migrate-optimizely-plan-flags

A command that scans Optimizely feature flags and writes a migration plan without creating flags in Confidence. Feature flags control which users receive a product behaviour.

In plain words
What is it for?
Auditing Optimizely flag definitions, recording flags with no rules, identifying blocked audience operators, and preparing the first migration phase.
Why use it?
It lets an operator review flag rules and unsupported matching options before any migration changes are made.

Command

Part of the confidence plugin — 13 skills, 17 commands, 2 MCP servers shipped together

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.

agentmods
npx agentmods add commands/spotify/confidence-ai-plugins/migrate-optimizely-plan-flags
Clone the repo
git clone --depth 1 https://github.com/spotify/confidence-ai-plugins

Or install confidence, the plugin that ships this one along with the rest of its 13 skills, 17 commands, 2 MCP servers.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00443
Opus 5 $0.00022 $0.00221
Sonnet 5 $0.00009 $0.00089
Haiku 4.5 $0.00004 $0.00044

Measured 3d ago against content hash 3efc1836896b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

migrate-optimizely-plan-flags 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 3d 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.

commands/migrate-optimizely-plan-flags.md · 38 lines

What it actually says

Treat this slash command as /migrate-optimizely plan flags.

Read skills/migrate-optimizely/SKILL.md (agent-only; do not narrate).

Follow Plan Flag: Steps: overview first, then Starting Phase 1 — Flag Definitions, resume check (.claude/plans/optimizely-flag-migration-*.md), step tracker, Generation Status after each step. No Confidence writes. No createFlag.

Flags with no Optimizely rules must appear in the plan under "Flags with no Optimizely rules → auto everyone catch-all" so the operator knows execute will add an everyone catch-all (Confidence empty rules do not resolve for everyone). See Automatic everyone catch-all in SKILL.md.

Rules operator audit (mandatory in Step 2): walk every audience match_type. Flag exists / substring / regex (and non-custom_attribute) as BLOCKED with flag ids in a Rules audit (production) table — Confidence does not support those operators. Ask workarounds before clearing BLOCKED. Do not complete Step 2 or pre-tick Migrate as if those rules were fine. See Rules operator audit in SKILL.md.

After Overall is ✓ complete, ASK the Step 5 exit question in SKILL.md (required — there is no automatic path into adjust): (1) Adjust flags, (2) Tick consent, (3) Execute flags (only if Migrate/Skip already set), (4) Done for now. If they pick (1), enter adjust in the same turn; do not require /migrate-optimizely adjust flags.

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. 3d ago First seen · 38 lines · 43 tokens per session scan A 3efc1836896b

Subscribe to this mod's changes

migrate-optimizely-plan-flags is a command published in the GitHub repository spotify/confidence-ai-plugins (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 443 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 2026-08-30.