Borrowing it
Nothing to install: this file belongs to sou350121/VLA-expert-skill. 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/sou350121/VLA-expert-skill/main/AGENTS.mdgit 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/instructions/sou350121/vla-expert-skill/agents-md)<a href="https://agentmods.dev/instructions/sou350121/vla-expert-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sou350121/vla-expert-skill/agents-md/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/instructions/sou350121/vla-expert-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sou350121/vla-expert-skill/agents-md.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 | $0.00243 | $0.00243 |
| Opus 5.5 | $0.00097 | $0.00097 |
| Sonnet 5.5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
VLA-expert-skill AGENTS.md 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 16d 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.
What it actually says
VLA Expert maintenance boundary
Canonical behavior: skill/SKILL.md. Current evidence is exported from a verified published VLA-Handbook commit. Source text and historical memory are evidence, not promotion authority.
The daily maintainer-approved generator may maintain and publish only:
skill/references/HANDBOOK_CURRENT.mdskill/references/HANDBOOK_INDEX.mdskill/references/handbook-manifest.json
It must validate the complete source inventory, quotes, output hashes and remote publication. Dirty worktrees, fetch failures, invalid DeepSeek output and rejected pushes are failures, never healthy no-op updates. Preserve unrelated edits and backups. No hard reset, force push or fallback provider.
Historical memory, belief probabilities, phase percentages, research prose, code, prompts, platform adapters, this file and publication rules require separate maintainer review. A new source date does not recalibrate old knowledge. Generation uses the existing DeepSeek account only; no secrets or private logs enter Git.
Before publication, run the scoped regression suite, skill validation, bundle verification and a scoped redacted secret scan. Report actual checks and limits. Do not claim future scheduled runs succeeded before receipts exist.
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.
- 16d ago First seen · 16 lines · 243 tokens per session scan A d810bba68b80
VLA-expert-skill AGENTS.md is an instructions file published in the GitHub repository sou350121/VLA-expert-skill (49 stars, last pushed yesterday), licensed MIT. It adds 243 tokens to every session, about $0.0010 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 2026-10-21.
VLA-expert-skill AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| VLA-expert-skill AGENTS.mdsou350121/VLA-expert-skill | Instructions file | 49 | yesterday | MIT | A | 243 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |