claude-code-plugins CLAUDE.md

Repository instructions for a Claude Code plugin marketplace that contains PagerDuty integrations. PagerDuty is a service for tracking and responding to software incidents.

In plain words
What is it for?
Working on the marketplace metadata, plugin commands, PagerDuty connection, and related skill-management code.
Why use it?
They give the coding agent the repository layout, plugin rules, and registration steps, so it can make changes in the expected places.

Instructions file

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.

agentmods
npx agentmods add instructions/pagerduty/claude-code-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/PagerDuty/claude-code-plugins
Per session 1,954 This file is loaded in full into every session.
When invoked 1,954 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01954 $0.01954
Opus 5 $0.00977 $0.00977
Sonnet 5 $0.00391 $0.00391
Haiku 4.5 $0.00195 $0.00195

Measured 2d ago against content hash 9b060c3b09bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-code-plugins CLAUDE.md scanned grade C with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`.mcp.json` declares external MCP servers the plugins depend on. The PagerDuty server is an HTTP MCP server that requires `PAGERDUTY_API_KEY` to be set in the environment (via `.claude/settings.local.json` or `~/.claude/

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

`.mcp.json` declares external MCP servers the plugins depend on. The PagerDuty server is an HTTP MCP server that requires `PAGERDUTY_API_KEY` to be set in the environment (via `.claude/settings.local.json` or `~/.claude/
CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

This is a Claude Code plugin marketplace for PagerDuty integrations. It contains plugins that bring operational intelligence into development workflows by correlating code changes with PagerDuty incident data.

Current plugins:

  • pagerduty: Includes multiple commands:
    • Pre-commit risk scoring using PagerDuty incident history and git diff analysis
    • PagerDuty skill creation and management for AI agents (Early Access)

Repository Structure

.claude-plugin/           # Marketplace and plugin metadata
  marketplace.json        # Marketplace registry definition
  plugin.json            # Plugin metadata (name, version, author)
commands/                # Plugin slash commands
  pre-commit-risk-scoring.md   # Risk assessment command
  create-pagerduty-skill.md    # Skill creation/management command
.mcp.json               # PagerDuty MCP server configuration

Plugin Architecture

Marketplace Registration

The marketplace is defined in .claude-plugin/marketplace.json with owner metadata and a list of plugins. Each plugin entry must specify:

  • name: Plugin identifier (e.g., "pagerduty")
  • source: Path to plugin definition (typically "./")
  • description: What the plugin does
  • version: Semantic version string
  • author: Attribution metadata

Plugin Metadata

Each plugin has a plugin.json at its source path containing name, description, version, and author. The version in plugin.json must match the version in marketplace.json.

Command Definitions

Commands are markdown files in the commands/ directory with frontmatter:

  • description: Human-readable command purpose
  • argument-hint: Optional syntax hint for arguments
  • allowed-tools: Whitelist of tools the command can invoke

The markdown body contains the full command prompt that gets executed when the slash command is invoked.

Read the full file on GitHub · 168 lines

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. 2d ago First seen · 168 lines · 1,954 tokens per session scan C 9b060c3b09bb

Subscribe to this mod's changes

claude-code-plugins CLAUDE.md is an instructions file published in the GitHub repository PagerDuty/claude-code-plugins (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,954 tokens to every session, about $0.0098 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.