substack-mcp: Instructions file for Codex

AGENTS.md

substack-mcp AGENTS.md is an instructions file for Codex, OpenCode from conorbronsdon/substack-mcp. It costs 186 tokens per session, scanned A, original, MIT.

Repository instructions for developing and releasing the Substack MCP project. They describe branch and pull-request practices, CI checks, release scripts, account boundaries, and handling of test credentials.

In plain words
What is it for?
Use them when changing this repository, running its checks, preparing releases, writing tests, or reviewing code that handles Substack accounts and private data.
Why use it?
They prevent development changes, releases, private account data, and credentials from being mixed up or exposed. They also preserve rules around drafts, Notes, tests, and publication selection.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is conorbronsdon/substack-mcp's own configuration. It tells Codex and OpenCode how to work on substack-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything substack-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to conorbronsdon/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.

Copy the file
curl -O https://raw.githubusercontent.com/conorbronsdon/substack-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/substack-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for substack-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/conorbronsdon/substack-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/conorbronsdon/substack-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/conorbronsdon/substack-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/substack-mcp/agents-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.

agentmods 80×15 button for substack-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/conorbronsdon/substack-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/substack-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 This file is loaded in full into every session.
When invoked 186 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00186 $0.00186
Opus 5 $0.00093 $0.00093
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00019 $0.00019

Measured today against content hash 08de932f065e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 today.

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.

AGENTS.md · 17 lines

What it actually says

Agent instructions

Read CLAUDE.md for repository architecture and development commands. Use a focused branch and PR; CI checks the supported Node/OS combinations.

Preserve the draft-only long-form boundary and explicit immediate-publication semantics of Notes. The tool catalog and side-effect classifications are checked by src/__tests__/annotations.test.ts and the output-contract snapshots. Publication selection and private data must not cross accounts; controls live in src/__tests__/resolve-publications.test.ts and output-contracts.test.ts.

Use the release scripts to synchronize versions; npm run check:release and npm run test:release enforce manifest alignment. Never put real credentials, private drafts, subscriber data or local account paths in tests, logs or packages. Credential hygiene requires reviewer inspection as well as automated checks. Use clearly example-*-prefixed synthetic credential fixtures.

Changes

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.

  1. today First seen · 17 lines · 186 tokens per session scan A 08de932f065e

Subscribe to this mod's changes

substack-mcp AGENTS.md is an instructions file published in the GitHub repository conorbronsdon/substack-mcp (29 stars, last pushed today), licensed MIT. It adds 186 tokens to every session, about $0.0009 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 2026-09-09.