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 commands/pagerduty/claude-code-plugins/create-pagerduty-skillgit clone --depth 1 https://github.com/PagerDuty/claude-code-pluginsWrote 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/commands/pagerduty/claude-code-plugins/create-pagerduty-skill)<a href="https://agentmods.dev/commands/pagerduty/claude-code-plugins/create-pagerduty-skill"><img src="https://agentmods.dev/badge/commands/pagerduty/claude-code-plugins/create-pagerduty-skill.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.04422 |
| Opus 5 | $0.00006 | $0.02211 |
| Sonnet 5 | $0.00002 | $0.00884 |
| Haiku 4.5 | $0.00001 | $0.00442 |
Grade C, and why
create-pagerduty-skill 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 4d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
[show full instructions] Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. Set your PAGERDUTY_API_KEY in the environment (.claude/settings.local.json or ~/.claude/settings.json) How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creating or updating a PagerDuty Skill for AI agents. Your role is to extract the user's domain knowledge and translate it into comprehensive, structured instructions that the agent can follow.
Pre-flight Checks
CRITICAL: Before proceeding, verify PagerDuty Advance MCP is available.
- Use ToolSearch to check for
mcp__pagerduty-advance-mcp-__create_skill_tool - If not found, display error and EXIT (do not proceed):
❌ PagerDuty Advance MCP is not available. This command requires the PagerDuty Advance MCP server to create and manage skills via API. Note: PagerDuty Skills is currently in Early Access (EA). To get access: 1. Request PagerDuty Skills EA access: https://www.pagerduty.com/early-access/ 2. Request PagerDuty Advance MCP/API EA access: https://support.pagerduty.com/main/changelog/pagerduty-advance-mcpapi-support-is-now-in-early-access-for-advance-customers 3. Once approved, configure PagerDuty Advance MCP in .mcp.json 4. Set your PAGERDUTY_API_KEY in the environment (.claude/settings.local.json or ~/.claude/settings.json) 5. Restart Claude Code 6. Re-run /pagerduty:create-pagerduty-skill - Do NOT proceed without MCP access - no silent degradation
API Constraints
Skills are managed via the PagerDuty Advance MCP API with these constraints:
- agent_type: Always
"sre"(only SRE Agent supports skills currently) - scope: REQUIRED -
"account"(shared, team-level) or"user"(personal, individual) - name: kebab-case, max 60 chars, unique per (agent, scope) - same name can exist in both scopes
- description: max 1024 chars
- instructions: max 5000 tokens total (entire skill document)
- limits:
- Account scope: Max 50 skills per agent
- User scope: Max 25 skills per agent
- immutable fields: scope and name cannot be changed after creation (must delete and recreate)
Validation rules:
- Name format:
^[a-z0-9]+(-[a-z0-9]+)*$(kebab-case only) - Token estimation:
chars / 4 ≈ tokens - Warn at 90% of 5000 token limit (4500 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.
- 4d ago First seen · 590 lines · 12 tokens per session scan C bed806e675a6
create-pagerduty-skill is a command published in the GitHub repository PagerDuty/claude-code-plugins (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 4,422 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks the agent to reveal its instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
nimbalyst-coach
Audit this project and your recent sessions, then recommend extensions, features, and agent-instruction changes that would make Nimbalyst work better for you.
investigate
Investigate a problem and align on the right next step before implementing.
playwright
Write or update Playwright E2E tests following project conventions.
social-response
Draft a response to a user reaching out on Discord or another social channel.
new-extension
Create a new Nimbalyst extension project from a starter scaffold.
walkthrough
Create a guided walkthrough for a feature or workflow.