writing-substack

writing-substack is a skill for Claude Code, Codex from mshadmanrahman/pm-pilot. It costs 43 tokens per session (457 once invoked), scanned A, original, MIT.

A writing guide for creating Substack Notes, which are short posts published on the Substack platform, within a 500-character limit.

In plain words
What is it for?
Use it to draft Substack Notes, suggest hashtags, count characters, and provide alternate opening lines.
Why use it?
It keeps the writing within the platform's length constraint and structures it around a hook, brief body, and invitation to respond.

Skill for Claude CodeCodex

Part of the pm-content plugin — 3 skills shipped together

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/mshadmanrahman/pm-pilot/writing-substack
Any agent
npx skills add mshadmanrahman/pm-pilot --skill writing-substack
Clone the repo
git clone --depth 1 https://github.com/mshadmanrahman/pm-pilot

Made for: Claude Code, Codex.

Or install pm-content, the plugin that ships this one along with the rest of its 3 skills.

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 writing-substack

README.md
[![agentmods](https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/writing-substack.svg)](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/writing-substack)
Your own site
<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/writing-substack"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/writing-substack.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00043 $0.00457
Opus 5 $0.00022 $0.00229
Sonnet 5 $0.00009 $0.00091
Haiku 4.5 $0.00004 $0.00046

Measured 4d ago against content hash dc9323a06d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-substack 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 4d 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.

plugins/pm-content/skills/writing-substack/SKILL.md · 70 lines

What it actually says

Writing Substack Notes

Create Substack Notes: short, punchy, engagement-optimized.

Trigger

"write a Substack Note", "Substack content", "Note ideas"

Format Constraints

  • Total length: Under 500 characters (Substack Notes limit).
  • Hook: First line grabs attention. Bold claim, surprising stat, or provocative question.
  • Body: 2-5 short paragraphs. One idea per paragraph. Conversational tone.
  • CTA: End with engagement driver (question, invitation, teaser).
  • Hashtags: 2-4 relevant hashtags suggested separately.

Process

  1. Confirm topic and angle with user.
  2. Load voice profile if configured (see writing-style skill).
  3. Draft Note within 500 char limit.
  4. Suggest 2-4 hashtags.
  5. Offer 1-2 alternate hooks if user wants options.

Output Format

{Hook line}

{Body paragraph 1}

{Body paragraph 2}

{CTA}

---
Suggested hashtags: #tag1 #tag2 #tag3
Character count: {n}/500

Examples

Topic: Product management lessons

Most PRDs are fiction.

They describe a world where scope never creeps, timelines hold, and stakeholders agree on day one.

The best PMs I know write living docs. Updated weekly. Contradictions included.

What does your PRD process actually look like?

---
Suggested hashtags: #ProductManagement #PRD #BuildingProducts
Character count: 312/500

Rules

  • Count characters accurately. Hard limit 500.
  • Conversational, not corporate. Write like talking to a smart friend.
  • One idea per Note. If there are multiple ideas, suggest a thread.
  • No clickbait. The hook should deliver on its promise.
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. 4d ago First seen · 70 lines · 43 tokens per session scan A dc9323a06d4a

Subscribe to this mod's changes

writing-substack is a skill published in the GitHub repository mshadmanrahman/pm-pilot (19 stars, last pushed 14d ago), licensed MIT. It adds 43 tokens to every session and 457 once invoked, about $0.0002 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 2026-08-30.