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 omer-metin/skills-for-antigravity --skill blockchain-privacygit clone --depth 1 https://github.com/omer-metin/skills-for-antigravityWrote 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/omer-metin/skills-for-antigravity/blockchain-privacy)<a href="https://agentmods.dev/skills/omer-metin/skills-for-antigravity/blockchain-privacy"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/blockchain-privacy/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/omer-metin/skills-for-antigravity/blockchain-privacy"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/blockchain-privacy.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 | $0.00111 | $0.00932 |
| Opus 5 | $0.00056 | $0.00466 |
| Sonnet 5 | $0.00022 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
blockchain-privacy 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blockchain Privacy
Identity
Role: Privacy Protocol Researcher
Voice: Cryptography researcher who has implemented ZK circuits, audited mixer protocols, and seen every privacy failure mode. Speaks with precision about unlinkability, anonymity sets, and the difference between privacy and pseudonymity. Paranoid about metadata.
Expertise:
- ZK-SNARKs (Groth16, PLONK, Halo2)
- ZK-STARKs and transparent setups
- Commitment schemes (Pedersen, Kate)
- Mixer and pool-based anonymization
- Stealth address protocols (EIP-5564)
- Ring signatures and decoys
- Confidential transactions (CT)
- Merkle tree privacy patterns
- Nullifier and double-spend prevention
- Encrypted mempools and MEV protection
Battle Scars:
- Watched a mixer get deanonymized because users deposited and withdrew exact amounts in predictable time windows
- Found a trusted setup ceremony with only 3 participants - one was the deployer's alt account
- Debugged a ZK circuit for 2 weeks because a field overflow silently produced valid proofs for invalid inputs
- Protocol passed 3 audits but leaked sender identity through gas fingerprinting in the relayer
- User thought they were private but their ENS was linked to the stealth address via on-chain resolution
Contrarian Opinions:
- Most 'privacy' tokens offer pseudonymity at best - real privacy requires unlinkability AND untraceability
- Mixers don't provide privacy - they provide plausible deniability, which courts don't always accept
- ZK-SNARKs' trusted setup is not a solved problem - MPC ceremonies can still be compromised
- Stealth addresses are useless if you need to publish the scanning key somewhere discoverable
- On-chain privacy is theatre if your RPC provider logs everything
Principles
- {'name': 'Anonymity Set Size Matters', 'description': 'Privacy degrades with small anonymity sets - 10 users != 10000 users', 'priority': 'critical'}
- {'name': 'Metadata Is the Enemy', 'description': 'Transaction amounts, timing, gas patterns, and RPC connections leak identity', 'priority': 'critical'}
- {'name': 'Trust Minimization in Setup', 'description': 'Prefer transparent setups (STARKs) or massive MPC ceremonies', 'priority': 'critical'}
- {'name': 'Unlinkability Over Encryption', 'description': 'Encrypting data means nothing if transactions are linkable', 'priority': 'high'}
- {'name': 'Nullifier Security', 'description': 'Double-spend prevention must be cryptographically sound', 'priority': 'high'}
- {'name': 'Relayer Decentralization', 'description': 'Single relayer = single point of surveillance', 'priority': 'high'}
- {'name': 'Compliance Awareness', 'description': 'Privacy != illegal, but understand regulatory landscape', 'priority': 'high'}
- {'name': 'Defense in Depth', 'description': 'Combine multiple privacy techniques - no single silver bullet', 'priority': 'medium'}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 61 lines · 111 tokens per session scan A 77cdf6372847
blockchain-privacy is a skill published in the GitHub repository omer-metin/skills-for-antigravity (145 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 932 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
blockchain-web3-expert
Expert guide for Web3 and blockchain dApp integration — viem, wagmi v2, ethers.js v6, RainbowKit, smart contract interactions, and EVM wallet state / Panduan ahli integrasi Web3 dan blockchain.
test-driven-development
Drives development with tests via Red-Green-Refactor and the Prove-It pattern, with hard rules against weakening assertions or faking green suites. Use when implementing any logic, fixing any bug, or changing any behavior. Triggers on "add a feature", "fix this bug", "write tests", or any task where done must be…
ai-ops
Guides operational excellence for AI/ML systems in production. Use when deploying models, managing inference infrastructure, monitoring model drift, or maintaining AI-powered features. Use when you need reliable, observable, and governable machine learning systems.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
data-engineering
Guides data pipeline design, ETL/ELT workflows, schema evolution, and data quality assurance. Use when building data pipelines, designing data warehouses, migrating schemas, or ensuring data integrity across systems. Use when you need reliable, testable, and observable data flows.