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 astra-sh/qvr --skill onboard-skillsgit clone --depth 1 https://github.com/astra-sh/qvrWrote 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/astra-sh/qvr/onboard-skills)<a href="https://agentmods.dev/skills/astra-sh/qvr/onboard-skills"><img src="https://agentmods.dev/badge/skills/astra-sh/qvr/onboard-skills/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/astra-sh/qvr/onboard-skills"><img src="https://agentmods.dev/badge/skills/astra-sh/qvr/onboard-skills.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 | $0.00149 | $0.01741 |
| Opus 5 | $0.00075 | $0.00870 |
| Sonnet 5 | $0.00030 | $0.00348 |
| Haiku 4.5 | $0.00015 | $0.00174 |
Grade A, and why
onboard-skills 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard skills with qvr
qvr installs agent skills (SKILL.md bundles) into a project from one or
more Git registries. qvr is agent-agnostic — it installs into whichever agent
target directories you configure (e.g. .claude/skills/, .agents/skills/, …).
A project's skill set lives in two committed files: qvr.toml is the
hand-editable intent (which skills, which default agents), and qvr.lock
(TOML, schema v5) is the resolved proof and the source of truth for what an
agent actually loads — anything that lands in a managed agent directory without a
matching lock entry is hidden on the next sync. Mutating commands write through to
both files. This skill walks discovery → install → reconcile.
When to use this
- The user wants to find a skill, add a registry, or install a skill with
qvr. - A skill was copied into a managed agent directory by hand and "isn't showing up".
- The user wants a skill available in every session (ambient/global), not just one project.
Do not use this for editing/forking a skill (see fork-and-publish-skill),
or for reproducing an existing set on another machine (see reproduce-skill-env).
Prerequisites
-
Confirm the CLI is present and note the version:
qvr --version -
Run from the project root where you want
qvr.toml+qvr.lockto live. The files and the agent-target symlinks are written relative to the current directory.
Workflow
1. Discover what's available
Search already-registered registries (substring match on name/description, with
optional hard filters). At least one of a query, --tag, or --author is
required:
qvr search pdf
qvr search --tag testing --author acme
qvr search review --full # untruncated descriptions
qvr search forms --github # search GitHub for repos tagged agent-skills
List registries and the skills each one indexes:
qvr registry list
qvr registry list anthropics/skills --full
2. Install a skill
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 · 168 lines · 149 tokens per session scan A bdf8c4de4dee
onboard-skills is a skill published in the GitHub repository astra-sh/qvr (23 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 1,741 once invoked, about $0.0007 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
hyperframes-best-practices
Production-grade HyperFrames workflow for turning a raw screencast or talking-head recording into a polished product video. Covers the smart-cut pipeline (transcript + silence + scene detection with word-boundary buffers), surgical audio scrubbing (concat-filter rendering, adeclick, targeted transient mute), the…
figma-connect
Figma-to-code bridge combining Figma MCP server tools with the Code Connect CLI for end-to-end design implementation workflows. Use this skill when implementing UI components from Figma design URLs, publishing Code Connect mappings to Figma Dev Mode, extracting design tokens from Figma variables, setting up Figma Code…
blotato
Blotato social-media publishing and scheduling platform — REST API + MCP server. Publish and schedule posts across X/Twitter, TikTok, Instagram, LinkedIn, YouTube, Facebook, Threads, Pinterest, and more from a single integration. Use this skill whenever the user wants to schedule, publish, queue, or batch-post content…
survey-passing
Find and complete paid expert surveys from expert network platforms (Arbolus, Guidepoint, GLG, AlphaSights, Techsponential) using the user's real professional background. Automates the mechanical form-filling of expert consultations that pay $50-$100+. Use this skill whenever the user mentions surveys, canopy, expert…
frontend-design
Create distinctive, production-grade frontend interfaces with visual verification. Use this skill when the user asks to build web components, pages, landing pages, dashboards, React/Vue/Svelte components, HTML/CSS layouts, or any web UI that needs to look polished. Also activates when styling, beautifying…
skill-builder
Meta-skill for creating new skills from natural language. Trigger phrases: "new skill", "create a skill", "build a skill", "make a skill", "generate a skill", "author a skill", "skill builder".