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.
npx agentmods add instructions/pagerduty/claude-code-plugins/claude-mdgit clone --depth 1 https://github.com/PagerDuty/claude-code-pluginsWhat 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.
| Model | Per session | Once 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 |
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/ 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 doesversion: Semantic version stringauthor: 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 purposeargument-hint: Optional syntax hint for argumentsallowed-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.
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 · 168 lines · 1,954 tokens per session scan C 9b060c3b09bb
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.
Other instructions, from other repositories
vibeyard CLAUDE.md
Claude Code instructions for elirantutia/vibeyard, covering claude.md, what this is, build & run, testing and architecture.
coder AGENTS.md
AGENTS.md instructions for coder/coder, covering coder development guidelines, task-specific guidance, workflow, essential commands and repository guardrails.
denova AGENTS.md
Instructions for alfredxw/denova, covering 项目目标, 必须遵守, 项目约定, 代码注意事项 and 前端与交互规范.
spring-plugin AGENTS.md
Instructions for explyt/spring-plugin, covering agents.md — contributor guide, project structure, build, test, run, code style and conventions and commits and pull requests.
coder CLAUDE.md
Claude Code instructions for coder/coder, a project described as: Secure environments for developers and their agents.
ORG2 AGENTS.md
AGENTS.md instructions for org2AI/ORG2, covering agents.md — agent skill routing for orgii, skill routing table, root-cause-first bug fixing, default delivery flow and ui copy conventions.