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 whawkinsiv/solo-founder-skills --skill prose-writinggit clone --depth 1 https://github.com/whawkinsiv/solo-founder-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/whawkinsiv/solo-founder-skills/prose-writing)<a href="https://agentmods.dev/skills/whawkinsiv/solo-founder-skills/prose-writing"><img src="https://agentmods.dev/badge/skills/whawkinsiv/solo-founder-skills/prose-writing/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/whawkinsiv/solo-founder-skills/prose-writing"><img src="https://agentmods.dev/badge/skills/whawkinsiv/solo-founder-skills/prose-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.03556 |
| Opus 5 | $0.00062 | $0.01778 |
| Sonnet 5 | $0.00025 | $0.00711 |
| Haiku 4.5 | $0.00012 | $0.00356 |
Grade A, and why
prose-writing 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 12d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prose Writing
Founders write a lot of prose: blog posts, essays, build-in-public updates, About pages, newsletter intros. Hand the task to AI and you get slop — hedged, generic, three-item-list cadence, throat-clearing openings, "this highlights" tails. This skill is the proactive composition workflow: voice first, structure second, drafting third, edit last.
If
ABOUT-ME.mdexists in the project root, read it before writing — it carries the founder's voice. IfMY-ICP.mdexists, read it for who the prose is talking to. The founder's voice delivers the customer's frame.
Three principles of prose that doesn't sound like AI
- Lead with a specific moment, claim, or number — not a category. "I shipped a feature on Tuesday and lost two customers by Friday" beats "Building products comes with tradeoffs."
- Trust the reader. State what you mean. Don't gesture at significance ("This highlights an important point about…"). The reader can see the point if you make it.
- Structure invisibly. Every paragraph earns its place by moving the argument or story forward. If a paragraph could be deleted with no loss, delete it.
Workflow
- [ ] Read ABOUT-ME.md and MY-ICP.md if they exist
- [ ] Build a voice card (once, reusable)
- [ ] Pick the format and state the one takeaway
- [ ] Write the opening line first
- [ ] Outline as 3–5 plain-English beats
- [ ] Draft fast, in voice. Don't edit while drafting.
- [ ] Edit pass: throat-clearing, "this highlights," ending
- [ ] Run humanize if it still sounds AI
Voice discovery (do once, reuse forever)
Before writing in your voice, you need to know what your voice is. This is a 15-minute exercise.
- Find 3 pieces of prose you wish you'd written. Blog posts, essays, threads. Not "good writing" in the abstract — writing that sounds like you on your best day.
- For each piece, note:
- Sentence length pattern. Mostly short? Mixed? Long sentences with short punches?
- Vocabulary register. Plain ("we shipped this thing")? Mid ("we released the feature")? High ("we deployed the capability")?
- Opinion stance. Stated directly? Hedged? Self-aware about uncertainty?
- Self in the prose. First person constantly? Occasionally? Never?
- Humor. Dry? Earnest? None?
- Distill into a 5-line voice card you paste into every prompt:
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.
- 12d ago First seen · 293 lines · 123 tokens per session scan A c3364a51d0d1
prose-writing is a skill published in the GitHub repository whawkinsiv/solo-founder-skills (243 stars, last pushed 16d ago), licensed MIT. It adds 123 tokens to every session and 3,556 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…