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 hiromaily/go-crypto-wallet --skill knowledge-gapgit clone --depth 1 https://github.com/hiromaily/go-crypto-walletWrote 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/hiromaily/go-crypto-wallet/knowledge-gap)<a href="https://agentmods.dev/skills/hiromaily/go-crypto-wallet/knowledge-gap"><img src="https://agentmods.dev/badge/skills/hiromaily/go-crypto-wallet/knowledge-gap/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/hiromaily/go-crypto-wallet/knowledge-gap"><img src="https://agentmods.dev/badge/skills/hiromaily/go-crypto-wallet/knowledge-gap.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 | $0.00015 | $0.00740 |
| Opus 5 | $0.00008 | $0.00370 |
| Sonnet 5 | $0.00003 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
knowledge-gap 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Gap Review
Run this after completing a task to identify issues in information retrieval and propose candidates for improving skills/rules.
Purpose
A skill for AI-assisted development that helps verbalize project-specific tacit knowledge and continuously improve the knowledge base.
When to Use
- During self-review after completing a task
- When you felt unsure during implementation
- When you had to repeatedly refer to existing code
Review Process
Step 1: Reflection Perspectives
Review the most recent task from the following perspectives:
-
Items that took time to research
- Information that required three or more tool calls to find
- Implicit patterns understood by referencing multiple parts of existing code
- Areas where you had to proceed by guessing because documentation was not found
-
Items where decisions were difficult
- Cases with multiple possible implementation approaches
- Situations where you checked existing patterns for error codes or naming conventions
- Parts where you were not confident whether your choice was correct
-
Information missing from existing skills/rules
- Cases where you referenced a skill but the required information was missing
- Mistakes or rework that could have been avoided if a rule had existed
Step 2: Classify the Issues
Classify the identified issues based on the following criteria:
| Difficulty | Criteria |
|---|---|
| High | Took more than 10 minutes / required multiple files |
| Medium | Took 5–10 minutes / referenced 1–2 existing files |
| Low | Less than 5 minutes / easy to find but worth recording |
Step 3: Propose Where to Maintain Them
Propose the appropriate destination based on the nature of each issue:
| Destination | Suitable Cases |
|---|---|
.claude/skills/ |
Knowledge referenced during specific tasks (invoked by command) |
.claude/rules/ |
Rules that should always be applied (auto-loaded) |
CLAUDE.md |
Project-wide principles and architecture |
| Update existing file | Can be handled by extending an existing skill/rule |
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 · 115 lines · 15 tokens per session scan A 5159d99322cb
knowledge-gap is a skill published in the GitHub repository hiromaily/go-crypto-wallet (127 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 740 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
agent-wallet
Operate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet…
agent-solidity
Write, audit and deploy Solidity smart contracts through a gated multi-step workflow (spec, threat model, design, implementation, in-process EVM proof, security audit, deployment), with a local EVM sandbox that needs no Foundry, Hardhat, anvil, node or funds. Trigger on Solidity, smart contract, .sol, ERC-20, ERC-721…
pqc-scan
Inventory the cryptography in a codebase that a quantum computer would break, and report what the scan could not read. Use when asked about post-quantum readiness, cryptographic inventory, a CBOM, or which algorithms a project signs with.
bytesagain-wallet-tracker
Crypto wallet analytics reference — address formats, on-chain analytics, transaction tracing, hardware wallets, and approval revocation.
agent-wallet
Operate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet…
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.