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 liyingsong99/AIBridge --skill skillgit clone --depth 1 https://github.com/liyingsong99/AIBridgeWrote 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/liyingsong99/aibridge/skill)<a href="https://agentmods.dev/skills/liyingsong99/aibridge/skill"><img src="https://agentmods.dev/badge/skills/liyingsong99/aibridge/skill/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/liyingsong99/aibridge/skill"><img src="https://agentmods.dev/badge/skills/liyingsong99/aibridge/skill.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 | $0.00079 | $0.00435 |
| Opus 5.5 | $0.00032 | $0.00174 |
| Sonnet 5.5 | $0.00016 | $0.00087 |
| Haiku 4.5 | $0.00008 | $0.00044 |
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 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.
What it actually says
AI Bridge Unity Skill
Invocation
Run from Unity project root. $CLI is the platform AIBridge CLI; on Windows PowerShell prefer:
& "./.aibridge/cli/AIBridgeCLI.exe" <command> [action] [options]
Common options: --timeout, --raw, --pretty, --json, --stdin, --help, --on-dialog. Installed command references live under references/ after Skill install
Harness Snapshot
Project-side capabilities are in Root Rule / workflow rules. $CLI harness status is optional diagnosis only — not enablement/freshness preflight
Operating Rules
- Unity validation:
compile unity.compile dotnetis an extra check, not a Unity fallback - Imported asset path discovery:
asset search/find --format pathswhen Editor is available - Edit order:
inspector set_property/set_properties→aibridge-prefab-patch→ Editor scripts →unity-yaml-editingonly for unsupported YAML structure - Prefab asset edits:
assetPath + objectPath + componentName/componentIndex;componentInstanceIdis scene-only focusWindows-only;dialogCLI-only;inputneeds Play Mode + EventSystemruntime: quicklist_targetsfirst;--probe trueonly for port scan; UI start withruntime.ui.snapshot- Code Index: only when Root Rule declares enabled — load
aibridge-code-indexfor declaration-name lookup - Do not proactively clean
.aibridgecache unless the user asks for maintenance
What ships with it
33 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.
- aibridge-batch-script.meta 169 B
- aibridge-batch-script/SKILL.md 1.7 KB
- aibridge-batch-script/SKILL.md.meta 155 B
- aibridge-code-index/aibridge-skill.json 38 B
- aibridge-code-index/SKILL.md 1.4 KB
- aibridge-development-workflow/agents/openai.yaml 399 B
- aibridge-development-workflow/references/branch-selection.md 4.7 KB
- aibridge-development-workflow/references/branches/debug.md 1.4 KB
- aibridge-development-workflow/references/branches/implementation.md 1.1 KB
- aibridge-development-workflow/references/branches/orchestration.md 994 B
- aibridge-development-workflow/references/branches/requirements.md 1.9 KB
- aibridge-development-workflow/references/branches/review.md 818 B
- aibridge-development-workflow/references/branches/validation.md 825 B
- aibridge-development-workflow/references/checklist.md 2.5 KB
- aibridge-development-workflow/references/coding-rules.md 1001 B
- aibridge-development-workflow/references/debug-investigation-checklist.md 1.8 KB
- aibridge-development-workflow/references/debug-investigation-workflow.md 2.1 KB
- aibridge-development-workflow/references/editor-generation.md 6.8 KB
- aibridge-development-workflow/references/harness-readiness-detail.md 2.6 KB
- aibridge-development-workflow/references/harness-readiness.md 1.6 KB
- aibridge-development-workflow/references/profiler-debugging.md 1.7 KB
- aibridge-development-workflow/references/profiler-debugging.md.meta 155 B
- aibridge-development-workflow/references/risk-gates.md 2.0 KB
- aibridge-development-workflow/SKILL.md 2.4 KB
- aibridge-prefab-patch/SKILL.md 2.6 KB
- aibridge-workflow-orchestration/references/builtin-recipes.md 5.2 KB
- aibridge-workflow-orchestration/references/evidence-schema.md 1.5 KB
- aibridge-workflow-orchestration/references/orchestration-patterns.md 7.5 KB
- aibridge-workflow-orchestration/references/recipe-schema.md 3.7 KB
- aibridge-workflow-orchestration/references/workflow-cli-reference.md 3.1 KB
- aibridge-workflow-orchestration/SKILL.md 1.5 KB
- unity-yaml-editing/references/unity-yaml-reference.md 12 KB
- unity-yaml-editing/SKILL.md 3.5 KB
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 · 32 lines · 79 tokens per session scan A fe7437393fc4
aibridge is a skill published in the GitHub repository liyingsong99/AIBridge (228 stars, last pushed 25d ago), licensed MIT. It adds 79 tokens to every session and 435 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
uloop-get-project-info
Get Unity project information via uloop CLI. Use when you need to check project settings, Unity version, platform, or other project metadata.
dotcraft-unity
Use when dotcraft-unity MCP, CLI, or unityexecutecsharp is available, or when the user asks to inspect, automate, capture, or debug Unity Editor state, scenes, assets, Console logs, or GameView output. Provides background-first Unity Editor automation through MCP or CLI.
unity
Inspect, automate, and debug a running Unity Editor. Use for Unity scenes, assets, project state, Console logs, and Editor C# execution.
unity-ui
A Unity user-interface development and testing workflow for UI Toolkit and uGUI, Unity's two main UI systems.
unity-shared
Shared rules for working with Unity Editor instances through the Unity command-line relay.
unity-verify
A Unity Editor verification workflow that refreshes the project, waits for compilation, checks errors, and can run tests.