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.
curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/remote-code-parity/SKILL.mdgit clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspaceWrote 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/maoxx241/vllm-ascend-workspace/remote-code-parity)<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/remote-code-parity"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/remote-code-parity/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/maoxx241/vllm-ascend-workspace/remote-code-parity"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/remote-code-parity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 148 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00072 | $0.04689 |
| Opus 5.5 | $0.00029 | $0.01876 |
| Sonnet 5.5 | $0.00014 | $0.00938 |
| Haiku 4.5 | $0.00007 | $0.00469 |
Grade A, and why
remote-code-parity 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.
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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote Code Parity
Keep a ready remote runtime in exact code parity with the local vllm-ascend-workspace checkout.
External business worktrees can be selected with repeatable
--source vllm=/actual/worktree --source vllm-ascend=/actual/worktree on
parity_sync.py or the low-level helper. Snapshots come from those exact
worktrees without resetting them or maintaining copied branches.
The opt-in ready-runtime coordinator uses
--apply-mode materialize for a compatible warm runtime, not a legacy first
install. Its execution gate verifies source/build identity and complete native
artifacts before allocating cards. parity_watch.py continuously publishes
content changes with source-only; it never modifies running source or builds.
Only materialize after all executions on that binding have been released.
The watcher alone is not execution parity or model readiness.
The task-facing vaws_run tool performs the materialize step automatically
from its bound actual business worktrees before queueing the managed job.
Retrying an uncertain launch uses the same execution id and pinned snapshot;
it must not synchronize underneath a possibly running service. Stop/finish
that execution before starting another code revision.
Use this skill when
- a remote smoke, service launch, or benchmark is about to start
machine-managementalready proved direct local -> container SSH by key- the request depends on local committed, staged, unstaged, or untracked non-ignored files
- the user expects “run my current local workspace remotely” instead of “run the latest pushed branch remotely”
Do not use this skill when
- the task is ad-hoc remote verification (run one command, read a log, check remote state) with no dependency on local code changes — use
.remote-devremote.bash/remote.readdirectly; parity is never a prerequisite for that - the main task is adding or repairing a machine, SSH, or container bootstrap
- the task is generic fork / remote topology setup
- the task is ordinary local coding with no remote execution
- the runtime cannot yet accept direct key-based login
- the user only wants a Git commit, push, or PR
What ships with it
12 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.
- references/acceptance.md 13 KB
- references/behavior.md 16 KB
- references/command-recipes.md 10 KB
- scripts/common.py 12 KB runs code
- scripts/gc_runtime_cache.py 2.5 KB runs code
- scripts/install_consent.py 7.9 KB runs code
- scripts/parity_sync.py 11 KB runs code
- scripts/parity_watch.py 2.0 KB runs code
- scripts/remote_code_parity.py 100 KB runs code
- scripts/transport_benchmark.py 11 KB runs code
- tests/test_git_transport.py 17 KB runs code
- tests/test_sync_decisions.py 8.0 KB runs code
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 Changed · +29 lines fe7e295e9b52
- 2mo ago First seen · 309 lines · 72 tokens per session scan A 80a7fa0d2646
remote-code-parity is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 4,689 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.
remote-code-parity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| remote-code-paritymaoxx241/vllm-ascend-workspace | Skill | 36 | 2mo ago | MIT | A | 72 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |