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-writinggit 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-writing)<a href="https://agentmods.dev/skills/skoowoo/vaultr-notes/vaultr-writing"><img src="https://agentmods.dev/badge/skills/skoowoo/vaultr-notes/vaultr-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/skoowoo/vaultr-notes/vaultr-writing"><img src="https://agentmods.dev/badge/skills/skoowoo/vaultr-notes/vaultr-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 | $0.00074 | $0.01526 |
| Opus 5 | $0.00037 | $0.00763 |
| Sonnet 5 | $0.00015 | $0.00305 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
vaultr-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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 0 — Topic alignment
Ask the user for three things (can be in one message):
- What — the topic or question the article addresses
- Who — the intended reader (their background, what they already know)
- Stance — the position or argument the article will take
If the user didn't say where to save the article, ask now. Remember the path.
Once you have those three, scan the knowledge base:
vaultr knowledge --help
vaultr knowledge list-indexes
Select 1–3 domain indexes most relevant to the topic. Read those index files to find matching units. If no indexes exist, scan _knowledge/ directly.
Present the palette for confirmation. Do not proceed to Phase 1 until the user signs off. Format it like this:
Sources found
| # | Knowledge unit | What it contributes |
|---|---|---|
| 1 | unit-name |
one sentence on what this unit brings to the article |
| 2 | … | … |
Possible gaps: list anything you think the article needs that the knowledge base doesn't cover (if any).
That's everything I found. Does this palette cover what you need, or should we add more? If something's missing, compile the relevant notes with
vaultr-compile-notefirst and I'll re-scan.
Wait for the user to confirm, remove units, or tell you what's missing before moving on. If the user wants to add coverage: suggest they run vaultr-compile-note on the relevant source, then re-scan and re-present the updated palette. Do not continue to Phase 1 with a palette the user hasn't confirmed.
Phase 1 — Starting beats
Write 2–3 candidate starting beats, each drawn from different units in the confirmed palette. Each beat is a different entry point into the article — a different angle on the same topic.
Show the beats before writing anything to the article file. For each, name which knowledge unit(s) it draws from, and preview where it might lead next.
What ships with it
1 file 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.
- 9d ago First seen · 133 lines · 74 tokens per session scan A 0b2146570558
vaultr-writing is a skill published in the GitHub repository skoowoo/vaultr-notes (90 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,526 once invoked, about $0.0004 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.