Borrowing it
Nothing to install: this file belongs to xianyu603/HaloCreek. 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/xianyu603/HaloCreek/master/.codex/skills/halocreek-build-review/SKILL.mdgit clone --depth 1 https://github.com/xianyu603/HaloCreekWrote 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/xianyu603/halocreek/halocreek-build-review)<a href="https://agentmods.dev/skills/xianyu603/halocreek/halocreek-build-review"><img src="https://agentmods.dev/badge/skills/xianyu603/halocreek/halocreek-build-review/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/xianyu603/halocreek/halocreek-build-review"><img src="https://agentmods.dev/badge/skills/xianyu603/halocreek/halocreek-build-review.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 | $0.00066 | $0.00607 |
| Opus 5 | $0.00033 | $0.00303 |
| Sonnet 5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
halocreek-build-review 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 12d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HaloCreek Build Review
Context
HaloCreek is an Avalonia desktop app at HaloCreek/HaloCreek.csproj.
The project targets net10.0-windows10.0.18362.0.
Prefer Windows PowerShell execution from the repository root. The default build command is:
dotnet build .\HaloCreek\HaloCreek.csproj
Use Windows PowerShell even when the agent is hosted through psmux; do not switch to WSL/bash commands unless the user explicitly asks for WSL-specific diagnosis.
Build Validation
Run build from the repository root:
dotnet build .\HaloCreek\HaloCreek.csproj
Treat the build as passing only when the output reports zero warnings and zero errors, for example 0 Warning(s) and 0 Error(s) or the localized equivalent.
Report the output assembly path if present, normally:
D:\work\HaloCreek\HaloCreek\bin\Debug\net10.0-windows10.0.18362.0\HaloCreek.dll
If the build fails because HaloCreek.exe, HaloCreek.dll, or another output file is locked by a running HaloCreek process, report the locked file/process from the build output. Do not kill the process, do not switch to an alternate output directory, and do not launch another app window unless the user explicitly asks for that recovery step.
Launch For Review
Only launch the app when the user explicitly asks to open or review the desktop window. Do this after all requested edits, builds, and checks are complete. Do not launch automatically after a successful build.
When launch is explicitly requested, launch the already-built Windows executable detached from the agent process by using the clean launch script:
.\.codex\skills\halocreek-build-review\Start-HaloCreekClean.ps1
The script removes psmux/terminal-multiplexer environment variables from its own process before starting HaloCreek, so the launched desktop app does not inherit the agent pane environment. Use this script instead of calling Start-Process directly.
Then report that the app was launched and leave the window open for the user. Do not stop the process unless the user explicitly asks to close it.
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.
- 12d ago First seen · 57 lines · 66 tokens per session scan A ddf0d1a56da4
halocreek-build-review is a skill published in the GitHub repository xianyu603/HaloCreek (1 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 607 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 2026-08-31.
Other skills, from other repositories
tech-preflight-dotnet
Verify .NET SDK compatibility, map project dependency graphs, and run baseline builds before code changes. Use when starting a new task, onboarding to a .NET solution, checking environment readiness, or diagnosing build failures from SDK mismatches.
typescript
TypeScript strict mode with eslint and jest.
python
Python development with ruff, mypy, pytest - TDD and type safety.
refactoring-csharp
Rename and refactor C# symbols in a .NET solution or multi-solution monorepo with a one-shot Roslyn CLI. Use when the user asks to rename a symbol, preview impact, update references across a solution, or refactor shared projects across several solutions.
ring:verifying-code
Verifying a Go project: runs every quality check (lint, vet, imports, format, docs, unit, integration, E2E) and returns a single MERGEREADY or NEEDSFIX verdict. Report-only: never fixes anything. Use for a quick pre-merge or pre-PR check outside a full dev-cycle. Skip when not a Go project, when you want a single…
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…