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 PageMastr/AIID --skill hid-bridgegit clone --depth 1 https://github.com/PageMastr/AIIDWrote 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/pagemastr/aiid/hid-bridge)<a href="https://agentmods.dev/skills/pagemastr/aiid/hid-bridge"><img src="https://agentmods.dev/badge/skills/pagemastr/aiid/hid-bridge/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/pagemastr/aiid/hid-bridge"><img src="https://agentmods.dev/badge/skills/pagemastr/aiid/hid-bridge.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 | $0.00110 | $0.01927 |
| Opus 5.5 | $0.00044 | $0.00771 |
| Sonnet 5.5 | $0.00022 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
hid-bridge 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HID Bridge
A single self-contained CLI (hidbridge.exe) that simulates keyboard and mouse input
at the Windows SendInput level (the same input-stack layer real HID devices report
through) and captures screenshots / short GIFs of a target window. Built so an agent
can actually play a game or actually operate an app rather than just reading its
source.
Binary: bin\hidbridge.exe (next to this file — self-contained, no .NET install
required). Source and build instructions: https://github.com/PageMastr/AIID
Every command prints exactly one JSON line to stdout: {"ok": true/false, ...}.
Always check ok before trusting the rest of a script.
Core workflow
- Find and focus the target window first.
SendInputdelivers events to whichever window currently has OS focus — it is not addressed by window handle. Any keyboard/mouse command will go to the wrong place (or nowhere useful) if the target window isn't focused.hidbridge.exe window focus <title-or-process-substring> - Drive it with
key/type/mousecommands. - Look at what happened with
screenshot, or capture a short clip withgif. Read the returnedpathwith the Read tool — screenshots and GIFs are real image files, so you can literally see the game/app state, not just infer it from logs.
Re-run window focus if focus may have been lost (e.g. after alt-tabbing, or if a
previous test spawned/killed a process).
Command reference
Window discovery
hidbridge.exe window list # all visible top-level windows
hidbridge.exe window find <substring> # first match, no side effects
hidbridge.exe window focus <substring> # bring to foreground + activate
hidbridge.exe window active # what currently has OS focus (debugging)
hidbridge.exe window rect <substring> # client-area rect in screen coords (debugging)
Matches against both window title and process name, case-insensitive substring.
window focus verifies the target actually became the foreground window (ok is
false if something else grabbed focus first) — if that happens, just retry the
focus call right before the input you're about to send.
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 · 159 lines · 110 tokens per session scan A 86510141379f
hid-bridge is a skill published in the GitHub repository PageMastr/AIID (4 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 1,927 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
regression-suite
Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
soak-test
Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.
smoke-check
Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.