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.
Borrowing it
Nothing to install: this file belongs to spotify/confidence-ai-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spotify/confidence-ai-plugins/main/CLAUDE.mdgit 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/instructions/spotify/confidence-ai-plugins/claude-md)<a href="https://agentmods.dev/instructions/spotify/confidence-ai-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/spotify/confidence-ai-plugins/claude-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.
<a href="https://agentmods.dev/instructions/spotify/confidence-ai-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/spotify/confidence-ai-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01047 | $0.01047 |
| Opus 5.5 | $0.00419 | $0.00419 |
| Sonnet 5.5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
confidence-ai-plugins CLAUDE.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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Confidence Plugin
This plugin integrates Confidence with Claude Code, providing tools for feature flag management, experimentation, and migration from other platforms.
Commands
/confidence:migrate-posthog <plan flag | plan code | execute <plan-file>>— Migrate feature flags from PostHog to Confidence SDK/confidence:migrate-eppo <plan flag | plan code | execute <plan-file>>— Migrate feature flags from Eppo to Confidence SDK/confidence:migrate-statsig <plan flag | plan code | execute <plan-file>>— Migrate feature flags from Statsig to Confidence SDK/confidence:migrate-optimizely(no args →plan access) or/confidence:migrate-optimizely <plan access | adjust access | execute access | plan flags | adjust flags | execute flags | plan code | adjust code | execute code | execute <plan-file>>— Migrate Optimizely to Confidence. Phase 0–2 each support plan / adjust / execute; Flag clients are Step 4 ofplan access. See README — Optimizely → Confidence/confidence:onboard-confidence <create-account | invite-user | create-client | setup-wizard | setup-warehouse | learn | status>— Create accounts, onboard users, set up SDK clients, configure warehouses, and learn experimentation concepts/confidence:analyze-project [project-dir]— Analyze a project and propose meaningful feature flag changes using Confidence/confidence:instrument-events [project-dir]— Analyze a project, identify events to track, create event definitions with entity references, add SDK track() calls, and verify the pipeline/confidence:explore-metric [event-name or fact-table-name]— Generate a pre-filled Metric Explorer URL for any event or fact table to preview and create metrics in the UI/confidence:setup-session-recording [project-dir]— Set up Confidence Session Recording in a browser-based project
Skills
- migrate-posthog — Auto-triggers when the user asks to migrate PostHog flags or transform SDK code to Confidence
- migrate-eppo — Auto-triggers when the user asks to migrate Eppo flags or transform SDK code to Confidence
- migrate-statsig — Auto-triggers when the user asks to migrate Statsig gates/configs/experiments or transform SDK code to Confidence
- migrate-optimizely — Auto-triggers when the user asks to migrate or adjust Optimizely users, teams, groups, roles, policies, clients, flags/rollouts/experiments, or SDK code to Confidence (including adjust flags / adjust code)
- onboard-confidence — Auto-triggers when the user asks to create a Confidence account, invite users, set up SDK clients, configure warehouses, run the setup wizard, or learn about experimentation
- analyze-project — Auto-triggers when the user asks what to feature-flag, wants flag suggestions, or asks to analyze their project for feature flag opportunities
- instrument-events — Auto-triggers when the user asks to instrument events, add tracking, set up event tracking, analyze what to track, or measure experiment impact
- explore-metric — Auto-triggers when the user asks to explore a metric, preview a metric, create a metric from an event or fact table, or open the Metric Explorer
- setup-session-recording — Auto-triggers when the user asks to add session recording, session replay, or integrate Confidence recordings into their app
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.
- 1mo ago Changed · +2 lines · +64 tokens per session fdad797d88de
- 1mo ago Changed · +9 lines · +253 tokens per session b35fda61f99e
- 2mo ago First seen · 31 lines · 730 tokens per session scan A 0d1ac45d5802
confidence-ai-plugins CLAUDE.md is an instructions file published in the GitHub repository spotify/confidence-ai-plugins (9 stars, last pushed 18d ago), licensed Apache-2.0. It adds 1,047 tokens to every session, about $0.0042 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.
confidence-ai-plugins CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| confidence-ai-plugins CLAUDE.mdspotify/confidence-ai-plugins | Instructions file | 9 | 18d ago | Apache-2.0 | A | 1,047 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |