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/hg-pyun/claude-code-marketplaceWrote 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/hg-pyun/claude-code-marketplace/dev-tools)<a href="https://agentmods.dev/plugins/hg-pyun/claude-code-marketplace/dev-tools"><img src="https://agentmods.dev/badge/plugins/hg-pyun/claude-code-marketplace/dev-tools/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/hg-pyun/claude-code-marketplace/dev-tools"><img src="https://agentmods.dev/badge/plugins/hg-pyun/claude-code-marketplace/dev-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-tools 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 2mo 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-tools",
"description": "Multi-agent dev toolkit: orchestration, code review, git/GitHub workflows, and debugging",
"version": "2026.07.05.2",
"author": {
"name": "hg-pyun"
},
"settings": {
"language": "Korean"
}
}
What it installs
The manifest is a name and a version. 11 skills, 1 command, 15 agents travel with it, and installing the plugin installs all of them — 2,859 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ralph A 100 tokens
- Skill team A 138 tokens
- Skill interview A 253 tokens
- Skill code-review A 104 tokens
- Skill curl-debug A 195 tokens
- Skill github-pr A 208 tokens
- Skill autopilot A 104 tokens
- Skill doctor-korean-document A 229 tokens
- Skill git-commit A 183 tokens
- Skill install-statusline B 220 tokens
- Skill ralplan C 145 tokens
- Command git-rebase-stack A 151 tokens
- Agent doc-writer A 30 tokens
- Agent verifier A 61 tokens
- Agent analyst A 45 tokens
- Agent architect A 66 tokens
- Agent debugger A 58 tokens
- Agent git-master A 91 tokens
- Agent performance-analyst A 36 tokens
- Agent planner A 54 tokens
- Agent reviewer A 46 tokens
- Agent security-auditor A 31 tokens
- Agent test-engineer A 71 tokens
- Agent tracer A 72 tokens
- Agent explorer A 41 tokens
- Agent code-simplifier C 53 tokens
- Agent executor C 74 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.
- 2mo ago First seen · 12 lines scan A d25d6f64cffd
dev-tools is a plugin published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 4mo 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 2026-08-31.
Other plugins, from other repositories
git-pr
Committing, PR creation and review triage, and dependency upgrades.
workflow
Code review and worktree workflow commands.
git
Git workflow tools: commits, PRs, review inbox, checkout, and work triage.
diffctx
Selects the minimum code an LLM needs to review a git diff.
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.
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting via gh api.