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.
git clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/plugins/jschulte/claude-plugins/pr-workflow)<a href="https://agentmods.dev/plugins/jschulte/claude-plugins/pr-workflow"><img src="https://agentmods.dev/badge/plugins/jschulte/claude-plugins/pr-workflow/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/plugins/jschulte/claude-plugins/pr-workflow"><img src="https://agentmods.dev/badge/plugins/jschulte/claude-plugins/pr-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pr-workflow 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 24d 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.
What it actually says
{
"name": "pr-workflow",
"version": "1.1.2",
"description": "5 skills for the life of a pull request: deliver-me (one change end to end, unsupervised), productionize (draft PR to reviewable PR), pr-resolver (resolve review feedback), bulletproof (a release verdict before merging) and issue-burndown (a backlog of issues into batched PRs).",
"author": { "name": "Jonah Schulte" },
"repository": "https://github.com/jschulte/claude-plugins",
"license": "MIT",
"keywords": ["pull-request", "code-review", "github", "release", "issues", "backlog", "git-worktree", "autonomous"]
}
What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 333 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 24d ago First seen · 10 lines scan A e58e1bbaf137
pr-workflow is a plugin published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-12.
Other plugins, from other repositories
delivery-suite
Publish the intended changes and verify what reached the remote repository or target environment.
oss
Open-source maintenance: analyse, review, resolve, release-readiness, and setup skills with four specialist agents.
gh-workflow
Generic GitHub workflow commands for issue management, PR creation, code review, and releases. Works with any repository by auto-detecting settings.
edloidas
Skills for planning, building, code review, auditing, maintenance, shipping, assistance, writing, Obsidian, and end-to-end workflows.
pr-shepherd
Shepherd one or an ordered sequence of open PRs all the way to merge. Drains every review thread to a fixpoint (reply inline, then resolve), waits out CI on a hardened observe-only poll loop, runs the test plan, then auto-merges on a fully green gate. For a sequence, rebases each later PR onto the freshly-merged main…
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.