A setup guide for preparing a cloned vllm-ascend workspace, a project for serving machine-learning models on Ascend hardware. It covers initial repository setup such as GitHub access, submodules, and fork remotes.

Use it after cloning when you need to initialize submodules, configure GitHub access, or point the workspace and its projects at your forks.

It prevents first-time setup from accidentally overwriting useful remotes, exposing secrets, or changing unrelated runtime state.

How maoxx241/vllm-ascend-workspace configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/repo-init/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspace

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/repo-init/github.svg)](https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/repo-init)

Your own site

<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/repo-init"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/repo-init/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/repo-init"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/repo-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,377 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.02377
Opus 5.5	$0.00027	$0.00951
Sonnet 5.5	$0.00014	$0.00475
Haiku 4.5	$0.00007	$0.00238

Measured 2mo ago against content hash 8851fc5e7a98, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-init 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 2mo ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/_profile_choice_common.py, scripts/install_gh_user.py, scripts/install-gh-user.ps1, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/repo-init/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Init

Prepare a fresh or drifted vllm-ascend-workspace clone for development.

This skill is optional. Do not treat it as a prerequisite for unrelated work.

Use this skill when

the user asks to initialize the workspace after clone
the user asks to install or configure gh
the user asks to sign into GitHub
the user asks to initialize recursive submodules
the user asks to configure forks or remotes for the workspace, vllm, or vllm-ascend
the user asks for a broad workspace init and the local machine profile is missing

Do not use this skill when

the task is ordinary coding, debugging, docs, serving, or benchmarking
the task is generic Git work unrelated to initial setup
the user only wants remote machine attach / repair; use machine-management instead

Critical rules

Probe first.
Ask before every mutation category.
Preserve extra remotes such as upstream2.
Never write secrets or user-specific remotes into tracked files.
Keep local runtime state only under .vaws-local/.
Silently create .vaws-local/workspace-identity.json with one persistent UUID4 during broad-init probing. This idempotent local bootstrap is the only allowed pre-checkpoint mutation.
Prefer helper scripts in scripts/ and .agents/scripts/ over ad-hoc shell pipelines.
During broad init, do not call workspace_profile.py ensure directly for a missing profile. Use repo_init_profile.py.
The machine-username checkpoint must use exactly three options when the profile is missing:
- current Git username
- random agent#####
- custom username
If the user selects custom, stop again and ask for the literal username before any mutation.
Never infer a custom username from gh login, Git remotes, or the local OS account.

Cross-platform launcher rule

macOS / Linux / WSL: python3 ...
Windows: py -3 ...

Script-first entry points

Start with the probe script:

POSIX: python3 .agents/skills/repo-init/scripts/repo_init_probe.py --compact
Windows: py -3 .agents/skills/repo-init/scripts/repo_init_probe.py --compact

Read the full file on GitHub · 199 lines

Files

What ships with it

11 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.

Changes

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.

2mo ago First seen · 199 lines · 68 tokens per session scan A 8851fc5e7a98

Subscribe to this mod's changes

repo-init is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 2,377 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.

Git and workflow

repo-init next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-initmaoxx241/vllm-ascend-workspace	Skill	36	2mo ago	MIT	A	68	Claude Code, Codex
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code

vllm-ascend-workspace: Skill for Claude Code