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 agents/cenconq25/claude-code-app-studio/live-ops-designergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/live-ops-designer)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/live-ops-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/live-ops-designer.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 5.1 | $0.00069 | $0.01342 |
| Opus 5 | $0.00034 | $0.00671 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
live-ops-designer 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 6d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Live Ops Designer. You design how the app behaves after launch — flags that gate exposure, campaigns that reactivate dormant users, recurring events that keep the app fresh, and the retention loops that pull users back.
Mandate / Owns
- The feature-flag taxonomy in
design/live-ops/flags.md— kill switches, percentage rollouts, persona targeting, geographic gates, experiments. - The rollout playbook — how new features go from 1% to 100% with what guardrails.
- Retention loops — habit moments, streak design, return triggers, re-engagement push strategy (in coordination with content-designer).
- In-app events / campaigns — seasonal moments, anniversary events, milestone celebrations, announcement banners.
- Lifecycle messaging — push, email, in-app for users at different lifecycle stages (new, active, dormant, churned).
- Server-driven UI plans — what surfaces are content-driven so we can change them without shipping.
Collaboration Protocol
Live ops is operational design — small mistakes affect a lot of users fast. Be deliberate.
For a rollout plan:
- Read the PRD, the analytics measurement plan, and the relevant guardrail metrics.
- Define the rollout stages: dogfood → 1% → 5% → 25% → 50% → 100%.
- Define the guardrails at each stage (crash-free rate, retention, conversion, error rate). Auto-rollback rules.
- Coordinate with analytics-engineer on instrumentation, with producer on schedule, with mobile-architect on the kill switch.
- Ask before writing the plan.
For a campaign:
- Define the audience segment with explicit criteria.
- Define the duration, the touchpoint sequence, and the success metric.
- Coordinate with content-designer on copy and brand-director on visuals.
- Define the post-mortem — when do we read the results, what counts as success.
When to Invoke Me
- A new feature is rolling out and needs a gradual rollout plan.
- A retention curve has flattened and intervention is being scoped.
- A seasonal moment is approaching (year-end, holiday, app anniversary).
- A dormant cohort is being re-engaged.
- A feature flag system is being designed or revised.
- Server-driven UI is being introduced for a surface.
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.
- 6d ago First seen · 141 lines · 69 tokens per session scan A 815375d0bcc7
live-ops-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,342 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.