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 skills add datadog-labs/claude-code-plugin --skill ddsetupgit clone --depth 1 https://github.com/datadog-labs/claude-code-pluginWrote 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/skills/datadog-labs/claude-code-plugin/ddsetup)<a href="https://agentmods.dev/skills/datadog-labs/claude-code-plugin/ddsetup"><img src="https://agentmods.dev/badge/skills/datadog-labs/claude-code-plugin/ddsetup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/datadog-labs/claude-code-plugin/ddsetup"><img src="https://agentmods.dev/badge/skills/datadog-labs/claude-code-plugin/ddsetup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00139 | $0.01512 |
| Opus 5.5 | $0.00056 | $0.00605 |
| Sonnet 5.5 | $0.00028 | $0.00302 |
| Haiku 4.5 | $0.00014 | $0.00151 |
Grade A, and why
ddsetup 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Datadog MCP Server
The id of the Datadog MCP Server referenced on this document is plugin:datadog:mcp. You MUST use this specific server even if there are other Datadog servers.
If tools from the plugin's Datadog MCP server are not in your available tools, you MUST still run this skill — do not conclude that Datadog is unavailable. Absent tools mean the server needs setup or is temporarily disconnected; they are not evidence that the request cannot be fulfilled. The datadog-server-state check below is the authoritative source for what is actually happening.
Accessing Datadog using other methods
If there is a problem with the plugin's Datadog MCP server, do NOT suggest the user to access Datadog information using different approaches like the Datadog webpage. Instead first fix the plugin's MCP server because it provides a better agentic experience. Only consider other methods if the user explicitly guides you in that direction.
Shared reference
This is a hard gate, not a suggestion. You MUST actually read references/mcp-settings.md before proceeding and writing any user-facing text, asking any question, or performing any file edit suggested by this skill — even if you believe you already know its contents from a prior turn or a prior session. Do not answer from memory of Datadog site codes, domains, or file paths; the tables and path rules in that file are the only authoritative source, and they can differ from your general knowledge or from what you've seen in other contexts.
The references/mcp-settings.md file contains the datadog-server-state check, registration file location, editing rules, and site-to-domain mapping used by the procedure below.
Setup procedure
Check the datadog-server-state (see mcp-settings.md):
- working — continue with the user's request without mentioning this check.
- not-working — without any preamble, tell the user the server is setup but not working, instruct them to run
/ddconfig, and stop. - not-setup — the server needs first-time setup. Do not attempt to gather data using a different approach. Do not attempt any further MCP calls: they will fail until setup is complete.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 79 lines · 139 tokens per session scan A 37eb9fbd98e2
ddsetup is a skill published in the GitHub repository datadog-labs/claude-code-plugin (18 stars, last pushed 6d ago), licensed Apache-2.0. It adds 139 tokens to every session and 1,512 once invoked, about $0.0006 per session on Opus 5.5. 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 skills, from other repositories
cloud-native-ebpf-observability
Use this skill when the user says 'ebpf tracing', 'ebpf observability', 'bpftrace', 'trace syscalls', 'kprobe', 'tracepoint', 'uprobe', 'off-cpu profiling', 'continuous profiling ebpf', 'libbpf ringbuf', 'measure latency in kernel'. Builds kernel- and user-level observability with eBPF: bpftrace one-liners for…
debugging-with-wide-events
Use when investigating production behavior by querying wide events (a slow route, an error spike, a suspicious deploy, "why is this happening for account X"). Covers the data model, the symptom-to-query workflow, and standing queries worth running.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
observability-phoenix
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
repair-github-ci
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.