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 commands/spotify/confidence-ai-plugins/migrate-optimizely-plan-flagsgit clone --depth 1 https://github.com/spotify/confidence-ai-pluginsWhat 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 | $0.00043 | $0.00443 |
| Opus 5 | $0.00022 | $0.00221 |
| Sonnet 5 | $0.00009 | $0.00089 |
| Haiku 4.5 | $0.00004 | $0.00044 |
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.
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.
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.
- 3d ago First seen · 38 lines · 43 tokens per session scan A 3efc1836896b
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.