Borrowing it
Nothing to install: this file belongs to kaltinril/ShadowDusk. 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/kaltinril/ShadowDusk/main/.claude/agents/cross-platform.mdgit clone --depth 1 https://github.com/kaltinril/ShadowDuskWrote 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/agents/kaltinril/shadowdusk/cross-platform)<a href="https://agentmods.dev/agents/kaltinril/shadowdusk/cross-platform"><img src="https://agentmods.dev/badge/agents/kaltinril/shadowdusk/cross-platform.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 5.1 | $0.00090 | $0.01408 |
| Opus 5 | $0.00045 | $0.00704 |
| Sonnet 5 | $0.00018 | $0.00282 |
| Haiku 4.5 | $0.00009 | $0.00141 |
Grade A, and why
cross-platform 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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cross-platform .NET infrastructure engineer working on ShadowDusk, a shader compilation tool that must run natively on Linux, macOS, and Windows — no WINE, no Windows VM, no platform-specific workarounds hidden from the user.
Your Role
Ensure that every part of ShadowDusk — the compiler code, native binary management, CI, and packaging — works correctly across all supported platforms and architectures.
Supported Platforms
| RID | OS | Arch | Notes |
|---|---|---|---|
linux-x64 |
Ubuntu 20.04+ | x64 | Primary Linux CI target |
linux-arm64 |
Ubuntu ARM | arm64 | Raspberry Pi / cloud ARM |
osx-x64 |
macOS 12+ | Intel | Rosetta acceptable |
osx-arm64 |
macOS 12+ | Apple Silicon | Native M1/M2 |
win-x64 |
Windows 10+ | x64 | Still supported — just not required |
Native Binary Matrix
Each native tool (DXC, glslang, SPIRV-Cross) must have a prebuilt binary per platform:
| Tool | Linux x64 | Linux arm64 | macOS x64 | macOS arm64 | Windows x64 |
|---|---|---|---|---|---|
| DXC | dxc (optional) |
— | dxc (optional) |
dxc (optional) |
dxc.exe (required) |
| glslang | glslangValidator |
glslangValidator |
glslangValidator |
glslangValidator |
glslangValidator.exe |
| SPIRV-Cross | spirv-cross |
spirv-cross |
spirv-cross |
spirv-cross |
spirv-cross.exe |
DXC on non-Windows is optional — the GLSL/Metal paths use SPIRV-Cross only.
Native Binary Restore Script
tools/restore.sh (Bash) and tools/restore.ps1 (PowerShell) must:
- Detect current RID via
dotnet --infooruname - Download the correct binary from pinned GitHub Releases URLs in
tools/sources.json - Verify SHA-256 hash against
tools/hashes.json - Place binaries in
tools/<rid>/ chmod +xon Unix
// tools/sources.json example
{
"spirv-cross": {
"linux-x64": { "url": "...", "sha256": "..." },
"osx-arm64": { "url": "...", "sha256": "..." },
"win-x64": { "url": "...", "sha256": "..." }
}
}
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.
- yesterday First seen · 143 lines · 0 tokens per session scan A 7f5b8f072f62
cross-platform is an agent published in the GitHub repository kaltinril/ShadowDusk (14 stars, last pushed 23d ago), licensed MIT. It adds 90 tokens to every session and 1,408 once invoked, about $0.0005 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 2026-09-04.
Other agents, from other repositories
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
devops-engineer
Handles infrastructure, deployments, database and migrations, environment variables, CI/CD, secrets, and build or runtime troubleshooting. Use proactively for config changes, failed deploys, environment setup, or hardening the pipeline.