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 skills add hssh8917/cc-skills --skill substack-ghostwritinggit clone --depth 1 https://github.com/hssh8917/cc-skillsWrote 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/skills/hssh8917/cc-skills/substack-ghostwriting)<a href="https://agentmods.dev/skills/hssh8917/cc-skills/substack-ghostwriting"><img src="https://agentmods.dev/badge/skills/hssh8917/cc-skills/substack-ghostwriting/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/skills/hssh8917/cc-skills/substack-ghostwriting"><img src="https://agentmods.dev/badge/skills/hssh8917/cc-skills/substack-ghostwriting.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 | $0.00207 | $0.03465 |
| Opus 5.5 | $0.00083 | $0.01386 |
| Sonnet 5.5 | $0.00041 | $0.00693 |
| Haiku 4.5 | $0.00021 | $0.00347 |
Grade A, and why
substack-ghostwriting 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 1mo 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.
This is a copy
97% identical to substack-ghostwriting — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Substack Ghostwriting & Content Optimization
A skill for writing Substack content — both newsletter issues (email-first) and web posts (web-first articles/essays) — that grows subscribers and converts readers. Handles two voice modes (own voice, ghostwriting) and two format modes (newsletter issue, web post).
Core philosophy
Substack is not a blog with an email list. It's a social-media-newsletter hybrid with an algorithm that optimizes for subscriptions, not engagement. This changes everything about how you write, format, and distribute content on the platform.
The algorithm's incentives genuinely align with quality. Substack's revenue comes from subscription cuts (not ads), so gaming engagement metrics doesn't help. What helps: writing content good enough that readers convert to paid subscribers and recommend you to others.
For ghostwriting specifically: the job is capturing someone's existing insights in their voice, not generating insights from scratch. As Nicolas Cole frames it: clients are "insights-rich and time-poor", writers are "time-rich but insights-poor." The art is extraction and voice matching.
Platform formatting constraints
Substack is a social-media-newsletter hybrid with an algorithm that optimizes for subscriptions, not engagement. Revenue comes from subscription cuts (not ads), so quality genuinely wins. For ghostwriting: the job is capturing someone's existing insights in their voice — clients are "insights-rich and time-poor."
Read references/platform-constraints.md for post fields, Notes limits, special content blocks, and media embeds.
Mode detection
Determine two dimensions:
Voice dimension:
- Own voice — the user writes/publishes under their own name. Go directly to the Writing Workflow.
- Ghostwriting — writing in someone else's voice, or preparing content for a client. Complete the Ghostwriting Workflow first, then the Writing Workflow.
Format dimension:
- Newsletter issue (email-first) — sent to subscribers' inboxes. Subject line and email formatting matter most. Read
references/email-formatting.mdduring Phase 3. - Web post (web-first) — published as a Substack article/essay, discoverable via search and Substack's feed. SEO and web formatting matter most. Read
references/web-post-formatting.mdduring Phase 3.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 244 lines · 207 tokens per session scan A af9f34bf2f45
substack-ghostwriting is a skill published in the GitHub repository hssh8917/cc-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 207 tokens to every session and 3,465 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to substack-ghostwriting, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.