Mimir

What it does

When your agent uses it

• Running Mimir locally
• On Kubernetes (Helm mimir-distributed)
• Scaling Prometheus past a single node
• Picking ingest / query / backend split

Example prompts

• “I need long-term Prometheus storage”
• “scale Prometheus”
• “multi-tenant metrics backend”
• “/mimir”

Requirements

• Docker

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Stand up monolithic Mimir locally
2. 2Send metrics — Prometheus remote_write
3. 3Send metrics — Grafana Alloy
4. 4Deploy on Kubernetes (Helm, microservices)

What it can do on your machine

Read from SKILL.md and the folder at commit 1ccacf2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • jq
  • helm
  • kubectl
  • docker

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • grafana.github.io

  Also links to:

  • grafana.com
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mimir loads about 1.2k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 219 tokens; SKILL.md has 149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~219

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from grafana/skills at commit 1ccacf2, republished under its Apache-2.0 licence (© grafana). 149 words, ~1,153 tokens.

name

mimir

description

Stand up Grafana Mimir for horizontally scalable, multi-tenant, long-term Prometheus + OTLP metrics storage. Covers monolithic / read-write / microservices deployment, S3 / GCS / Azure / filesystem block storage, Prometheus `remote_write` and OTLP ingestion, multi-tenancy with `X-Scope-OrgID`, ingester replication factor, compactor retention, and per-tenant limits. Use when running Mimir locally or on Kubernetes (Helm `mimir-distributed`), scaling Prometheus past a single node, picking ingest / query / backend split, configuring tenants and ingestion rate, debugging `/ready` 503s or `429 Too Many Requests`, or pointing Grafana at a Mimir datasource — even when the user says "I need long-term Prometheus storage", "scale Prometheus", "multi-tenant metrics backend", "Cortex replacement", "remote_write target", or "store 10M active series" without naming Mimir.

license

Apache-2.0

# demo.yaml
target: all
multitenancy_enabled: false

blocks_storage:
  backend: filesystem
  bucket_store:
    sync_dir: /tmp/mimir/tsdb-sync
  filesystem:
    dir: /tmp/mimir/data/tsdb
  tsdb:
    dir: /tmp/mimir/tsdb

compactor:
  data_dir: /tmp/mimir/compactor
  sharding_ring:
    kvstore: { store: memberlist }

distributor:
  ring:
    instance_addr: 127.0.0.1
    kvstore: { store: memberlist }

ingester:
  ring:
    instance_addr: 127.0.0.1
    kvstore: { store: memberlist }
    replication_factor: 1

server:
  http_listen_port: 9009
  grpc_listen_port: 9095
  log_level: error

# 1. Run it
docker run --rm -p 9009:9009 -v $(pwd)/demo.yaml:/etc/mimir/demo.yaml \
  grafana/mimir:latest --config.file=/etc/mimir/demo.yaml

# 2. Verify readiness (expect HTTP 200, body: "ready")
curl -sf http://localhost:9009/ready

# 3. Verify it's serving the API
curl -s http://localhost:9009/api/v1/labels | jq '.status'   # → "success"

# 4. Verify self-metrics scrape
curl -s http://localhost:9009/metrics | grep -E '^mimir_(distributor|ingester)_' | head

remote_write:
  - url: http://localhost:9009/api/v1/push
    headers:
      X-Scope-OrgID: tenant1   # required when multitenancy_enabled: true

# Verify samples are landing
curl -s -H 'X-Scope-OrgID: tenant1' \
  'http://localhost:9009/api/v1/query?query=up' | jq '.data.result | length'
# Expect > 0 within ~30s of Prometheus scraping

prometheus.remote_write "mimir" {
  endpoint {
    url = "http://mimir:9009/api/v1/push"
    headers = { "X-Scope-OrgID" = "tenant1" }
  }
}

# 1. Install
helm repo add grafana https://grafana.github.io/helm-charts
helm install mimir grafana/mimir-distributed --version 6.0.6 -f values.yaml

# 2. Verify every pod is Running / Ready
kubectl get pods -n mimir
#   distributor, ingester, querier, query-frontend, store-gateway, compactor, ruler

# 3. Verify the gateway is ready
kubectl port-forward -n mimir svc/mimir-nginx 9009:80 &
curl -sf http://localhost:9009/ready

multitenancy_enabled: true
# Every request must include header:  X-Scope-OrgID: <tenant-id>

© grafana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/grafana-lgtm/mimir of grafana/skills.

• SKILL.md
• references/architecture.md
• references/storage.md

Open the folder on GitHubat commit 1ccacf2