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 skills/olo-dot-io/uni-cli/bgclick-revnpx skills add olo-dot-io/Uni-CLI --skill bgclick-revgit clone --depth 1 https://github.com/olo-dot-io/Uni-CLIWrote 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/olo-dot-io/uni-cli/bgclick-rev)<a href="https://agentmods.dev/skills/olo-dot-io/uni-cli/bgclick-rev"><img src="https://agentmods.dev/badge/skills/olo-dot-io/uni-cli/bgclick-rev.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 | $0.00056 | $0.00916 |
| Opus 5 | $0.00028 | $0.00458 |
| Sonnet 5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
bgclick-rev 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background-Click Reverse Engineering
Use this skill only for research on a user-provided macOS .app. If IDA Pro or IDA MCP is unavailable, stop early and explain the blocker. Do not modify Uni-CLI source code from this skill; write research artifacts and reproduction code only after the binary evidence is gathered.
Outputs
Create a research bundle under <workspace>/research/:
SHARED-CONTEXT.mdwith target paths, bundle IDs, signing status, IDA MCP instance mapping, and priors to verify.findings/<phase-or-question>.mdfor call-site maps and open questions.sub_<addr>-<label>.mdfor every decompiled function used as evidence.frame-map.mdfor Swift async task-frame offsets.FINAL-REPORT.mdwith behavior spec, evidence table, reproduction diff, and VM test plan.
If asked to build a reproduction, add:
Sources/<Module>/BackgroundClicker.swiftEchoApp/main.swiftimpl-research.mdwith empirical VM runs.
Priors To Verify
Treat these as hypotheses until confirmed in the target binary:
- Events are posted with
CGEvent.postToPid(_:). - The synthetic event starts as
NSEvent.mouseEvent(...), then usesevent.cgEvent. - Explicit integer fields are
3button,7subtype value3,91window under pointer, and92window that can handle the event. - Screen location is set, read back, translated by the target window origin, and written with
CGEventSetWindowLocationresolved bydlsym. - Background targets receive
CGEventFlags.maskCommand(0x00100000), not the non-coalesced flag. CGWindowIDcomes fromCGWindowListCopyWindowInfo(.optionOnScreenOnly, kCGNullWindowID)filtered by owner PID.- Do not double-write fields already populated by
NSEvent.cgEvent. - The click path should not activate the target app through AppKit, AX frontmost setters, or SLS/CGS private activation APIs.
Workflow
- Triage the
.app: locate main executable and helper apps, recordcodesign -d --entitlements -,nm -u, and relevant Mach-O paths. - Confirm IDA MCP instances and map each instance to a binary in
SHARED-CONTEXT.md. - Audit service binary call sites upward from
CGWindowListCopyWindowInfo,CGWindowListCreateDescriptionFromArray, AX APIs, screen-capture APIs,dlsym, anddlopen. - Identify the dispatch function that logs or formats the click dispatch message, then trace the Swift async continuation chain into the synthesizer.
- For each decompiled function used, write
research/sub_<addr>-<label>.mdwith a one-line verdict, trimmed evidence, frame writes, and Swift equivalent. - Resolve dyld-hash wrappers to concrete CoreGraphics symbols. Verify with
dlsymon a comparable macOS host when possible. - Produce
findings/cgevent-fields.mdmapping every explicitsetIntegerValueFieldwrite to SDK constants and source expressions. - Hunt open questions independently. Each finding file starts with a one-sentence verdict and includes evidence addresses.
- Build
BackgroundClicker.swiftonly from verified behavior. Use public AppKit/CoreGraphics APIs plusdlsymforCGEventSetWindowLocation. - Validate in a VM with an EchoApp counter window. Record window number, screen point, window-local point, activation state, and pass/fail in
impl-research.md.
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.
- 5d ago First seen · 58 lines · 56 tokens per session scan A 82adb95f0f0f
bgclick-rev is a skill published in the GitHub repository olo-dot-io/Uni-CLI (270 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 916 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 skills, from other repositories
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.