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.
npx agentmods add instructions/damienbenveniste/substack-mcp/agents-mdgit clone --depth 1 https://github.com/damienbenveniste/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/damienbenveniste/substack-mcp/agents-md)<a href="https://agentmods.dev/instructions/damienbenveniste/substack-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/damienbenveniste/substack-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01203 | $0.01203 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
substack-mcp AGENTS.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 3d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
These rules apply to every code, test, documentation, and configuration change in this repository.
Project Orientation
- This is
substack-mcp, a strict TypeScript package generated byscaffold-guard. - Keep source in
src/and tests intests/. - Treat this file as the shared instruction source for coding agents.
- This repository implements a private Substack draft MCP server. Keep product scope draft-only unless the user explicitly changes that boundary.
- Keep roadmap and milestone material in plan documents or README sections, not in this operating contract.
Working Style
- Start by inspecting relevant files, tests, docs, and current repository state.
- Make focused changes that satisfy the request without unrelated rewrites.
- Preserve user changes and do not overwrite existing work without explicit intent.
- Do not claim completion until relevant validation has passed or a concrete blocker is reported.
Delegation and External Context
- Keep the main thread focused on decisions, edits, validation, and final synthesis.
- For non-trivial implementation work, use worker subagents when available and assign concrete files, modules, templates, docs, tests, or configuration ownership before substantial local edits.
- Use read-only subagents for bounded work that would otherwise clutter the main thread: broad codebase reconnaissance, test-failure triage, documentation review, compatibility research, or issue/PR summarization.
- Give subagents a narrow brief with explicit paths, ownership, expected output, and recommended validation. Do not delegate final judgment, destructive actions, secret handling, or release decisions.
- Treat subagent output as evidence to verify, not as authoritative truth. The primary agent owns all edits and completion claims.
- Use MCP servers when available for current external context: repository hosting for issues, PRs, and CI; documentation/context servers for library APIs; browser tools for rendered UI checks; and read-only database or observability servers for diagnostics.
- Keep MCP usage read-only unless the user explicitly asks for mutation. If an MCP server is unavailable, continue with repo-local evidence and state the limitation.
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.
- 3d ago First seen · 119 lines · 1,203 tokens per session scan A 5969a839c1cb
substack-mcp AGENTS.md is an instructions file published in the GitHub repository damienbenveniste/substack-mcp (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,203 tokens to every session, about $0.0060 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
substack-mcp CLAUDE.md
Instructions for marcomoauro/substack-mcp, covering claude.md, language, commands, distribution and releases and layout.
python-substack GEMINI.md
Instructions for ma2za/python-substack, covering python-substack maintainer instructions, project, development and releases.
wet-mcp AGENTS.md
Instructions for n24q02m/wet-mcp, covering agents.md - wet-mcp, cau truc, lenh thuong dung, mise shortcuts and cau hinh quan trong.
pfsense-mcp-server AGENTS.md
Instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
brandkit-mcp CLAUDE.md
Instructions for ejwhite7/brandkit-mcp, covering claude.md -- brandkit mcp, project overview, key concepts, repository structure and brand atomic system layout.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.