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 SigNoz/agent-skills --skill signoz-mcp-setupgit clone --depth 1 https://github.com/SigNoz/agent-skillsWrote 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/signoz/agent-skills/signoz-mcp-setup)<a href="https://agentmods.dev/skills/signoz/agent-skills/signoz-mcp-setup"><img src="https://agentmods.dev/badge/skills/signoz/agent-skills/signoz-mcp-setup/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/signoz/agent-skills/signoz-mcp-setup"><img src="https://agentmods.dev/badge/skills/signoz/agent-skills/signoz-mcp-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00160 | $0.03976 |
| Opus 5.5 | $0.00064 | $0.01590 |
| Sonnet 5.5 | $0.00032 | $0.00795 |
| Haiku 4.5 | $0.00016 | $0.00398 |
Grade B, and why
signoz-mcp-setup scanned grade B with 1 finding 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 1mo 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.
`~/.claude/settings.json`, preserving unrelated settings. Claude ignores How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SigNoz MCP Setup
Initialize or repair the SigNoz MCP server registration shipped with this
plugin. The target state is one working signoz MCP server. Do not create a
duplicate server unless the user explicitly asks for a separate configuration.
Shared reference
Read references/mcp-settings.md before checking state, mapping user input, or editing registration files. It contains the server-state check, registration file locations, editing rules, and region mapping used by this procedure.
Read references/client-configs.md for a portable Agent Plugins v1 install, when the user names a client other than the bundled Claude Code or Cursor plugin path, when a native client config already exists, or when self-hosted stdio/local-binary setup is requested.
Configuration procedure
Step 1: Identify the client
Determine this before checking state: it decides where state is allowed to be checked from.
Use the client named in $ARGUMENTS or the user's latest message. If no
client is named, infer it only when the active environment is obvious (which
agent CLI or editor is running this skill, not just what files happen to exist
on disk):
Classify the install from the format the active client loaded, not from other
files that happen to coexist in the plugin root. An Agent Plugins v1 install
uses the portable mcp.json when its root plugin.json declares the canonical
Agent Plugins schema, even if the same root contains registration files for
Claude Code, Cursor, or Grok Build. Use a client-specific registration
file only when that client loaded the corresponding compatibility package.
- Portable Agent Plugins v1 install, including a VS Code or Codex installation
whose root manifest declares the Agent Plugins schema: use the standard
mcp.jsonin the installed plugin root. - Claude Code compatibility-package install: use the persisted plugin option referenced by its bundled registration file. Cursor compatibility-package install: use its bundled registration file.
- Grok Build: use the Grok Build CLI recipe in
client-configs.md. It ships a bundled registration file, but its endpoint is configured through[mcp_servers.signoz], not by editing that file. - VS Code / GitHub Copilot native MCP setup: use the native recipe only when no
Agent Plugins v1 install is active, the user explicitly requests native
config, or the endpoint is not eligible for portable
mcp.json. - Claude Desktop, Gemini CLI, Devin CLI, Windsurf, Zed, Antigravity CLI, or
OpenCode: use the matching native client recipe in
client-configs.md. - Unknown or unsupported client: use the generic HTTP MCP recipe and point the user to the SigNoz MCP Server docs for their client's exact config surface.
What ships with it
3 files 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.
- 1mo ago First seen · 331 lines · 160 tokens per session scan B 4daf7625917b
signoz-mcp-setup is a skill published in the GitHub repository SigNoz/agent-skills (19 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 3,976 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
deploy-slack-app
Use when a developer wants to deploy, host, or run a Slack app somewhere it keeps working after the local process stops, or mentions Railway, Heroku, railway up, git push heroku, slack deploy, a deploy hook in .slack/hooks.json, hosting a Socket Mode or Request URL (HTTP) Bolt app, deploying from Windows, graduating…
otel-collector-builder
Build custom OpenTelemetry Collector distributions with OCB (OpenTelemetry Collector Builder). Use when authoring or debugging a builder manifest (builder.yaml), choosing component and provider versions, building a collector that bundles a custom or out-of-distribution component, setting up CI or Docker builds of a…
otel-profiles
OpenTelemetry profiles signal and the eBPF profiler (otelcol-ebpf-profiler, profiling receiver). Use when setting up continuous profiling with OpenTelemetry, deploying the eBPF profiler on Linux hosts, Docker, or Kubernetes (DaemonSet, kind, k3d), building a profiles pipeline, sending OTLP profiles to Pyroscope…
huawei-cloud-agentarts-otel-ingestion
OpenTelemetry ingestion skill for Huawei Cloud AgentArts observability platform. Provides OTel telemetry data (trace/metrics/logs) ingestion into AgentArts agent-ops, AI Agent observation with genai semantic conventions, auto-configuration for Java/Python/Node.js/Go applications, and ingestion diagnostics and…
setting-up-wide-events-store
Use when a human asks to set up, deploy, or finish deploying the bundled Wide Events DuckDB store (the Kamal accessory that receives production telemetry). Covers the store generator, DNS, kamal setup, and post-deploy verification end to end.