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 fork-and-publish-skillgit 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/fork-and-publish-skill)<a href="https://agentmods.dev/skills/astra-sh/qvr/fork-and-publish-skill"><img src="https://agentmods.dev/badge/skills/astra-sh/qvr/fork-and-publish-skill/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/fork-and-publish-skill"><img src="https://agentmods.dev/badge/skills/astra-sh/qvr/fork-and-publish-skill.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 | $0.00139 | $0.01561 |
| Opus 5 | $0.00069 | $0.00781 |
| Sonnet 5 | $0.00028 | $0.00312 |
| Haiku 4.5 | $0.00014 | $0.00156 |
Grade A, and why
fork-and-publish-skill 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 11d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fork and publish a skill with qvr
qvr lets you take an installed skill, eject it into your project to edit directly, then publish the result — either back to its origin or to a brand new fork you own — cutting tagged releases as you go. After each publish the lock entry flips back to consume mode, so you can iterate: edit → publish v0.2.0 → edit → publish v0.3.0. This skill drives that loop.
When to use this
- The user wants to tweak a skill's content and keep the change.
- They want to publish a skill back upstream, or fork it to a repo they control.
- They want to cut tagged releases and iterate version by version.
For installing/discovering skills use onboard-skills; for verifying provenance
of what you publish use verify-skill-supply-chain.
Prerequisites
- The skill must be installed in a project (not only
--global). Editing a global skill in place would mutate a copy every project shares, so it's not supported. To change a global skill:qvr add <skill>into a project, edit and publish there, then re-add the published version with--global. - A clean-ish working state helps;
publishrefuses a dirty eject dir unless you pass--auto-commit.
Workflow
1. Eject the skill for editing
qvr edit promotes the symlinked skill into a real directory under the canonical
agent target (the alphabetical-first installed target — e.g. .claude/skills/<name>/
or .cursor/rules/<name>/, depending on what you installed into); any other
installed target dirs become relative symlinks to it. The lock entry gains
mode = 'edit'.
qvr edit my-skill
qvr edit my-skill --author "Jane Dev" --email [email protected] # initial-commit identity
It's idempotent — running it again after the first eject is a no-op.
2. Make and review changes
Edit the files in the ejected skill directory (the canonical agent target), then review:
qvr diff my-skill # git diff in the skill worktree
qvr diff my-skill --stat
qvr status my-skill # dirty state + git ahead/behind
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.
- 11d ago First seen · 152 lines · 139 tokens per session scan A 1cbd3e489df1
fork-and-publish-skill is a skill published in the GitHub repository astra-sh/qvr (23 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 1,561 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
skillshare-changelog
Generate CHANGELOG.md entry from recent commits in conventional format. Also syncs the website changelog page. Use this skill whenever the user asks to: generate a changelog, document what changed between tags, or create a new CHANGELOG entry. If you see requests like "write the changelog for v0.17", "what changed…
skillshare-release
End-to-end release workflow for skillshare. Runs tests, generates changelog (via /changelog), optionally writes local RELEASENOTES, updates version numbers, commits, and drafts announcements. Use when the user says "release", "prepare release", "cut a release", "release v0.19", or any request to publish a new version.…
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
share-a-library
Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.
release
Prepare and publish Perigon.CLI patch releases, including versioning, release notes, bilingual docs, validation, and the nuget-branch CI handoff.
upload
Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.