Borrowing it
Nothing to install: this file belongs to ssalevan/habiclient. 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/ssalevan/habiclient/main/.claude/skills/u64/SKILL.mdgit clone --depth 1 https://github.com/ssalevan/habiclientWrote 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/ssalevan/habiclient/u64)<a href="https://agentmods.dev/skills/ssalevan/habiclient/u64"><img src="https://agentmods.dev/badge/skills/ssalevan/habiclient/u64.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01867 |
| Opus 5 | $0.00000 | $0.00933 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade A, and why
u64 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 8d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultimate 64 Remote Debugging
Remote control and debug the Habitat C64 client running on Ultimate 64 hardware via REST API.
Usage
Use u64_tool.py in the project root to automate the U64. Write and run Python scripts that import U64Session.
Quick crash diagnosis
from u64_tool import U64Session
u = U64Session("192.168.1.158")
u.diagnose()
# CPU paused, key memory locations dumped
# Call u.resume() when done
Memory inspection
from u64_tool import U64Session
u = U64Session("192.168.1.158")
u.pause()
u.dump(0x0800, 0x40) # Hex+ASCII dump
u.disassemble(0x080D, 32) # 6502 disassembly
val = u.read_byte(0x0001) # Read single byte
word = u.read_word(0xFFFA) # Read 16-bit LE word
data = u.read_mem(0x0100, 256) # Read raw bytes
u.resume()
Memory writes
u.write_byte(0xD020, 0x02) # Set border color
u.write_bytes(0xFFFA, [0xFC, 0x01]) # Set NMI vector
Upload and boot CRT
u = U64Session("192.168.1.158")
u.upload_crt("Dist/Habitat.crt")
# U64 resets and boots from cartridge
Full Habitat boot (disk-based)
u = U64Session("192.168.1.158")
u.boot_habitat("steve")
# Mounts disks, resets, navigates launcher, waits for game
Screen reading
u.pause()
rows = u.read_screen() # All 25 rows as ASCII
row5 = u.read_screen(5) # Single row
u.dump_screen() # Print all rows
u.wait_for_screen_text("HABITAT", timeout=30) # Poll until text appears
u.resume()
Keystroke injection
u.inject_keys(0x0D) # Press Return
u.type_text("steve") # Type name + Return (auto-appended)
CLI Usage
python3 u64_tool.py 192.168.1.158 --diagnose # Full crash diagnostics
python3 u64_tool.py 192.168.1.158 --boot-state # Quick boot check
python3 u64_tool.py 192.168.1.158 --pause # Pause CPU
python3 u64_tool.py 192.168.1.158 --resume # Resume CPU
python3 u64_tool.py 192.168.1.158 --reset # Reset C64
python3 u64_tool.py 192.168.1.158 --dump 0800 40 # Dump memory (hex)
python3 u64_tool.py 192.168.1.158 --disasm 080D 20 # Disassemble (hex)
python3 u64_tool.py 192.168.1.158 --read 0001 # Read byte
python3 u64_tool.py 192.168.1.158 --write D020 02 # Write byte
python3 u64_tool.py 192.168.1.158 --screen # Dump screen text
python3 u64_tool.py 192.168.1.158 --crt Dist/Habitat.crt # Upload CRT
python3 u64_tool.py 192.168.1.158 --boot steve # Full boot sequence
python3 u64_tool.py 192.168.1.158 --check # Check game state
python3 u64_tool.py 192.168.1.158 --version # Firmware version
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.
- 8d ago First seen · 183 lines · 0 tokens per session scan A e28128613e4c
u64 is a skill published in the GitHub repository ssalevan/habiclient (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,867 tokens. 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.
Other skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when a device is unreachable, a user reports connectivity problems, an interface…