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/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/dev-utils)<a href="https://agentmods.dev/plugins/richfrem/agent-plugins-skills/dev-utils"><img src="https://agentmods.dev/badge/plugins/richfrem/agent-plugins-skills/dev-utils/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/richfrem/agent-plugins-skills/dev-utils"><img src="https://agentmods.dev/badge/plugins/richfrem/agent-plugins-skills/dev-utils.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-utils 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 4d 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": "dev-utils",
"version": "1.4.0",
"description": "Unified Developer Utilities Suite — 19 skills consolidated from standalone plugins. Covers ADR management, coding conventions, context bundling, Mermaid diagram rendering, GitHub issue logging & friction management, GitHub issue backlog bridge, issue prioritizer & Projects v2 sync, GitHub issue worktree manager, GitHub issue PR lifecycle orchestrator, GitHub issue resolution reviewer, GitHub issue refactor proposer, TODO scanning, HuggingFace download/upload/init, text humanization, link validation, symlink management, agent context hygiene (optimize-context), and red-team context bundling.",
"author": {
"name": "Richard Fremmerlid"
},
"repository": "https://github.com/richfrem/agent-plugins-skills",
"license": "MIT",
"keywords": [
"dev-utils",
"utilities",
"context-bundler",
"github-issue",
"github-issue-backlog",
"github-issue-prioritizer",
"github-issue-worktree",
"github-issue-pr-lifecycle",
"adr-manager",
"link-checker",
"huggingface",
"mermaid",
"coding-conventions",
"humanize",
"symlink-manager",
"optimize-context"
],
"capabilities": [
"context-bundling",
"github-issue-logging",
"github-projects-v2-sync",
"worktree-isolation",
"pr-lifecycle-orchestration",
"adr-auditing",
"link-checking",
"diagram-rendering",
"context-hygiene",
"code-conventions"
]
}
What it installs
The manifest is a name and a version. 19 skills travel with it, and installing the plugin installs all of them — 1,186 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill context-bundler A 26 tokens
- Skill github-issue-agent A 101 tokens
- Skill github-issue-refactor-proposer A 186 tokens
- Skill coding-conventions-agent A 28 tokens
- Skill github-issue-backlog-agent A 69 tokens
- Skill github-issue-pr-lifecycle-agent A 85 tokens
- Skill github-issue-prioritizer A 73 tokens
- Skill github-issue-resolution-reviewer A 135 tokens
- Skill github-issue-worktree-agent A 84 tokens
- Skill hf-download A 45 tokens
- Skill optimize-context A 50 tokens
- Skill adr-management A 26 tokens
- Skill hf-init A 24 tokens
- Skill hf-upload A 49 tokens
- Skill humanize A 26 tokens
- Skill link-checker-agent A 25 tokens
- Skill symlink-manager A 70 tokens
- Skill convert-mermaid A 27 tokens
- Skill todo-check A 57 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.
- 4d ago Changed e936f0ceecca
- 1mo ago Changed · -2 lines 2cf7eb40a46f
- 1mo ago First seen · 43 lines scan A 67190dd0e619
dev-utils is a plugin published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), 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 2026-09-03.
Other plugins, from other repositories
deckhand
Drive a GitHub Projects v2 kanban board end to end. Two skills: plan the backlog (epics, sub-issues, board hygiene), then run tickets through implement, isolated adversarial review, fix-loop, and merge.
vibe-flow
Orchestration skills for Vibe Kanban: plan → ship → link → review → merge with wave-based dispatch, executor routing (T0-T4), and autonomous fix loops.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.