← All skills
guardrail-smart-accounts
95 / 100 · Low risk
Fine to try.
By LeoYeAI/agent-master-skills (GitHub) · coding · 2,186 stars · scanned at commit 8f88f9a
Give AI agents on-chain spending guardrails. Deploy ERC-4337 smart accounts with policy-enforced limits — agents cannot move funds beyond what you authorize, enforced at the contract level, not just in software.
Works with any agent that supports SKILL.md skills.
What this skill can do
Connects to the internet
The author does not mention this.
Found in 16 places.
Show 13 more
- skills/guardrail-smart-accounts/SKILL.md, line 371
await fetch(`${apiUrl}/api/v1/policies/${policyId}`, { method: "PUT", headers, body: JSON.stringify({...}) }); - skills/guardrail-smart-accounts/SKILL.md, line 374
await fetch(`${apiUrl}/api/v1/policies/${policyId}/revoke`, { method: "POST", headers }); - skills/guardrail-smart-accounts/SKILL.md, line 377
await fetch(`${apiUrl}/api/v1/policies/${policyId}/reactivate`, { method: "POST", headers }); - skills/guardrail-smart-accounts/SKILL.md, line 380
await fetch(`${apiUrl}/api/v1/policies`, { headers }); - skills/guardrail-smart-accounts/SKILL.md, line 381
await fetch(`${apiUrl}/api/v1/policies/${policyId}`, { headers }); - skills/guardrail-smart-accounts/SKILL.md, line 382
await fetch(`${apiUrl}/api/v1/policies/${policyId}`, { method: "DELETE", headers }); - skills/guardrail-smart-accounts/SKILL.md, line 419
const permission = await fetch(`${apiUrl}/api/v1/permissions`, { - skills/guardrail-smart-accounts/SKILL.md, line 431
const minted = await fetch(`${apiUrl}/api/v1/permissions/${permission.id}/mint`, { - skills/guardrail-smart-accounts/SKILL.md, line 438
await fetch(`${apiUrl}/api/v1/permissions/${permission.id}`, { method: "DELETE", headers }); - skills/guardrail-smart-accounts/SKILL.md, line 441
await fetch(`${apiUrl}/api/v1/permissions?agent_id=${agentId}`, { headers }); - skills/guardrail-smart-accounts/SKILL.md, line 460
const result = await fetch(`${apiUrl}/api/v1/validate`, { - skills/guardrail-smart-accounts/SKILL.md, line 489
const sim = await fetch(`${apiUrl}/api/v1/validate/simulate`, { - skills/guardrail-smart-accounts/SKILL.md, line 532
const logs = await fetch(
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'guardrail-smart-accounts' ] || [ -L ~/.agents/skills/'guardrail-smart-accounts' ]; then echo 'A skill folder named guardrail-smart-accounts already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/LeoYeAI/agent-master-skills' "$d" && git -C "$d" checkout --quiet '8f88f9a0dd5a1075d4f0c7626f9d960844d57575' -- 'skills/guardrail-smart-accounts' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/guardrail-smart-accounts' ~/.agents/skills/'guardrail-smart-accounts' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'guardrail-smart-accounts' ~/.claude/skills/'guardrail-smart-accounts' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for LeoYeAI/agent-master-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/LeoYeAI/agent-master-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | 8f88f9a | 95 |
| 2026-11-07 | 8f88f9a | 100 |