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 Ancienttwo/repo-harness --skill windows-python-firstgit clone --depth 1 https://github.com/Ancienttwo/repo-harnessWrote 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/ancienttwo/repo-harness/windows-python-first)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/windows-python-first"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/windows-python-first/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/ancienttwo/repo-harness/windows-python-first"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/windows-python-first.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 | $0.00053 | $0.01185 |
| Opus 5.5 | $0.00021 | $0.00474 |
| Sonnet 5.5 | $0.00011 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
windows-python-first scanned grade A with 1 finding 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
When Python starts a native executable, pass an argument list to `subprocess.run`. Use `shell=False` and an explicit `cwd`. Inspect the return code. For `.cmd` or `.bat` tools, account for Windows shell parsing; do not a How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Python First
Worker entrypoint. Confirm that the task runs in native Windows before using these rules.
Use Python for file and text operations in native Windows. Use PowerShell to launch programs and for Windows APIs that require it. Keep direct Git, build, and test commands when they already work.
Select the runtime
Confirm the OS and the shell from the tool context. If needed, use $PSVersionTable.PSVersion to identify the PowerShell version. A Windows host can run a WSL shell. Use Linux rules inside WSL.
Use the project's Python interpreter when it has one. Otherwise, check py -3 --version. If that command is unavailable, check python --version. Confirm Python 3 and its executable path before use. A command name alone does not prove that an interpreter is installed.
For file and text work, launch the selected interpreter with -X utf8. This enables Python UTF-8 mode. It does not change the encoding of other programs or prove that PowerShell will decode their output correctly.
If Python is unavailable, use an existing file-edit tool. Use a short PowerShell command only when its behavior is clear. Report a missing runtime when it blocks the task. Do not install software or change system settings without task authorization.
Choose the smallest operation
- Use an available file-edit tool for a small source patch.
- Use Python for file reads and writes, text replacement, JSON, CSV, and batch file operations. Prefer its standard library.
- Use direct commands for Git, package managers, builds, and tests. Do not add a Python wrapper without a reason.
- Use PowerShell for Windows services, registry operations, and PowerShell modules when the task requires them.
Keep shell commands simple
Put multi-line Python code in a UTF-8 .py file with the file-edit tool. Store temporary helpers in the task's scratch directory. Do not put them in tracked source without a project reason.
Pass paths and data as arguments. Read them through sys.argv or argparse. Do not insert user text, JSON, regexes, or Windows paths into generated source code.
What ships with it
1 file 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.
- 5d ago First seen · 77 lines · 53 tokens per session scan A de7045013bce
windows-python-first is a skill published in the GitHub repository Ancienttwo/repo-harness (434 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,185 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, Select, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.