev/instructions/qurihara/scrapbox-cosense-mcp-editable/claude-md"><img src="https://agentmods.dev/badge/instructions/qurihara/scrapbox-cosense-mcp-editable/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/qurihara/scrapbox-cosense-mcp-editable/claude-md"><img src="https://agentmods.dev/badge/instructions/qurihara/scrapbox-cosense-mcp-editable/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 | $0.01095 | $0.01095 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
scrapbox-cosense-mcp-editable 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MCP server for Cosense (Scrapbox). Also works as a CLI.
Commands
npm run build # TypeScript → JavaScript (uses tsconfig.build.json)
npm run watch # Auto-rebuild during development
npm run test # Run Jest tests
npm run lint # ESLint (console.log triggers warning)
npm run inspector # Debug with MCP Inspector
Architecture
Tools (7)
| Tool | Description | Auth |
|---|---|---|
get_page |
Retrieve page content, metadata, and links | - |
list_pages |
List pages with sorting and pagination (max 1000) | - |
search_pages |
Keyword search (API limit: 100 results) | - |
create_page |
Create new page. Rejects if page already exists | SID |
get_page_url |
Generate URL from page title | - |
insert_lines |
Insert text after a target line (exact match). Appends to end if not found | SID |
get_smart_context |
Get page + linked pages (1-hop/2-hop) in AI-optimized format | SID |
CLI
All tools are also available as CLI subcommands (get, list, search, create, url, insert, context). Run scrapbox-cosense-mcp <command> --help for usage. Key flags:
--compact— Token-efficient output (85% smaller for list)--json— JSON output--project=NAME— Override project name
Skill (SKILL.md)
skills/scrapbox/SKILL.md defines a Claude Code skill that wraps the CLI. When users invoke /cosense, Claude Code reads SKILL.md and executes CLI commands via Bash. Keep SKILL.md concise — details should be discoverable via --help.
Desktop Extensions (.mcpb)
manifest.json + .mcpbignore enable Claude Desktop Extensions packaging. The .mcpb file is auto-built and attached to GitHub Releases by release-mcpb.yml. To build locally: npm install --omit=dev && npx @anthropic-ai/mcpb pack.
Directory Structure
src/cosense.ts— Scrapbox REST API clientsrc/routes/handlers/— One handler module per toolsrc/utils/format.ts— Response formatting,stringifyError,formatErrorsrc/utils/sort.ts— Sorting with pinned page filteringsrc/utils/markdown-converter.ts— Markdown → Scrapbox conversion (usesmd2sb)src/types/— API response and MCP request/response type definitionssrc/cli.ts— CLI entry point (args → CLI mode, no args → MCP server)src/index.ts— Server entry point
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.
- 9d ago First seen · 95 lines · 1,095 tokens per session scan A 1c100f97148f
scrapbox-cosense-mcp-editable CLAUDE.md is an instructions file published in the GitHub repository qurihara/scrapbox-cosense-mcp-editable (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,095 tokens to every session, about $0.0055 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.