Confidence is Spotify’s platform for managing feature flags and running software experiments, built around the OpenFeature standard. Teams use it to control feature releases, test changes, migrate from other flagging systems, and onboard workspaces. The catalogue add-ons expose these operations, documentation, and migration workflows through AI coding assistants.
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 skills/spotify/confidence-ai-plugins/explore-metricnpx skills add spotify/confidence-ai-plugins --skill explore-metricgit clone --depth 1 https://github.com/spotify/confidence-ai-pluginsWrote 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/skills/spotify/confidence-ai-plugins/explore-metric)<a href="https://agentmods.dev/skills/spotify/confidence-ai-plugins/explore-metric"><img src="https://agentmods.dev/badge/skills/spotify/confidence-ai-plugins/explore-metric.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 | $0.00085 | $0.02465 |
| Opus 5 | $0.00043 | $0.01233 |
| Sonnet 5 | $0.00017 | $0.00493 |
| Haiku 4.5 | $0.00009 | $0.00247 |
Grade A, and why
explore-metric 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 5d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore Metric
Generate a pre-filled Metric Explorer URL for any event or fact table, so the user can preview and create metrics in the Confidence UI with one click.
Goal
Bridge the gap between raw event data and actionable experiment metrics. The user has events flowing — this skill helps them turn that data into a metric they can attach to experiments, by generating a ready-to-use Metric Explorer link with everything pre-filled.
User-Facing Communication Rules
- Use AskUserQuestion for all choices — never numbered lists in plain text
- Every question MUST have a recommended default. Analyze the available data and make an informed suggestion. Put the recommended option first with "(Recommended)" appended to its label. The user should be able to accept defaults and keep moving without having to think from scratch.
- Start from the business question, not the data model. Ask what the user wants to measure before diving into fact tables and columns.
Prerequisites
Confidence Flags MCP
Test: mcp__confidence-flags__getIdentityInfo (no args)
If not available, install it:
claude mcp add confidence-flags --transport http --url https://mcp.confidence.dev/mcp/flags
Flow
1. Understand what to measure
Before jumping to fact tables, ask the user what they're trying to understand. If the user provided a specific event or fact table as an argument, skip this step.
If no argument was provided, use AskUserQuestion:
What do you want to measure?
Examine the available fact tables and metrics to suggest the most relevant options. For example:
- Checkout conversion — are users completing purchases? (Recommended if a checkout fact table exists)
- Click-through rate — are users clicking? (Recommended if click/impression measures exist)
- Revenue impact — how much are users spending?
- Something else — describe what you want to measure
Use the answer to guide fact table selection and metric kind in subsequent steps.
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.
- 5d ago First seen · 215 lines · 85 tokens per session scan A 51b56b647332
explore-metric is a skill published in the GitHub repository spotify/confidence-ai-plugins (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,465 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…
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…