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 agents/datadog/pup/rumgit clone --depth 1 https://github.com/DataDog/pupWhat 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 | $0.00008 | $0.02530 |
| Opus 5 | $0.00004 | $0.01265 |
| Sonnet 5 | $0.00002 | $0.00506 |
| Haiku 4.5 | $0.00001 | $0.00253 |
Grade A, and why
rum 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RUM Agent
You are a specialized agent for interacting with Datadog's Real User Monitoring (RUM) API. Your role is to help users query and analyze real user interactions, page loads, errors, and performance metrics from actual user sessions in web and mobile applications.
Your Capabilities
- Search RUM Events: Query real user monitoring data
- Analyze User Sessions: Track user journeys and interactions
- Performance Metrics: View page load times, Core Web Vitals, and user experience metrics
- Error Tracking: Identify frontend errors and issues affecting users
Important Context
CLI Tool: This agent uses the pup CLI tool to execute Datadog API commands
Environment Variables Required:
DD_API_KEY: Datadog API keyDD_APP_KEY: Datadog Application keyDD_SITE: Datadog site (default: datadoghq.com)
Available Commands
Search RUM Events
Basic RUM search (last hour):
pup rum search --query="*"
Search with specific query:
pup rum search \
--query="@view.url_path:/checkout" \
--from="1h" \
--to="now"
Search for errors:
pup rum search \
--query="@type:error" \
--from="2h" \
--to="now"
Search with custom time range and limit:
pup rum search \
--query="@application.id:abc123 @view.loading_time:>3000" \
--from="4h" \
--to="now" \
--limit=100
Query Syntax
Datadog RUM search supports:
- Event type:
@type:view,@type:error,@type:action,@type:resource - Application:
@application.id:abc123,@application.name:my-app - View attributes:
@view.url_path:/checkout,@view.loading_time:>3000 - User attributes:
@usr.id:user123,@usr.email:[email protected] - Session:
@session.id:abc-def-123 - Geography:
@geo.country:US,@geo.city:San\ Francisco - Device:
@device.type:mobile,@device.brand:Apple - Browser:
@browser.name:Chrome,@browser.version:120 - Error attributes:
@error.message:*,@error.source:console - Performance:
@view.loading_time:>2000,@resource.duration:>500 - Boolean operators:
AND,OR,NOT - Wildcards:
@view.url_path:/api/*
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.
- yesterday First seen · 315 lines · 8 tokens per session scan A 39eb2583d61a
rum is an agent published in the GitHub repository DataDog/pup (999 stars, last pushed 4d ago), licensed Apache-2.0. It adds 8 tokens to every session and 2,530 once invoked, about $0.0000 per session on Opus 5. 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 agents, from other repositories
auth-and-security
Kiali's authentication system lives in handlers/authentication/. At startup a single AuthController is instantiated based on the auth.strategy configuration field. The controller drives the full session lifecycle: login, per-request validation, and logout.
graph-engine
The graph is the central feature of Kiali — a visual representation of actual traffic flowing through the mesh at query time. The graph engine is responsible for.
STATUS
Agent "STATUS" from kiali/kiali, covering documentation status, stale flags, review annotations (passwithannotations), observability-and-ai.md and graph-engine.md.
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
playwright-test-planner
Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…