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/dryvist/claude-code-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/dryvist/claude-code-plugins/github-workflows)<a href="https://agentmods.dev/plugins/dryvist/claude-code-plugins/github-workflows"><img src="https://agentmods.dev/badge/plugins/dryvist/claude-code-plugins/github-workflows/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/dryvist/claude-code-plugins/github-workflows"><img src="https://agentmods.dev/badge/plugins/dryvist/claude-code-plugins/github-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
github-workflows 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 2d 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": "github-workflows",
"version": "6.8.0",
"description": "PR finalization (single, repo-wide, or org-wide including bots), repo refresh, rebase-merge, merge, review thread resolution, issue shaping, issue sweeping that reconciles open issues against reality, and diagnosing silent GitHub Actions failures",
"author": {
"name": "JacobPEvans"
},
"license": "Apache-2.0",
"repository": "https://github.com/JacobPEvans/claude-code-plugins",
"keywords": [
"github",
"pull-request",
"issues",
"pr-management",
"rebase",
"stacked-prs",
"refresh",
"shape-up",
"workflow"
],
"skills": [
"./skills/finalize-pr",
"./skills/ship",
"./skills/merge-pr",
"./skills/rebase-pr",
"./skills/pr-stacks",
"./skills/promote-release",
"./skills/refresh-repo",
"./skills/prune-branches",
"./skills/gh-cli-patterns",
"./skills/shape-issues",
"./skills/issue-sweep",
"./skills/resolve-pr-threads",
"./skills/trigger-ai-reviews",
"./skills/shared-workflow-org-refs",
"./skills/pr-sweep",
"./skills/github-code-search",
"./skills/github-actions-silent-failures",
"./skills/pr-standards"
]
}
What it installs
The manifest is a name and a version. 18 skills travel with it, and installing the plugin installs all of them — 1,049 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill finalize-pr A 63 tokens
- Skill gh-cli-patterns A 102 tokens
- Skill merge-pr A 71 tokens
- Skill rebase-pr A 52 tokens
- Skill resolve-pr-threads A 73 tokens
- Skill ship A 30 tokens
- Skill github-actions-silent-failures A 65 tokens
- Skill issue-sweep A 57 tokens
- Skill pr-standards A 23 tokens
- Skill pr-sweep A 57 tokens
- Skill refresh-repo A 64 tokens
- Skill promote-release A 71 tokens
- Skill prune-branches A 48 tokens
- Skill github-code-search A 60 tokens
- Skill pr-stacks A 79 tokens
- Skill trigger-ai-reviews A 65 tokens
- Skill shape-issues A 16 tokens
- Skill shared-workflow-org-refs A 53 tokens
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.
- 2d ago Changed c8d79864000b
- 3d ago Changed 36a347ce2946
- 6d ago Changed c0d70a47dd2c
- 7d ago Changed 8e18b30a5cee
- 11d ago Changed 4b0b5a28937b
- 12d ago Changed cd3b551243ed
- 17d ago Changed 05a61cd92621
- 20d ago Changed 38b3a3ccc3cb
- 23d ago Changed · +1 lines febd0aad3975
- 1mo ago First seen · 41 lines scan A a5155fd90b2d
github-workflows is a plugin published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. 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 2026-08-31.
Other plugins, from other repositories
hydra
Git Worktree management for parallel agent execution - isolated working directories without Git conflicts.
devops-pipeline
CI/CD automation — git worktrees, deploy pipeline, canary monitoring, auto-format/test hooks, and GitHub Actions templates.
forgedock
Autonomous AI development pipeline that uses GitHub as a structured knowledge graph for Claude Code agents. Adds /work-on, /review-pr, /quality-gate, /orchestrate, and 20+ pipeline commands.
harness-kit
Claude Code harness for product + engineering delivery. From idea to merged PR, one pipeline. Run /harness-kit:install to set it up in your project.
ship
Complete PR workflow from commit to production with validation.
gate-router
Map changed Git files to local verification commands.