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 2233admin/reverse-skill-evolver --skill competition-browser-persistencegit clone --depth 1 https://github.com/2233admin/reverse-skill-evolverWrote 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/2233admin/reverse-skill-evolver/competition-browser-persistence)<a href="https://agentmods.dev/skills/2233admin/reverse-skill-evolver/competition-browser-persistence"><img src="https://agentmods.dev/badge/skills/2233admin/reverse-skill-evolver/competition-browser-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/2233admin/reverse-skill-evolver/competition-browser-persistence"><img src="https://agentmods.dev/badge/skills/2233admin/reverse-skill-evolver/competition-browser-persistence.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 | $0.00111 | $0.00625 |
| Opus 5.5 | $0.00044 | $0.00250 |
| Sonnet 5.5 | $0.00022 | $0.00125 |
| Haiku 4.5 | $0.00011 | $0.00063 |
Grade A, and why
competition-browser-persistence 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.
This is a copy
100% identical to competition-browser-persistence — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competition Browser Persistence
Use this skill only as a downstream specialization after $ctf-sandbox-orchestrator is already active and has established sandbox assumptions, node ownership, and evidence priorities. If that has not happened yet, return to $ctf-sandbox-orchestrator first.
Use this skill when the decisive branch lives in browser-held state rather than only in visible HTML or backend source.
Reply in Simplified Chinese unless the user explicitly requests English.
Quick Start
- Identify the active persistence surface first: cookie jar, localStorage, sessionStorage, IndexedDB, Cache Storage, or service worker.
- Record origin, scope, domain, path, expiry, and key names before mutating state.
- Tie stored state to one concrete effect: request header, rendered branch, cached response, offline behavior, or hidden route access.
- Separate boot-time state from runtime-mutated state.
- Reproduce the smallest stateful sequence that reaches the decisive branch.
Workflow
1. Map Browser State Surfaces
- Inspect cookies, storage buckets, service worker registrations, cache entries, and transient globals exposed during boot.
- Record which origin, host, route, or feature flag each state item actually applies to.
- Keep auth tokens, refresh material, CSRF state, cached responses, and feature toggles in separate evidence blocks.
2. Tie State To Runtime Behavior
- Show how stored state becomes request headers, role derivation, route visibility, cached API data, or offline fallback behavior.
- Compare clean-state and mutated-state runs with one variable changed at a time.
- Distinguish UI-only state from backend-accepted state.
3. Reduce To The Decisive Persistence Chain
- Compress the result to the smallest chain: initial page or login -> state persisted -> subsequent request or render branch -> resulting capability.
- Keep extracted storage, service worker scripts, and replay steps tied to the same origin and route.
- If the problem broadens into general web routing or worker behavior outside browser persistence, switch back to the broader web-runtime skill.
What ships with it
2 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 · 51 lines · 111 tokens per session scan A 48282126789e
competition-browser-persistence is a skill published in the GitHub repository 2233admin/reverse-skill-evolver (17 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 625 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to competition-browser-persistence, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
argent-device-interact
Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…
douyin-search
An example AI skill that automates searching for videos in Douyin, a Chinese short-video app, using the app's visible controls. It opens Douyin, enters a keyword, searches, and opens the first result.
ui-automation
Control the physical UI of any app on this device (clicks, scrolls, typing).
click
Tap a UI element by text on the screen.
browser
Full browser capability — managed Browsie session or emergency Main direct mode.
web-fetch
Fetch web content — 4-level escalation chain from curl to full browser.