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 skills add ruizrica/agent-pi --skill qa-state-persistencegit clone --depth 1 https://github.com/ruizrica/agent-piWrote 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/ruizrica/agent-pi/qa-state-persistence)<a href="https://agentmods.dev/skills/ruizrica/agent-pi/qa-state-persistence"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/qa-state-persistence/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/skills/ruizrica/agent-pi/qa-state-persistence"><img src="https://agentmods.dev/badge/skills/ruizrica/agent-pi/qa-state-persistence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00108 | $0.01432 |
| Opus 5.5 | $0.00043 | $0.00573 |
| Sonnet 5.5 | $0.00022 | $0.00286 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
qa-state-persistence scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(agent-device:*) Bash(agent-browser:*) Bash(xcrun:*) Bash(node:*) Bash(curl:*) Bash(npx:*) Read How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-state-persistence
QA test skill for verifying UI state persistence across navigation. Tests that state changes (likes, bookmarks, cart additions, form inputs) survive scrolling away and returning. Uses the dual-driver architecture (CDP + agent-device).
What It Tests
| Test | Method | Assertion |
|---|---|---|
| Navigate to feed | CDP navigation | Route is on feed screen |
| Record item identity | CDP feed data query | Item ID and initial state captured |
| Verify initial state | CDP property query | State property is in expected initial value |
| Mutate state | CDP data mutation | Property flips (e.g., isLiked: false → true) |
| Scroll away (N items) | CDP scroll or agent-device swipe | Feed index advances |
| Scroll back | CDP scrollToIndex(0) |
Feed index returns to 0 |
| State persisted | CDP property query | KEY ASSERTION: property still has mutated value |
| Cleanup | CDP data mutation | Restore original state |
| Final route check | CDP cdp_get_route |
Still on feed screen |
Configuration
Set your app-specific values in qa.config.sh:
# What property to test
export STATE_PROPERTY="isLiked" # Property name to toggle
export STATE_COUNTER_PROPERTY="likesCount" # Associated counter (optional)
export STATE_SCROLL_COUNT=5 # How many items to scroll past
# Feed screen
export SCREEN_EXPLORE="ExploreScreen" # Your feed screen name
# Feed debug hook (set up in your app's dev build)
export GLOBAL_FEED_VAR="__qaFeedState" # Global variable name
Setting Up the Feed Debug Hook
In your app's feed component (dev builds only), expose:
// In your feed component (e.g., ExploreFeed.tsx):
if (__DEV__) {
globalThis.__qaFeedState = {
currentIndex: currentIndex,
scrollToNext: () => flatListRef.current?.scrollToIndex({ index: currentIndex + 1 }),
scrollToIndex: (i) => flatListRef.current?.scrollToIndex({ index: i }),
getData: () => feedData, // Return the full data array
getItem: (i) => feedData[i], // Return item at index
dataLength: feedData.length,
};
}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 167 lines · 108 tokens per session scan A eb225b493235
qa-state-persistence is a skill published in the GitHub repository ruizrica/agent-pi (276 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 1,432 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.