Borrowing it
Nothing to install: this file belongs to dkships/substack-publisher-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/dkships/substack-publisher-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/dkships/substack-publisher-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/dkships/substack-publisher-mcp/claude-md)<a href="https://agentmods.dev/instructions/dkships/substack-publisher-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dkships/substack-publisher-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/dkships/substack-publisher-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dkships/substack-publisher-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 | $0.00706 | $0.00706 |
| Opus 5.5 | $0.00282 | $0.00282 |
| Sonnet 5.5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
substack-publisher-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 15d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Substack Publisher MCP
MCP server for Substack's official Publisher API. TypeScript, ES modules, @modelcontextprotocol/sdk with stdio transport, native fetch (no HTTP framework). Setup and tool docs: README.md.
Commands
npm run build # Compile TypeScript to dist/
npm test # Unit tests (node:test via tsx)
npm start # Run the server
Run npm run build after source changes — MCP clients execute dist/index.js, not the TypeScript source.
Environment variables
- Read directly from
process.env; the server never loads.envfiles. Set vars in the MCP client config, or in your shell fornpm start. - Keys:
SUBSTACK_API_KEY(single publication) orSUBSTACK_API_KEY_<NAME>(multi-publication). - Never commit API key values.
Conventions
- Use
registerTool/registerResourcefor MCP registration (not deprecated.tool()) - API clients live in their own module under
src/(e.g.,substack.ts) - Return raw structured data from tools; let the caller synthesize
- Errors return
isError: truewith the message - When documenting API behavior, verify against the code and live Substack API responses — do not assume
Definition of done
npm run buildcompiles,npm testpasses,npm startboots without errors
Code style
Adapted from Fabien Sanglard's agent.md (2026-08-21).
- Avoid magic numbers and strings. Extract recurring or meaningful values into named constants or enums; leave self-explanatory one-off values inline. A value defined by a spec (HTTP 200, a protocol byte) gets a constant regardless.
- Reduce indentation. Use early returns and
continueinstead of nesting. - Keep function names under 30 characters.
- Use an enum or a string-literal union instead of a boolean parameter.
- Put blank lines between logical blocks. Let the reader breathe.
- Comment what a block does and why, briefly. Use an example where it helps; offer an ASCII diagram when explaining a whole system.
- Treat a visibility change as a breaking design shift. Keep things private or unexported unless the design requires external access, and ask before widening one.
- Program to levels of abstraction. Low-level mechanics (raw SQL, socket streams, vendor SDK calls, file parsing) live behind a driver or service layer; callers work in domain concepts.
- Hold the layer boundaries. Each layer talks only to the one directly below it, with no holes punched through: a UI component never calls the database or a raw HTTP client directly.
- Don't touch code unrelated to the feature you're implementing, including adding comments to blocks you didn't write. Minimize changed lines.
- Always use braces, even on a one-line
if. - Fixing a bug: write the failing test first, watch it fail, then write the fix and watch it pass.
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.
- 15d ago Changed · +2 lines · +5 tokens per session f684f26b2ba2
- 2mo ago First seen · 55 lines · 701 tokens per session scan A 28cc48414517
substack-publisher-mcp CLAUDE.md is an instructions file published in the GitHub repository dkships/substack-publisher-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 706 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.
substack-publisher-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| substack-publisher-mcp CLAUDE.mddkships/substack-publisher-mcp | Instructions file | 6 | 2d ago | MIT | A | 706 | 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 | today | 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 |