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 skoowoo/vaultr-notes --skill vaultr-quote-extractgit clone --depth 1 https://github.com/skoowoo/vaultr-notesWrote 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/skoowoo/vaultr-notes/vaultr-quote-extract)<a href="https://agentmods.dev/skills/skoowoo/vaultr-notes/vaultr-quote-extract"><img src="https://agentmods.dev/badge/skills/skoowoo/vaultr-notes/vaultr-quote-extract/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/skoowoo/vaultr-notes/vaultr-quote-extract"><img src="https://agentmods.dev/badge/skills/skoowoo/vaultr-notes/vaultr-quote-extract.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 | $0.00110 | $0.00958 |
| Opus 5 | $0.00055 | $0.00479 |
| Sonnet 5 | $0.00022 | $0.00192 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
vaultr-quote-extract 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vaultr Quote Extractor
Extract high-value verbatim passages from a Vaultr note and save each one as a short note with a backlink to the source.
What counts as a good quote
Think of it like a pull quote in a magazine: not just the punchline, but enough setup that the insight lands on its own. A single sentence that contains the conclusion but relies on prior paragraphs for meaning is not a good quote — include the setup.
A quote worth saving:
- Tells a complete mini-story: claim + reasoning, or observation + implication, or setup + payoff. If you need to re-read the source to understand why it matters, the quote is too short.
- Is verbatim — exact words from the source, never paraphrased or summarized. Splice adjacent sentences or paragraphs together if they form a coherent unit; trim only scaffolding words between them.
- Has enough context to be vivid and specific when encountered cold, weeks later.
- Is dense with meaning — surprising, counterintuitive, or crystallizing something the reader half-knew but couldn't articulate.
Typical length: 2–5 sentences, or one full paragraph. A single memorable sentence is fine only when it is fully self-explanatory. A quote can span multiple consecutive paragraphs if they build a single argument.
Skip generic transitions, introductions, obvious statements, and boilerplate. Quality over quantity — 3–8 quotes per note is typical.
Step-by-step
1. Identify the source
The user will name the note as either a vault-absolute path (/clips/article.md) or a bare name (article.md or article). Use whichever form they provided.
2. Read the note
vaultr raw_note read <path-or-name>
If this fails, surface the error directly — don't proceed.
3. Extract the stem and display text
The backlink needs a stem (the filename without .md) and a display label.
Derive the stem:
# e.g. /clips/网络效应.md → 网络效应
basename "<path>" .md
For the display label, use (in priority order):
- The
title:value from YAML frontmatter, if present - The first H1 heading (
# ...), if present - The stem itself
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.
- 10d ago First seen · 87 lines · 110 tokens per session scan A 04d562271156
vaultr-quote-extract is a skill published in the GitHub repository skoowoo/vaultr-notes (90 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 958 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
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
workflows
A workflow guide for tasks that need several kinds of reasoning in sequence, such as research, finding the main conflict, choosing a small starting point, and planning sustained work.