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 boykush/scraps --skill querygit clone --depth 1 https://github.com/boykush/scrapsWrote 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/boykush/scraps/query)<a href="https://agentmods.dev/skills/boykush/scraps/query"><img src="https://agentmods.dev/badge/skills/boykush/scraps/query/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/boykush/scraps/query"><img src="https://agentmods.dev/badge/skills/boykush/scraps/query.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 | $0.00061 | $0.01163 |
| Opus 5.5 | $0.00024 | $0.00465 |
| Sonnet 5.5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00116 |
Grade A, and why
query 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query
Answer a question against the wiki and return a citation-rich synthesis.
Implements Karpathy's Query primitive for Scraps: search the wiki, read relevant scraps, and synthesize an answer that references its sources by [[Title]]. Citations make the answer auditable and ready to be filed back as a new scrap if the user chooses.
When to use
- "What do I have on X?" / "What did I write about Y?"
- "Compare X and Y across my notes"
- "Summarize what I know about Z"
- "Find scraps related to W"
Workflow
-
Understand the question
- Identify the core topic and any constraints (time range, ctx folder, tag, etc.)
- If the question is ambiguous, ask one clarifying question before searching
-
Search (broad → narrow)
scraps search "<keyword>" --jsonfor each main keyword- Try multiple phrasings if the first search returns few results
- For tag-driven questions:
scraps tag backlinks "<tag>" --json
-
Select candidates
- From search results, pick the 5–15 most relevant scraps
- Prefer scraps that span the question (different ctx, different tags) over many near-duplicates
-
Read selected scraps
scraps get "<key>" --jsonfor each candidate, passing the hit'skeyback- Use field projection to save context when appropriate, e.g.
--json body,--json headings, or--json code_blocks - If a link result includes
heading, read just that section withscraps get "<key>" --heading "<heading>" --json body - For graph-shaped questions, also use:
scraps links "<key>" --json(outbound)scraps backlinks "<key>" --json(inbound)
-
Synthesize with citations
- Write the answer in plain Markdown
- Cite every claim that comes from a scrap as
[[Title]](or[[Ctx/Title]]when needed) - Do not invent information beyond what the scraps and the user's question support
- Choose the output shape that fits the question:
- prose paragraph for narrative questions
- GFM table for comparisons
- bullet list for enumerations
- mermaid diagram for relationships
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.
- 4d ago Changed 2117800b55d9
- 1mo ago First seen · 83 lines · 61 tokens per session scan A a198695ea375
query is a skill published in the GitHub repository boykush/scraps (45 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,163 once invoked, about $0.0002 per session on Opus 5.5. 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
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
scratch
Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.
obsidian
Obsidian vault management — create notes, backlinks, tags, and Dataview queries via file operations.
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
gmail
Search, read, draft, and send Gmail when the user asks to work with their inbox or email.
google-calendar
Read schedules, check availability, and create or update Google Calendar events when the user asks to work with their calendar.