vllm-ascend-workspace: Skill for Codex

.agents/skills/vllm-ascend-change-validation/SKILL.md

vllm-ascend-change-validation is a skill for Codex from maoxx241/vllm-ascend-workspace. It costs 104 tokens per session (653 once invoked), scanned A, original, MIT.

A validation planner for changes to vLLM and vllm-ascend, software used to serve machine-learning models. It maps changed components to the tests and evidence needed for a release-ready report.

In plain words
What is it for?
Use it to analyze a workspace diff, create a validation plan, connect results to plan items, and produce a pull-request validation report.
Why use it?
It helps determine which correctness, build, performance, graph, operator, distributed, and profiling checks are needed after a code change.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is maoxx241/vllm-ascend-workspace's own configuration. It tells Codex how to work on vllm-ascend-workspace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vllm-ascend-workspace configures →

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/vllm-ascend-change-validation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspace

Made for: 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.

agentmods badge for vllm-ascend-change-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation/github.svg)](https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation)
Your own site
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation/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.

agentmods 80×15 button for vllm-ascend-change-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-change-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.00653
Opus 5 $0.00052 $0.00327
Sonnet 5 $0.00021 $0.00131
Haiku 4.5 $0.00010 $0.00065

Measured 12d ago against content hash 73216472dcd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vllm-ascend-change-validation 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/change_validation.py, tests/test_change_validation.py), 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/vllm-ascend-change-validation/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vLLM Ascend Change Validation

Use this Skill as the validation planner and evidence aggregator for a code change.

Workflow

  1. Obtain the exact baseline and candidate diff, including relevant untracked files.
  2. Run scripts/change_validation.py plan.
  3. Review impact-analysis.json and validation-plan.json; correct false-positive or missing mappings before consuming NPU resources.
  4. Execute required items with the owning Skill:
    • correctness evidence: vllm-ascend-correctness-validation;
    • eager-pass/graph-fail diagnosis: vllm-ascend-graph-debug;
    • service lifecycle: vllm-ascend-serving;
    • benchmark and profiling evidence: their dedicated Skills;
    • distributed, operator, or performance workflows when those Skills are available.
  5. Link each downstream Run Manifest with the plan item IDs it covers.
  6. Run finalize.
  7. Deliver pr-validation-report.md with explicit missing and recommended coverage.

The planner defaults to the versioned rules in references/validation-rules.yaml, so the Skill remains functional when the formal workspace knowledge store is empty. Use --knowledge PATH to supply a reviewed workspace-specific rule set. Missing matches produce a generic targeted smoke plus manual-review flag; they never imply that no validation is needed.

Entry point

scripts/change_validation.py provides:

  • plan: collect or read a unified diff, classify impact, write a validation plan, and create a parent Run Manifest;
  • link: associate a downstream Run Manifest with one or more plan items;
  • finalize: assess required coverage and child statuses, then generate the final PR report.

Read:

Rules

  • Keep the reason and source rule for every plan item.
  • Distinguish required and recommended; resource constraints do not silently downgrade required evidence.
  • Treat child failed as failed, child non-terminal/inconclusive or missing required coverage as inconclusive.
  • A passed parent requires every required item to be covered by at least one passed child run.
  • Record unsupported, unknown, and intentionally omitted combinations under known limitations.
  • Do not duplicate Serving, correctness, Benchmark, Profiling, graph-debug, distributed-debug, or operator-debug implementation.
  • Keep run state under .vaws-local/change-validation/.

Read the full file on GitHub · 54 lines

Files

What ships with it

7 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.

  1. 12d ago First seen · 54 lines · 104 tokens per session scan A 73216472dcd0

Subscribe to this mod's changes

vllm-ascend-change-validation is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 8d ago), licensed MIT. It adds 104 tokens to every session and 653 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 2026-08-30.

Related

Other skills, from other repositories

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

diegosouzapw/OmniRoute · 34 tokens

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…

davila7/claude-code-templates · 73 tokens

merger-model

Build accretion/dilution analysis for M&A transactions. Models pro forma EPS impact, synergy sensitivities, and purchase price allocation. Use when evaluating a potential acquisition, preparing merger consequences analysis for a pitch, or advising on deal terms. Triggers on "merger model", "accretion dilution", "M&A…

anthropics/financial-services · 87 tokens

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

NousResearch/hermes-agent · 22 tokens

validate

Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.

semantica-agi/semantica · 0 tokens

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…

NVIDIA/Model-Optimizer · 115 tokens