Bankml
bankml (github.com/cryptoAGI/bankml, local ~/cryptoAGI/bankml) — the zero-dependency Rust runtime for 1-bit (Q1_0) and ternary (Q2_0_g64) GGUF models, bit-exact against llama.cpp b11192, with `bankml serve` (a verifying loopback gateway that pins the model by sha256 and puts a receipt on every answer) and the Savante UI (interact on 127.0.0.1:7873, view on the LAN at :7874). Use when working on bankml's kernels, oracles, release gate, serve/receipts, the model importer, the Savante UI (chat, .history/.memory, Merkle commitments, agents, THOT, PostgreSQL, iNFT, voice, embeddings), cutting a release, or measuring speed. Triggers "bankml", "bankml serve", "Q1_0", "Q2_0", "Bonsai", "release gate", "oracle", "receipt", "Savante UI", "savante.py", "view.py", "models.py", "speak.py", "console.py", "serve --native", "Ollama API", "JSON schema", "logprobs", "slot".
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
Verified low-bit inference for the CPU you already have. A Rust runtime with no crates: its own GGUF guard, sha256 pin, AVX2 kernels for ggml's Q1_0 (1.125 bits per weight) and Q2_0_g64 (ternary, 2.25 bpw) that are bit-exact against the compiled llama.cpp b11192 libraries, a thread pool, its own forward pass (Qwen3 and Llama graphs; Q1_0, Q2_0_g64 and F16 weights; token-identical to llama.cpp), and bankml serve, which answers behind that gate — through llama-server, or with --native from bankML's own forward pass. Authors: Professor Codephreak and Gregory L. Magnusson (cryptoAGI). Licence:…
What this skill does
Bankml is a community-contributed Claude Code skill in the network-security sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/bankml/ and loads when your prompt matches the skill's trigger.
When to invoke it: Use when working on bankml's kernels, oracles, release gate, serve/receipts, the model importer, the Savante UI (chat, .history/.
Who uses this skill
The Bankml Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 206,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/bankml
curl -L https://claudskills.com/skills/bankml/SKILL.md \
-o ~/.claude/skills/bankml/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/bankml/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/bankml/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\bankml\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the Bankml Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/bankml/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the Bankml skill do?
bankml (github.com/cryptoAGI/bankml, local ~/cryptoAGI/bankml) — the zero-dependency Rust runtime for 1-bit (Q1_0) and ternary (Q2_0_g64) GGUF models, bit-exact against llama.cpp b11192, with `bankml serve` (a verifying loopback gateway that pins the model by sha256 and puts a receipt on every answer) and the Savante UI (interact on 127.0.0.1:7873, view on the LAN at :7874). Use when working on bankml's kernels, oracles, release gate, serve/receipts, the model importer, the Savante UI (chat, .history/.memory, Merkle commitments, agents, THOT, PostgreSQL, iNFT, voice, embeddings), cutting a release, or measuring speed. Triggers "bankml", "bankml serve", "Q1_0", "Q2_0", "Bonsai", "release gate", "oracle", "receipt", "Savante UI", "savante.py", "view.py", "models.py", "speak.py", "console.py", "serve --native", "Ollama API", "JSON schema", "logprobs", "slot".
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Bankml skill?
Use Bankml when your Claude Code task falls under the Security category — specifically in the network security area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Bankml" or describe the task and let Claude pick). Browse related skills at
/category/security/.
What is a Claude Code skill and how does the Bankml skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Bankml is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at
/learn/what-is-a-claude-skill/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
cryptoAGI. (2026). Bankml [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/bankml/
BibTeX
@misc{bankml-2026,
author = {cryptoAGI},
title = {Bankml [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/bankml/}
}
Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/bankml/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/bankml.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/bankml.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Bankml"></iframe>
Security scan
Grade A · scanned 2026-10-11 — free static scan against the OWASP Agentic Skills Top 10.
The scan flagged 1 of 10 categories (network), including lower-severity patterns. Patterns shown inside code fences are weighted as examples rather than instructions — read the grading methodology for what this does and does not guarantee.
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ⚠ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/bankml/#security)
More Security skills
Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore