prometheus-mcp: Instructions file for Codex

AGENTS.md

prometheus-mcp AGENTS.md is an instructions file for Codex, OpenCode from prometheus/prometheus-mcp. It costs 2,532 tokens per session, scanned A, original, Apache-2.0.

A project guide for prometheus-mcp, a server that lets AI clients query Prometheus, a system that stores and evaluates monitoring data. It documents how to build, test, lint, update embedded Prometheus documentation, and extend the server.

In plain words
What is it for?
Use it when building or testing prometheus-mcp, running its linter, refreshing its documentation snapshot, finding Make targets, or adding a new tool.
Why use it?
It gives contributors the project-specific commands and rules they need. This reduces missed checks and mistakes when changing the server.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is prometheus/prometheus-mcp's own configuration. It tells Codex and OpenCode how to work on prometheus-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prometheus-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to prometheus/prometheus-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prometheus/prometheus-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/prometheus/prometheus-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for prometheus-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/prometheus/prometheus-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/prometheus/prometheus-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/prometheus/prometheus-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/prometheus/prometheus-mcp/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.

agentmods 80×15 button for prometheus-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/prometheus/prometheus-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/prometheus/prometheus-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,532 This file is loaded in full into every session.
When invoked 2,532 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02532 $0.02532
Opus 5.5 $0.01013 $0.01013
Sonnet 5.5 $0.00506 $0.00506
Haiku 4.5 $0.00253 $0.00253

Measured 7d ago against content hash b7ffb44e5d4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prometheus-mcp 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 7d 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.

AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide for Prometheus MCP Server

An MCP server that exposes a running Prometheus instance (or compatible backend, e.g. Thanos) to LLM clients as typed tools and resources, plus search over an embedded snapshot of the official Prometheus docs (Bleve-indexed at startup). README.md is the canonical reference for the tool list, install methods, auth, telemetry, and flags — when a change affects any of those, update the README rather than duplicating it here.

Build, test, lint

Standard Prometheus tooling: Makefile includes Makefile.common and drives promu; CI is prometheus/promci (.github/workflows/ci.yml). Release artifacts are built in CI, not locally.

Task Command
Tests make test
Single test while iterating go test -race -run TestName ./pkg/mcp/
Lint make lint
Full pre-commit check (style, license headers, lint, yamllint, tidy, build, test) make
Build host binary make build
Refresh embedded docs snapshot make docs
List project-specific targets make help

Things CI enforces that are easy to miss locally:

  • The docs embed. cmd/prometheus-mcp/main.go declares //go:embed all:external/docs, and that directory is gitignored — make docs populates it from a pinned prometheus/docs tarball (DOCS_VERSION in the Makefile). On a fresh clone, raw go build ./... / go test ./... fails with a "no matching files" embed error; run any make build/test target once and raw go commands work from then on (package-scoped commands like go test ./pkg/mcp/ don't need the snapshot at all).
  • License headers. Every source file needs the Apache-2.0 header (check_license runs as part of bare make). Copy it from any existing .go file when creating a new one.
  • No drift. CI runs make and then git diff --exit-code — un-tidied go.mod/go.sum or anything else the build regenerates must be committed.
  • Golden tool schemas. TestToolInputSchemas compares every tool's ListTools input schema byte for byte against pkg/mcp/testdata/schemas/<tool>.json. Any change to an input struct, a jsonschema tag, or a tool's InputSchema fails the test until you run make update-golden and commit the fixtures. Read that diff before committing it — it is exactly what LLM clients receive. A "type": [ appearing in a fixture means a nullable slice crept back in (wrap the input with inputSchemaFor). A go-sdk or jsonschema-go bump that changes inferred output fails the test too; regenerate on that PR and review the diff rather than merging red.
  • golangci-lint (version taken from make print-golangci-lint-version) and govulncheck also gate PRs.
  • The Go version is pinned in three places — go.mod, .promu.yml, and the builder image in ci.yml. Bump them together.

Read the full file on GitHub · 61 lines

Changes

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.

  1. 7d ago Changed · +1 lines · +179 tokens per session b7ffb44e5d4c
  2. 8d ago Changed · +38 tokens per session ed7a5b8e13f5
  3. 22d ago Changed · +5 lines · +436 tokens per session 315e4a52e6ee
  4. 1mo ago First seen · 55 lines · 1,879 tokens per session scan A bd7a452a2cc3

Subscribe to this mod's changes

prometheus-mcp AGENTS.md is an instructions file published in the GitHub repository prometheus/prometheus-mcp (127 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,532 tokens to every session, about $0.0101 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.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens

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).

microsoft/vscode · 2,731 tokens