claudeconf

claudeconf is a plugin for Claude Code from nikolaypaskov/claudeconf-plugin. Its manifest loads nothing; the 1 skill, 1 agent it bundles cost 176 tokens per session together, scanned A, original, MIT.

A Claude Code plugin that generates a development and security setup around a project. It uses standard tools for checks such as git hooks, continuous integration, end-to-end tests, and dependency admission.

In plain words
What is it for?
It is for generating pipelines, repository checks, security controls, supply-chain checks, and a diagnostic agent for Claude Code projects.
Why use it?
It provides a repeatable set of quality and security checks instead of leaving each project to assemble them manually. It also includes a read-only tool for inspecting the setup.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add nikolaypaskov/claudeconf-plugin
agentmods
npx agentmods add plugins/nikolaypaskov/claudeconf-plugin/claudeconf
Clone the repo
git clone --depth 1 https://github.com/nikolaypaskov/claudeconf-plugin

Made for: Claude Code.

Wrote 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.

agentmods badge for claudeconf

README.md
[![agentmods](https://agentmods.dev/badge/plugins/nikolaypaskov/claudeconf-plugin/claudeconf.svg)](https://agentmods.dev/plugins/nikolaypaskov/claudeconf-plugin/claudeconf)
Your own site
<a href="https://agentmods.dev/plugins/nikolaypaskov/claudeconf-plugin/claudeconf"><img src="https://agentmods.dev/badge/plugins/nikolaypaskov/claudeconf-plugin/claudeconf.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 agent cost 176 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claudeconf 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 3d 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.

plugins/claudeconf/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "claudeconf",
  "version": "0.5.0",
  "description": "Research-driven, technology-agnostic harness generator for Claude Code: pinned, standard-tool quality + security pipelines (git hooks, CI, e2e, gates, supply-chain admission, agent-hardening) plus a read-only harness-doctor agent.",
  "author": {
    "name": "Nikolay Paskov",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/nikolaypaskov/claudeconf-plugin",
  "repository": "https://github.com/nikolaypaskov/claudeconf-plugin",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "skill",
    "harness",
    "ci",
    "code-quality",
    "security",
    "lefthook",
    "github-actions"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 agent travel with it, and installing the plugin installs all of them — 176 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 3d ago First seen · 23 lines scan A a30208151306

Subscribe to this mod's changes

claudeconf is a plugin published in the GitHub repository nikolaypaskov/claudeconf-plugin (3 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 2026-08-31.

Related

Other plugins, from other repositories

bellwether

Drive PRs to merge-ready: watch CI, fix failures, resolve review comments. Self-contained watch loop that keeps going until pr.ready=true.

roderik/bellwether · not measured

procoder

A harness that gives AI coders the tools and skills to work like a senior developer. All nine domains shipped: security, best practices, maintainability, performance, documentation, clean code, CI/CD, DevOps, GitOps — plus the code index. Hooks hand the agent results; the agent stays in control.

azrtydxb/procoder · not measured

argot

A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.

get-tmonier/argot · not measured

compose-doctor

Deterministic 0-100 health score and agent fix-loop for Android Jetpack Compose, wrapping detekt + compose-rules. Bundles the compose-doctor skill and the /compose-doctor command.

rotemmiz/compose-doctor · not measured

costguard

Find and quantify cloud and CI spend waste from your coding agent. Costguard runs read-only billing checks (GitHub Actions, Supabase, Railway, Netlify, Neon), static CI/cron waste rules, dry-run-first auto-fixes for workflow files, and a monthly cost digest — all driven from your session via /costguard-audit…

mbanderas/costguard · not measured

github-actions-setup

Sets up automated CI/CD with GitHub Actions in one pass — test workflow on push/PR, plus deploy to AWS, Vercel, or a generic SSH server.

khemratechconsulting/github-actions-setup · not measured