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 sou350121/VLA-expert-skill --skill skillgit clone --depth 1 https://github.com/sou350121/VLA-expert-skillWrote 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/sou350121/vla-expert-skill/skill)<a href="https://agentmods.dev/skills/sou350121/vla-expert-skill/skill"><img src="https://agentmods.dev/badge/skills/sou350121/vla-expert-skill/skill/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/sou350121/vla-expert-skill/skill"><img src="https://agentmods.dev/badge/skills/sou350121/vla-expert-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 134 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.00748 |
| Opus 5.5 | $0.00023 | $0.00299 |
| Sonnet 5.5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
vla-expert 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 17d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VLA Expert
Answer the user's VLA question with evidence and a clear boundary between reported results, inference and advice. This module supplies domain knowledge; the user's task, local project rules and verification requirements still govern the work.
Find relevant evidence
- Read the header and coverage boundary in HANDBOOK_CURRENT.md. Its sync date describes a published repository snapshot, not a fresh review of every research claim.
- Search HANDBOOK_INDEX.md by method, company, paper title or topic. Read the linked, commit-pinned Handbook page relevant to the question. The complete index includes theory, companies, biweekly reports and deployment guides; it is not a paper ranking or an independent paper count.
- For metrics, model versions, releases or industry events, follow the page's primary sources and verify the requested version, date and conditions. If a local Handbook is available, verify its commit before treating it as this snapshot. A missing file or inaccessible source remains unverified.
The legacy memory is a historical snapshot. Its belief probabilities, phase percentages, predictions and valuation figures are historical opinions, not current calibrated facts. A newer index does not renew them. Use it for orientation only, then check the relevant source.
Scale the response to the question
- QUICK: answer a definition or concrete lookup briefly. Cite the source that actually supports it, and state missing evidence when needed.
- DEEP: compare mechanisms, assumptions, evaluation conditions and failure modes. Seek the strongest supporting and opposing evidence. Explain what could overturn a consequential judgment; do not force a debate or confidence score.
For VLA comparisons, distinguish action representation, action generation, training data, embodiment and evaluation protocol. Do not compare success rates from different tasks as a controlled ranking. Control frequency, policy inference rate and action-chunk execution rate are different quantities.
What ships with it
4 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.
- 17d ago Changed · -74 lines · -64 tokens per session 8ad6ce486bb5
- 2mo ago First seen · 142 lines · 122 tokens per session scan A 9156fcbf4398
vla-expert is a skill published in the GitHub repository sou350121/VLA-expert-skill (49 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 748 once invoked, about $0.0002 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.
vla-expert compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vla-expertsou350121/VLA-expert-skill | Skill | 49 | yesterday | MIT | A | 58 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |