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 migrate-v0-to-v1git 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/migrate-v0-to-v1)<a href="https://agentmods.dev/skills/boykush/scraps/migrate-v0-to-v1"><img src="https://agentmods.dev/badge/skills/boykush/scraps/migrate-v0-to-v1/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/migrate-v0-to-v1"><img src="https://agentmods.dev/badge/skills/boykush/scraps/migrate-v0-to-v1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00105 | $0.02314 |
| Opus 5 | $0.00053 | $0.01157 |
| Sonnet 5 | $0.00021 | $0.00463 |
| Haiku 4.5 | $0.00011 | $0.00231 |
Grade A, and why
migrate-v0-to-v1 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate v0 to v1
Upgrade a Scraps v0 wiki to the v1 source shape with controlled edits and CLI verification.
This is the migration tooling: v1 deliberately does not add a built-in
scraps migrate command. The LLM runs the old and new CLIs, builds an
inventory, edits the wiki, and reports anything that needs human judgment.
Inputs
wiki-root: directory containing the wiki. If omitted, use the current directory.
Do not ask the user for Scraps versions up front. Discover them before editing.
CLI Runner
Resolve CLI versions in this order:
- Refresh or inspect repository tags when the Scraps source repository is
available:
git fetch --tagswhen network is allowedgit tag --list 'v0.*' --sort=-version:refname | head -1git tag --list 'v[1-9]*' --sort=-version:refname | head -1
- If tags are unavailable, inspect the wiki/repo for existing pins in
mise.toml, GitHub Actions, lockfiles, README commands, or setup scripts. - If v0 still cannot be resolved, ask for the old version before making
migration edits. v0
tag list --jsonis required for safe tag conversion. - If the v1-or-newer CLI cannot be resolved from tags, use the moving
v1ref for GitHub Actions and the latest v1-compatible CLI available tomise.
At the time this skill was written, the latest known tags were:
- v0:
v0.33.0 - v1-or-newer:
v1.0.0-rc.2
Prefer dynamically resolving tags over hard-coding these examples.
Use these command forms when mise is available:
mise exec "github:boykush/scraps@$SCRAPS_V0_REF" -- scraps -C "$WIKI_ROOT" tag list --json
mise exec "github:boykush/scraps@$SCRAPS_V1_OR_NEWER_REF" -- scraps -C "$WIKI_ROOT" lint
If no version-pinned execution is available, use the scraps on PATH only after
checking scraps --version and confirming it matches the phase being run.
For v0 commands that predate -C, use the equivalent v0 directory flag if
needed. Prefer running from the wiki root over guessing when a v0 CLI does not
support -C.
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 · 213 lines · 105 tokens per session scan A 1bcfe98610f6
migrate-v0-to-v1 is a skill published in the GitHub repository boykush/scraps (47 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 2,314 once invoked, about $0.0005 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
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.
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
web-scraping
Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into…
qdrant
Manage Qdrant vector database via REST API. Use when the user asks to create or delete collections, upsert or search vectors, inspect points, filter by payload fields, manage snapshots, check cluster status, or debug semantic search issues. Covers collection CRUD, point upsert/search/scroll/count, payload indexes…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
nab
How and WHY to use nab — the preferred URL->markdown microfetch tool for agents. Decision: nab (auth + cookies + anti-bot, 50ms, LLM-shaped markdown) > jina (clean MD fallback) > NEVER WebFetch (50K tokens/call, 25x waste). Prefer the nab MCP tools (fetch, fetchbatch, submit, login, authlookup) when the plugin's nab…