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 instructions/grafana/oats/agents-mdgit clone --depth 1 https://github.com/grafana/oatsWrote 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/oats/agents-md)<a href="https://agentmods.dev/instructions/grafana/oats/agents-md"><img src="https://agentmods.dev/badge/instructions/grafana/oats/agents-md.svg" alt="Measured on agentmods" 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 | $0.00890 | $0.00890 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
oats 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
For a broader contributor orientation, see CONTRIBUTING.md. For durable architecture and product decisions, see the architecture decision records.
Project Overview
OATs (OpenTelemetry Acceptance Tests) is a declarative test framework for OpenTelemetry written in Go. It enables full round-trip testing from instrumented applications to the observability stack (LGTM: Loki, Grafana, Tempo, Prometheus, Mimir, OpenTelemetry Collector).
Test cases are defined in YAML files, discovered through an oats-config.yaml
whose meta.version: 3 is the single schema version (cases carry no version
field of their own). They can validate traces (TraceQL), logs (LogQL), metrics
(PromQL), and profiles (Pyroscope queries) using Docker Compose or Kubernetes
backends.
Build Commands
# Build
mise run build
# Run non-e2e tests
mise run test
# Run e2e tests
mise run e2e-test
Mise task implementations live in .mise/tasks/ as executable file tasks.
Keep task scripts there rather than adding new mise-invoked scripts under
scripts/; shared helpers used directly by CI or release workflows may remain
in scripts/.
Linting
# Auto-fix lint issues (recommended dev workflow)
mise run lint:fix
# Verify only (same command used in CI)
mise run lint
# Run all checks
mise run check
Linting is handled by flint.
Flint runs shellcheck, shfmt, actionlint, hadolint, rumdl, taplo, ryl,
biome, typos, editorconfig, lychee, renovate-deps, and gofmt.
EditorConfig rules live in .editorconfig.
Architecture
Package Organization
main.go— RootoatsCLI entry pointinternal/cli/— The gcx-driven CLI implementation used by the root binaryinternal/legacyyaml/— legacy (v1/v2) test-case parsing, execution, migration, models, response parsing, and signal-specific assertions (runner.go,traces.go,metrics.go,logs.go,profiles.go); used only by themigratesubpackagetesthelpers/— Docker Compose management, Kubernetes (k3d), and HTTP request helperstests/— Integration and e2e test 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.
- 4d ago First seen · 110 lines · 890 tokens per session scan A 73f13a2cfe19
oats AGENTS.md is an instructions file published in the GitHub repository grafana/oats (47 stars, last pushed today), licensed Apache-2.0. It adds 890 tokens to every session, about $0.0044 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 instructions, from other repositories
openllmetry CLAUDE.md
Instructions for traceloop/openllmetry, covering openllmetry repository guide, repository structure, nx workspace commands, run tests across all packages and run linting across all packages.
openinference AGENTS.md
Instructions for Arize-ai/openinference, covering claude.md, repository overview, repository structure, essential commands by language and python.
clawmetry AGENTS.md
AGENTS.md instructions for vivekchand/clawmetry, covering agents.md — for ai coding agents, quick context, where new code goes (open-core split), the rules that bite and common tasks.
mcp-ts-core AGENTS.md
AGENTS.md instructions for cyanheads/mcp-ts-core, covering developer protocol, consumers, core rules, exports reference and import conventions.
gonzo AGENTS.md
Instructions for control-theory/gonzo: This repo includes a Claude Code plugin with a guided log-analysis skill at skills/gonzo/.
signoz-mcp-server CLAUDE.md
Instructions for SigNoz/signoz-mcp-server, covering claude.md — development conventions, feature planning convention, rules, git & pr and code style.