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.
/plugin marketplace add giuseppe-trisciuoglio/developer-kitnpx agentmods add plugins/giuseppe-trisciuoglio/developer-kit/developer-kit-coregit clone --depth 1 https://github.com/giuseppe-trisciuoglio/developer-kitGrade A, and why
developer-kit-core 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": "developer-kit",
"version": "4.0.0",
"description": "Core agents and commands required by all Developer Kit plugins",
"author": {
"name": "Giuseppe Trisciuoglio",
"email": "[email protected]"
},
"homepage": "https://github.com/giuseppe-trisciuoglio/developer-kit",
"repository": "https://github.com/giuseppe-trisciuoglio/developer-kit.git",
"license": "MIT",
"keywords": [
"developer-kit",
"core",
"code-review",
"refactoring",
"debugging",
"architecture",
"documentation"
],
"agents": [
"./agents/general-code-explorer.md",
"./agents/general-code-reviewer.md",
"./agents/general-refactor-expert.md",
"./agents/general-software-architect.md",
"./agents/general-debugger.md",
"./agents/document-generator-expert.md",
"./agents/learn-analyst.md"
],
"commands": [
"./commands/devkit.refactor.md",
"./commands/devkit.feature-development.md",
"./commands/devkit.fix-debugging.md",
"./commands/documentation/devkit.generate-document.md",
"./commands/documentation/devkit.generate-changelog.md",
"./commands/documentation/devkit.generate-security-assessment.md",
"./commands/devkit.github.create-pr.md",
"./commands/devkit.github.review-pr.md",
"./commands/lra/devkit.lra.init.md",
"./commands/lra/devkit.lra.add-feature.md",
"./commands/lra/devkit.lra.checkpoint.md",
"./commands/lra/devkit.lra.mark-feature.md",
"./commands/lra/devkit.lra.recover.md",
"./commands/lra/devkit.lra.start-session.md",
"./commands/lra/devkit.lra.status.md",
"./commands/devkit.verify-skill.md"
],
"skills": [
"./skills/adr-drafting",
"./skills/memory-md-management",
"./skills/docs-updater",
"./skills/drawio-logical-diagrams",
"./skills/github-issue-workflow",
"./skills/learn",
"./skills/bug-fix-brief",
"./skills/pr-review-comments"
]
}
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 First seen · 59 lines scan A 6215df5db2b7
developer-kit-core is a plugin published in the GitHub repository giuseppe-trisciuoglio/developer-kit (337 stars, last pushed 14d 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 2026-08-30.
Other plugins, from other repositories
andyelessar-skills
Plugin marketplace listing 10 plugins: meta-prompts, agents-creator, plugin-creator, prose-guide, dotnet.
skill-guide
Design, write, review, and improve SKILL.md files using proven patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) with intent-based protocols for creating, reviewing, and improving agent skills.
microsoft-agents-sdk
Plugin marketplace listing 4 plugins: agents-sdk-common, agents-for-js, agents-for-net, agents-for-python.
aeon
Aeon's Claude Code plugins - install the operator console for setting up and running an Aeon agent instance.
personal-corp-os
Personal Corp OS: run a one-person company through AI agents with a weekly rhythm, department repos, safe public releases, and open Claude Code and Codex skills.
contentful
Agent skills for Contentful apps, APIs, migrations, and personalization.