A read-only command-line tool for sending PromQL queries to a Prometheus server. Prometheus is a system that stores time-series measurements such as request errors, latency, and resource use.

It is for running instant or time-range PromQL queries and viewing the results as a table, CSV, JSON, or graph.

It lets you inspect monitoring data without changing source code or the monitored system. It can return query results or explain failures when investigating operational signals.

promql-cli — Skill for Claude Code and Codex by OutlineDriven

Install

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.

Any agent

npx skills add OutlineDriven/odin-claude-plugin --skill promql-cli

Clone the repo

git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-infra, the plugin that ships this one along with the rest of its 13 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/promql-cli.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/promql-cli)

Your own site

<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/promql-cli"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/promql-cli.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 916 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.00916
Opus 5	$0.00017	$0.00458
Sonnet 5	$0.00007	$0.00183
Haiku 4.5	$0.00003	$0.00092

Measured yesterday against content hash 841e1a20205c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

promql-cli 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 yesterday.

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.

plugins/odin-infra/skills/promql-cli/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PromQL CLI

Contract

Field	Bound contract
Trigger	User asks to execute or investigate PromQL, or to debug latency, error, or saturation signals against a Prometheus server.
Authority	Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. HTTP GET queries to the Prometheus HTTP API only.
Side effect	Evaluates PromQL queries through the Prometheus HTTP API. Reads metrics, writes nothing.
Done	Query results in the requested format, or a classified failure diagnosis, are returned to the user.

Inputs

PromQL query (required): the PromQL expression to evaluate.
Prometheus server URL (required): the base endpoint to query against, e.g. http://prometheus:9090.
Time range (optional): start and end timestamps or duration for range queries. Instant queries omit this.
Output format (optional): table, csv, json, or graph. Defaults to table.
Step interval (optional): resolution for range queries, e.g. 15s, 1m.

Procedure

Validate that the PromQL query is non-empty and the server URL is well-formed (scheme, host, and port present). If either is invalid, return a validation failure naming the missing or malformed field. Done when: the query and URL pass validation.
Construct the HTTP API request. For an instant query, use GET <server_url>/api/v1/query?query=<urlencoded_query>, appending &time=<unix_time> only when a time value is supplied. For a range query, first choose step as the supplied step interval or 15s when one is not supplied; the step interval is required for range queries. Then use GET <server_url>/api/v1/query_range?query=<urlencoded_query>&start=<unix_start>&end=<unix_end>&step=<step>. Set the Accept header to application/json. Do not send credentials unless the user supplies them explicitly. Done when: the HTTP request is constructed with all supplied parameters.
Execute the request using the host's HTTP client. Apply a 30-second timeout. If the server requires authentication, use the credentials the user supplied; do not invent or store credentials. Done when: the HTTP response is received or the request fails.
Classify the result. If the HTTP status is 200 and the response body has status: "success", extract the data.result array and render it in the requested format. If the HTTP status is 200 and status: "error", extract errorType and error from the response body. If the HTTP status is non-200, classify by status code. If the request timed out or the connection failed, classify accordingly. Done when: the result is classified as success or a named failure class.

Read the full file on GitHub · 41 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 153 B

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.

yesterday First seen · 41 lines · 34 tokens per session scan A 841e1a20205c

Subscribe to this mod's changes

promql-cli is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 916 once invoked, about $0.0002 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 2026-09-06.

Analytics and metrics claude-code-plugin claude-code-plugins claude-marketplace claude-plugins outline-driven-development

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens