Grafana Agent Observability is an SDK and plugin collection that collects telemetry from coding agents and AI agents built into applications, including sessions, tool calls, traces, tokens, costs, generations, and evaluations. Developers use it to monitor coding-agent usage or instrument agents in their own services, with SDKs for several programming languages. The catalogue add-ons help configure and use this observability workflow with coding agents.
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 grafana/agento11y --skill setup-coding-agentgit clone --depth 1 https://github.com/grafana/agento11yWrote 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/grafana/agento11y/setup-coding-agent)<a href="https://agentmods.dev/skills/grafana/agento11y/setup-coding-agent"><img src="https://agentmods.dev/badge/skills/grafana/agento11y/setup-coding-agent/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/grafana/agento11y/setup-coding-agent"><img src="https://agentmods.dev/badge/skills/grafana/agento11y/setup-coding-agent.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 | $0.00126 | $0.07918 |
| Opus 5.5 | $0.00050 | $0.03167 |
| Sonnet 5.5 | $0.00025 | $0.01584 |
| Haiku 4.5 | $0.00013 | $0.00792 |
Grade E, and why
setup-coding-agent scanned grade E with 3 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/grafana/agento11y/main/plugins/agento11y/scripts/install.sh | sh Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
For an offline dry run, use `agento11y guards test 'rm -rf ~/.ssh'`. It does not execute input, check Cloud rules, contact endpoints, start a daemon, or write files. It tests saved policy even when host guard requests ar Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/grafana/agento11y/main/plugins/agento11y/scripts/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up a coding agent with Grafana Agent observability
Grafana Agent observability records model calls, tokens, timing, tool names, and
reported or estimated cost. Conversation content is opt-in. The agento11y
binary launches agents and hosts hook-based integrations; pi and OpenCode export
in process. This path installs and configures the integration. It never changes
the user's application code.
Do the steps the machine's current state calls for, not all five. Step 1 says where to start: a machine that needs one credential re-saved does not need a reinstall, and a working setup the user asked a question about needs no changes at all.
Rules
- Never mint, generate, or guess a credential. The token is a Grafana Cloud access-policy token that only the user can create. Ask for it, or tell the user where to click. A made-up token produces a 401.
- Never invent an endpoint URL. The API URL and the OTLP endpoint come from the setup page of the user's own stack (Step 3). Do not assemble one from the stack name; regions differ.
- Never print or echo a token, and never ask for the connection block in
chat. The block the setup page hands out carries a live token, and this
conversation can be exported. The user pastes it into login's own prompt. A
token you have to pass yourself goes in over stdin with
--token-stdin. - Do not edit application code. Adding SDK calls to the user's app is a
different job ("Path B"). If the user wants their own app or agent
instrumented, stop and hand off to the
agento11y-instrumentskill, which ships with thegcxCLI (gcx agent skills install agento11y-instrument). - Do not enable full content capture or guards without asking. The default,
metadata_only, excludes prompts, responses, and tool I/O from generation exports.fullsends that content to Grafana Cloud. Guards send the content they evaluate toAGENTO11Y_ENDPOINTregardless of capture mode. Local mode is separate: it always captures full content in the local store.
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.
- today Changed · +4 lines 134a200a1508
- 5d ago Changed · -6 lines 4c0a4344dbde
- 7d ago Changed b711892dc62e
- 12d ago Changed be3c4e85d3cb
- 13d ago Changed 1fb2da6e3848
- 14d ago Changed 6f9f4fa995a4
- 15d ago Changed 27e3fd18bc1f
- 16d ago Changed 4d10f7db7eac
- 26d ago Changed · +5 tokens per session af12911c26c6
- 1mo ago First seen · 500 lines · 121 tokens per session scan E 5617d4277c54
setup-coding-agent is a skill published in the GitHub repository grafana/agento11y (132 stars, last pushed today), licensed Apache-2.0. It adds 126 tokens to every session and 7,918 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…