substack-api

A tool for working with Substack, a publishing platform for newsletters and posts, through a logged-in user's account. It uses the account's browser session rather than a public API key.

In plain words
What is it for?
Reading posts, creating drafts, publishing issues, scheduling sends, mirroring content, and extracting data such as subscribers from a Substack publication.
Why use it?
It removes the need to handle Substack tasks manually in a browser or build unsupported integrations from scratch. Account access still requires the user's session cookie and publication subdomain.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/anthonydavidadams/substack-api-reference/substack-api-reference
Any agent
npx skills add AnthonyDavidAdams/substack-api-reference --skill substack-api-reference
Clone the repo
git clone --depth 1 https://github.com/AnthonyDavidAdams/substack-api-reference

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00068 $0.01453
Opus 5 $0.00034 $0.00727
Sonnet 5 $0.00014 $0.00291
Haiku 4.5 $0.00007 $0.00145

Measured yesterday against content hash 6120983d3add, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

substack-api scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [`examples/`](examples/) — drop-in curl + TypeScript code
SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Substack API Skill

You can drive Substack programmatically using their internal cookie-authenticated API. There is no public API key program — auth is the session cookie a normal browser uses.

When to use this skill

Trigger phrases (not exhaustive):

  • "post to Substack" / "send via Substack"
  • "create a draft in [my Substack]"
  • "publish to {publication}.substack.com"
  • "import my Substack subscribers"
  • "read my Substack posts"
  • "schedule a Substack send"

Before you do anything

You need TWO pieces of state from the user:

  1. Session cookieconnect.sid value (or substack.sid on older accounts). See AUTH.md for how to obtain.
  2. Publication subdomain — e.g. yournewsletter (NOT the full URL). Get this from /api/v1/user/profile/self if not supplied.

Always confirm both before making mutating calls. If the user supplied a URL like https://yournewsletter.substack.com, parse out the subdomain.

Canonical request shape

Cookie: connect.sid=<value>; substack.sid=<value>
User-Agent: Mozilla/5.0

Mozilla/5.0 is enough — default Node/Python User-Agents get 403'd.

The five operations you'll actually do

1. Validate a cookie + discover the user's publications

GET https://substack.com/api/v1/user/profile/self

Returns {id, handle, publicationUsers: [{publication: {id, name, subdomain}, role, is_primary}]}.

  • Any 200 = cookie valid
  • 401 = cookie expired or wrong
  • Pick the publication via subdomain — show user a picker if multiple exist

2. Create a draft (no send)

POST https://{subdomain}.substack.com/api/v1/drafts
Content-Type: application/json

{
  "draft_title": "Subject line",
  "draft_subtitle": "Optional preheader",
  "draft_body": "<p>HTML body</p>",
  "type": "newsletter"
}

draft_body accepts HTML. Substack will normalize. Returns the draft object with id and slug.

3. Update an existing draft (Replace flow)

PUT https://{subdomain}.substack.com/api/v1/drafts/{id}
Content-Type: application/json

{ "draft_title": "...", "draft_subtitle": "...", "draft_body": "..." }

Read the full file on GitHub · 178 lines

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. yesterday First seen · 178 lines · 68 tokens per session scan A 6120983d3add

Subscribe to this mod's changes

substack-api is a skill published in the GitHub repository AnthonyDavidAdams/substack-api-reference (5 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,453 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

razbor-servisa

Метод-рефлекс: как превратить ЛЮБОЙ сторонний сервис в CLI-инструмент для агента, когда у сервиса нет удобного «разъёма». Скилл сам определяет ситуацию доступа (есть открытый API / API кривой и неполный / API нет вообще) и ведёт по нужной ветке: собрать по докам API, либо подсмотреть скрытый API прямо в браузере …

Ntmib/razbor-servisa · 322 tokens

horse-websocket

Guidelines and workflows for developing and maintaining WebSocket endpoints and protocol upgrades within the Horse framework.

HashLoad/horse · 23 tokens

horse-streaming

Diretrizes e workflows para desenvolvimento e manutenção de transmissões de dados em tempo real (Web Streams e Server-Sent Events - SSE) no framework Horse.

HashLoad/horse · 35 tokens

higgsfield-shotlist-director

Turns a brief, script, scene breakdown, treatment, or story idea into ONE connected director's shotlist for Seedance 2.0 — a single editable HTML artifact with a global Style Prefix, an @-asset glossary, and named per-scene prompts (1a, 1b, 2a…) each in Style → Characters → Scene → CUT 1..N form. Use whenever the user…

OSideMedia/higgsfield-ai-prompt-skill · 201 tokens

developing-preact

Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON…

oaustegard/claude-skills · 76 tokens

creating-bookmarklets

Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.

oaustegard/claude-skills · 47 tokens