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 claude-dev-suite/claude-dev-suite --skill hwigit clone --depth 1 https://github.com/claude-dev-suite/claude-dev-suiteWrote 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/claude-dev-suite/claude-dev-suite/hwi)<a href="https://agentmods.dev/skills/claude-dev-suite/claude-dev-suite/hwi"><img src="https://agentmods.dev/badge/skills/claude-dev-suite/claude-dev-suite/hwi/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/claude-dev-suite/claude-dev-suite/hwi"><img src="https://agentmods.dev/badge/skills/claude-dev-suite/claude-dev-suite/hwi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00817 |
| Opus 5 | $0.00036 | $0.00409 |
| Sonnet 5 | $0.00014 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
bitcoin-hardware-hwi 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HWI (Hardware Wallet Interface)
Python library + CLI for vendor-agnostic HW wallet operations.
Maintained by Bitcoin Core team (bitcoin-core/HWI).
Why HWI
Each HW vendor has its own protocol (Trezor's, Ledger's BOLOS, Coldcard's CKCC, BitBox02's, Jade's). HWI unifies them under one API:
enumerate— list connected devices.getmasterxpub/getxpub.displayaddress.signtx/signpsbt.signmessage.setupdevice,wipe, etc.
Supported vendors
- Trezor Model One, Model T, Safe 3, Safe 5.
- Ledger Nano S Plus, Nano X, Stax, Flex.
- Coldcard Mk4, Q.
- BitBox02 (Multi + Bitcoin-Only).
- Blockstream Jade.
- (Some legacy: KeepKey.)
CLI usage
# Detect devices
hwi enumerate
# Get xpub
hwi -t trezor getxpub "m/84'/0'/0'"
# Sign a PSBT
hwi -t coldcard signtx <psbt_base64>
# Display an address for verification
hwi -t ledger displayaddress --path "m/84'/0'/0'/0/0"
Python API
import hwilib.commands
devices = hwilib.commands.enumerate()
device = devices[0] # pick one
xpub = hwilib.commands.getxpub(device, "m/84'/0'/0'")
signed_psbt = hwilib.commands.signtx(device, base64_psbt)
Integration in Bitcoin Core
Bitcoin Core's external-signer interface uses HWI:
bitcoin-cli -rpcwallet=hot \
-named externalsigner_setup \
command="hwi --chain main"
# Now wallet RPC funded via external signer
bitcoin-cli -rpcwallet=hot getnewaddress
# Generates address; user verifies on device.
bitcoin-cli -rpcwallet=hot walletprocesspsbt <psbt>
# Calls HWI to sign on device.
Multisig with multiple devices
HWI supports wallet policies for multisig:
- Build descriptor with all signers.
- For each device, register the wallet policy (HMAC-bound).
- Submit PSBT to HWI; iterate over devices, each signs partial.
Common issues
- Permissions: USB device permissions on Linux (udev rules required for hidraw / libusb).
- Vendor pin entry: some devices ask for PIN via screen; HWI blocks until user inputs.
- Wallet policy not registered for multisig → device rejects.
- Macros / scripts: passing PIN via env vars only for some vendors; secure handling required.
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.
- 5d ago First seen · 106 lines · 72 tokens per session scan A 141032f34280
bitcoin-hardware-hwi is a skill published in the GitHub repository claude-dev-suite/claude-dev-suite (31 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 817 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
ind
Industrial Designer for physical, hardware, connected-product, and physical-digital software experiences. Use for tangible product design, material honesty, product form, hardware/software touchpoints, lifecycle design, repairability, and Rams/Ive-style reduction before engineering or UI work.
chain-idx
Generate blockchain event indexing setup.
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…