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 bettyguo/obsidian_mcp --skill prep-for-writinggit clone --depth 1 https://github.com/bettyguo/obsidian_mcpWrote 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/bettyguo/obsidian_mcp/prep-for-writing)<a href="https://agentmods.dev/skills/bettyguo/obsidian_mcp/prep-for-writing"><img src="https://agentmods.dev/badge/skills/bettyguo/obsidian_mcp/prep-for-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/bettyguo/obsidian_mcp/prep-for-writing"><img src="https://agentmods.dev/badge/skills/bettyguo/obsidian_mcp/prep-for-writing.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 | $0.00027 | $0.00648 |
| Opus 5 | $0.00014 | $0.00324 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
prep-for-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 11d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
The user is about to write a long-form piece (essay, blog post, talk, paper) on a topic where their vault already has the raw material. Output is a single scratchpad note with quoted excerpts, source wikilinks, and an outline scaffold.
Procedure
- Capture the topic from the user. If absent, ask.
- Optionally capture: target length ("1500 words"), audience ("PKM-curious devs"), and angle ("personal essay" vs "tutorial"). Defaults: unspecified.
- Call
find_related(seed=topic, top_k=25). - Call
read_notes_batch(paths=[top 10–15 candidates])respecting the 200K-char cap. - From the bodies, extract 1–3 high-signal quotes per source. A quote is high-signal if it makes a specific claim or expresses a striking phrase. Cap each quote at ~3 sentences.
- Propose a writing outline: 3–6 sections, each with a one-sentence claim and 2–4 supporting quotes. The outline structure depends on the user's angle if specified.
- Write the scratchpad to
Writing/<slug>.md(use the topic as a slugified filename). Frontmatter:status: drafting,topic,created,target_lengthif given. Body uses the template in §Output format. - Surface the scratchpad path and a one-paragraph top-line. Suggest the user open it in Obsidian; remind them to flip
statustopublished(or delete the scratchpad) when done.
Output format
# Scratchpad: {topic}
> Target: {length / angle / audience} (or "unspecified")
> Generated: {YYYY-MM-DD}
## Outline
### 1. {Section claim}
- Quote from [[Source A]]:
> {quoted text}
- Quote from [[Source B]]:
> {quoted text}
### 2. {Section claim}
- ...
## Bibliography
- [[Source A]] — {one-line summary}
- [[Source B]] — {one-line summary}
- ...
## Draft
(empty — the user writes here)
Anti-patterns
- Don't write the draft. Stop at the outline. The user writes the draft.
- Don't paraphrase quotes. Use the user's actual words. Misattribution to oneself is a small disaster.
- Don't include more than ~15 sources. If the user's vault has 40+ relevant notes, pick the most central via
find_hubsconstrained to the topic — and tell the user you down-selected. - Don't auto-publish or auto-commit anywhere. The scratchpad is private until the user moves it.
- Don't run this skill against
.canvasor.basefiles; they're not body text.
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.
- 11d ago First seen · 60 lines · 27 tokens per session scan A 25b12f86e236
prep-for-writing is a skill published in the GitHub repository bettyguo/obsidian_mcp (8 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 648 once invoked, about $0.0001 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…