Borrowing it
Nothing to install: this file belongs to sandraschi/substack-mcp. 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/sandraschi/substack-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/sandraschi/substack-mcpWrote 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/sandraschi/substack-mcp/claude-md)<a href="https://agentmods.dev/instructions/sandraschi/substack-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/substack-mcp/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/sandraschi/substack-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/substack-mcp/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 | $0.00338 | $0.00338 |
| Opus 5.5 | $0.00135 | $0.00135 |
| Sonnet 5.5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
substack-mcp 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.
What it actually says
CLAUDE.md — substack-mcp Development Directives
Purpose: Agent instructions and quick reference commands for substack-mcp.
Port Allocation
- Backend (FastAPI + FastMCP HTTP
/mcp):11163 - Frontend Webapp (Vite React SPA):
11164
Commands
# Backend Dev Server
uv run python -m substack_mcp.server --port 11163
# Frontend Webapp Dev Server
cd webapp && npm run dev
# Unified Start Script (Clears port zombies, launches uvicorn & vite, opens browser)
powershell -ExecutionPolicy Bypass -File .\start.ps1
# Run Tests
uv run pytest
# Python Lint & Format
uv run ruff check .
uv run ruff format .
# Webapp Biome Lint & Format
cd webapp && npm run lint
cd webapp && npm run format
# Webapp Build
cd webapp && npm run build
# Run Full Quality Suite
just check
Conventions & Rules
- FastMCP 3.1+: All tools must use the Portmanteau pattern (consolidated tools with an
operationparameter). - SQLite Storage: All data persists in
data/substack.sqlite3. - Ruff & Biome: Maintain 0 lint errors in both Python (
ruff check) and TypeScript (biome check .). - No Bare Ports: Always clear ports
11163and11164before binding.
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 · 46 lines · 338 tokens per session scan A c3ea7b328f00
substack-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/substack-mcp (1 stars, last pushed 17d ago), licensed MIT. It adds 338 tokens to every session, about $0.0014 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.
substack-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| substack-mcp CLAUDE.mdsandraschi/substack-mcp | Instructions file | 1 | 17d ago | MIT | A | 338 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |