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.
Borrowing it
Nothing to install: this file belongs to grafana/agento11y. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/grafana/agento11y/main/AGENTS.mdgit 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/instructions/grafana/agento11y/agents-md)<a href="https://agentmods.dev/instructions/grafana/agento11y/agents-md"><img src="https://agentmods.dev/badge/instructions/grafana/agento11y/agents-md/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/instructions/grafana/agento11y/agents-md"><img src="https://agentmods.dev/badge/instructions/grafana/agento11y/agents-md.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 | $0.03053 | $0.03053 |
| Opus 5.5 | $0.01221 | $0.01221 |
| Sonnet 5.5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
agento11y AGENTS.md 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 23d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on agento11y
This file is for agents working on this repo (the SDKs in go/, python/, js/, java/, dotnet/ and the launchers in plugins/).
For agents working in a consumer project (instrumenting their app, or installing one of our plugins), point them at llms.txt instead. That is the file we ship to users.
Read the README and mise tasks for the obvious stuff: layout, package names, where languages live. This file only documents what you can't discover by looking.
Git blame ignores the local viewer reformat in .git-blame-ignore-revs. Run git config blame.ignoreRevsFile .git-blame-ignore-revs once in each clone.
Proto is the source of truth
proto/agento11y/v1/*.proto is the source of truth. Generated stubs live under each language tree:
- Go:
go/proto/agento11y/ - Python:
python/agento11y/internal/gen/agento11y/ - JS:
js/proto/agento11y/(the runtime loads.protofiles directly, no codegen) - Java, .NET: compiled on build via the gradle protobuf plugin and
Grpc.Tools; no committed stubs.
Never edit generated files. Edit the .proto, then:
mise run generate:proto
CI runs mise run check:proto and fails the build if the committed stubs drift from the proto. Tool versions are pinned in mise.toml so output is byte-identical across machines. See docs/development.md for the full table.
Secret patterns are the second source of truth
redaction/patterns.json is the only editable secret-pattern table. Each engine gets its list generated from it, next to hand-written code: go/agento11y/redaction_patterns_gen.go, python/agento11y/_redaction_patterns.py, js/src/redaction-patterns.generated.ts, dotnet/src/Grafana.Agento11y/RedactionPatterns.g.cs, plugins/agento11y/internal/redact/patterns_gen.go.
Never edit those five files. Edit patterns.json, then:
mise run generate:redaction
CI runs mise run check:redaction in the same job as the proto drift check. redaction/README.md covers the pattern fields and the shared fixtures.
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.
- 23d ago Changed · +139 tokens per session 94410b331d3d
- 1mo ago Changed · +3 lines · +185 tokens per session 85f0248163f1
- 1mo ago Changed · +12 lines · +158 tokens per session 6582f8d89434
- 2mo ago First seen · 112 lines · 2,571 tokens per session scan A ad0b4985483c
agento11y AGENTS.md is an instructions file published in the GitHub repository grafana/agento11y (132 stars, last pushed today), licensed Apache-2.0. It adds 3,053 tokens to every session, about $0.0122 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.