Borrowing it
Nothing to install: this file belongs to FlameskyDexive/Legends-Of-Heroes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FlameskyDexive/Legends-Of-Heroes/master/.codex/skills/aibridge/SKILL.mdgit clone --depth 1 https://github.com/FlameskyDexive/Legends-Of-HeroesWrote 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/flameskydexive/legends-of-heroes/aibridge)<a href="https://agentmods.dev/skills/flameskydexive/legends-of-heroes/aibridge"><img src="https://agentmods.dev/badge/skills/flameskydexive/legends-of-heroes/aibridge/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/flameskydexive/legends-of-heroes/aibridge"><img src="https://agentmods.dev/badge/skills/flameskydexive/legends-of-heroes/aibridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 34 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00125 | $0.02004 |
| Opus 5 | $0.00063 | $0.01002 |
| Sonnet 5 | $0.00025 | $0.00401 |
| Haiku 4.5 | $0.00013 | $0.00200 |
Grade A, and why
aibridge 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 13d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Bridge Unity Skill
Invocation
Run commands from the Unity project root.
CLI Path: ./.aibridge/cli/AIBridgeCLI.exe
Example Alias: $CLI is a shorthand for the platform-appropriate AIBridge CLI invocation. Examples use $CLI for consistency; replace it with the matching invocation form when running commands directly.
Invocation Forms:
- Windows executable:
./.aibridge/cli/AIBridgeCLI.exe <command> [action] [options] - macOS/Linux DLL:
dotnet ./.aibridge/cli/AIBridgeCLI.dll <command> [action] [options] - PowerShell call operator:
& "./.aibridge/cli/AIBridgeCLI.exe" <command> [action] [options]
Most Unity-side commands require an action such as asset search or inspector set_property. CLI-only commands and helpers can differ: focus has no action, dialog uses status/click/wait, and multi uses --cmd or --stdin. Use --help or the generated command reference for the exact form.
Global Options:
--timeout <ms>- Timeout (default: 5000)--on-dialog <mode>- When a Unity command is blocked by a modal dialog, optionally wait or click:none,wait,cancel,save,discard,ok,yes,no,delete,replace--raw/--pretty- JSON output (default: raw)--json <json>/--stdin- Complex parameters--help- Show help
Cache Directory: .aibridge/ (Editor commands/results/screenshots and Runtime targets under .aibridge/runtime/targets/)
Dialog Output Rule: dialog status omits blockedByDialog and dialogs when no blocking Unity modal dialog is detected. Missing fields mean no dialog.
Operating Rules
- Use
compile unityfor Unity validation.compile dotnetis an explicit extra solution-build check, not a fallback. - For Unity assets, prefer
asset search/find --format paths; use host file reads for file contents, andasset read_textonly when host reads are unavailable. - Resource edit order: use
inspector set_property/set_propertiesfor single or batched fields,aibridge-prefab-patchfor complex Prefab structure edits it supports, Unity Editor scripts for high-level generated assets, andunity-yaml-editingonly for unsupported serialized-file structure work. - For scene objects, Prefabs, and serialized Unity assets, discover targets with
inspector get_components/get_properties/find_property, then write with AIBridge/Unity APIs when possible; avoid raw YAML unless no supported API can express the operation. - Direct YAML edits are acceptable only after loading
unity-yaml-editing, including unsupported Scene/Prefab/ScriptableObjectTable/custom.assetoperations. Preservem_Script,fileID/guid/typereferences, YAML indentation, and paired.metaGUIDs; validate afterward with import, targeted inspection,compile unity, and Error logs. - For prefab asset edits, use
assetPath + objectPath + componentNameorcomponentIndex;componentInstanceIdis scene-only. - For complex prefab asset edits, use the
aibridge-prefab-patchskill and preferprefab patch --ops <file>with dry-run first. - In PowerShell, avoid inline complex
--json; build JSON in a variable, escape embedded quotes for native EXE argument passing, and pass command parameters directly, especiallyinspector set_properties --values $values. focusis Windows CLI-only.dialogis CLI-only, uses Windows window APIs or macOS Accessibility permission, and omits dialog fields when no modal dialog is detected.screenshot gameandscreenshot gifrequire Play Mode;screenshot scene_viewworks in Edit mode when a Scene view is open.inputrequires Play Mode and an active EventSystem; use it withgameview,screenshot, andget_logsfor UI interaction checks.runtimeis CLI-only and talks toAIBridgeRuntimeinside a Player or Play Mode target. Useruntime list_targetsfirst, then targetlatestor a specific target id.- Code Index is a separate optional Skill. Use
aibridge-code-indexonly when that Skill is installed and project rules say Code Index is enabled; otherwise userg, file reads, and regular AIBridge commands.
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.
- 13d ago First seen · 127 lines · 125 tokens per session scan A f6d2f669dfe1
aibridge is a skill published in the GitHub repository FlameskyDexive/Legends-Of-Heroes (925 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 2,004 once invoked, about $0.0006 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
luban-dev
A guide for Luban, a game-configuration tool that turns spreadsheets and schemas into C# code and binary data for a TEngine project.
html-to-ugui
A pipeline for turning HTML interface prototypes into Unity UGUI Prefabs, which are reusable Unity interface objects. It uses browser-rendered layout data to preserve positions, images, text, controls, and device-adaptation intentions.
tengine-dev
A development guide for TEngine, a framework used to build Unity games. It covers the framework’s modules, user interfaces, events, asset loading, hot updates, configuration, and related tools.
game-development
Game development patterns, architectures, and best practices.
anti-cheat-systems
Analyze layered game integrity defenses and select repository resources for process-memory reports, acquired-memory forensics, callback scope, behavioral measurement and driver-policy evidence. Use for DMA versus host-mediated acquisition, input provenance, replay fidelity, collector health, detector rollout/recovery…
game-hacking-techniques
Classify game-cheating threats across client memory, code injection, rendering, input, engines, kernels, DMA and remote transports. Use for repository-backed attack-surface maps, attacker prerequisites, state exposure, legitimate comparison baselines, and observable artifacts. Select engine source, capture or…