Genlayer Agent Playbook — Security skill for Claude Code
Agent-ready GenLayer builder playbook: confirmed GenVM nondet bug catalog, contract skeletons, direct-mode test template, audit scripts, portal acceptance/rejection lessons, and build checklists.
How to install Genlayer Agent Playbook
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Siriron/genlayer-agent-playbook and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Genlayer Agent Playbook does
Agent-ready GenLayer builder playbook: confirmed GenVM nondet bug catalog, contract skeletons, direct-mode test template, audit scripts, portal acceptance/rejection lessons, and build checklists.
Alternatives in Security
- Goal Prompt Builder — Build audit-friendly /goal prompts for OpenAI Codex 225 ★
- Openclaw Ops — OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans 225 ★
- Public Skills Builder — Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no 155 ★
README
GenLayer Agent Playbook
Everything a coding agent needs to build, test, audit, and submit GenLayer projects without relearning it.
    
**[Agent manual](./AGENTS.md)** · **[Knowledge index](./docs/INDEX.md)** · **[Templates](./templates/)** · **[Audit scripts](./scripts/)**
What this is
A production-grade knowledge base for building on [GenLayer](https://genlayer.com): Python intelligent contracts on GenVM, React + Vite frontends, and portal submissions. It distills a full build history, every confirmed GenVM runtime bug with its fix, the evidence-binding rules that survived staff review, and the exact reasons real submissions were accepted or rejected.
Point a coding agent at this repository and it starts from the settled answers instead of rediscovering each failure live.
| For | Coding agents (Claude Code, Cursor, Copilot, Codex, Gemini) and the builders directing them |
| Entry point | `AGENTS.md` (mirrored as `CLAUDE.md`) |
| Covers | Ethics gate, concept evaluation, contract rules, 12-bug nondet catalog, frontend SDK, checklists, portal rules, review lessons |
| Ships | 2 contract skeletons, a direct-mode test suite template, README template, 3 audit/limit scripts |
| Target | GenLayer StudioNet only |
How an agent should use it
- Load `AGENTS.md` as the standing instruction file.
- Fo
Related Skills
Sail Skill
SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, secur
Docsmith Fix Loop
Fix a confirmed docsmith skill/template/script finding, prove the fix with an eval + audit, and — only if it p
Store Check
Read-only pre-submission audit covering iOS privacy manifest and usage strings, Play data safety, permissions,
Spec Check
Audit GWT acceptance test specs for implementation leakage. Optionally provide a specific file path.
Owasp Security
OWASP Top 10:2025, ASVS 5.0, and Agentic AI security (2026) with code review checklists, secure patterns, and
Carryforward
Extract lessons learned, update CONSIDERATIONS.md, and maintain SECURITY-COMPLIANCE.md between phases
Related Agents
Finance F4 Cashflow
Finance F4 - daily cash sheet and 13-week outlook. Opening bank, confirmed receipts, supplier outflows coloure
Tester Executor
Explicit-invocation only (Team Tester, Executor) — dispatched by the Manager to write ABAP Unit test class ske
Raw Data Downloader
Downloads raw data files for a Data Basis dataset from the source URL(s). Handles diverse download mechanisms