jes adds one-command guardrails for Claude Code and Codex via agent hooks
EdenEmarco177 · x · 2026-10-02
The author shares a minimal way to add guardrails to coding agents: run uvx jes login and uvx jes claude-settings (swap to uvx jes codex-settings for Codex), then apply the generated hook settings to Claude Code. jes then inspects the agent's prompt, every tool call, tool result, and final reply, blocking risky ones — no code required. Docs also cover Hermes, OpenCode, and more. Checks run through a decision model on the TypeSafe API that returns probability verdicts rather than generated text; the library itself is Apache-2.0. A LangChain/LangGraph middleware integration example was published earlier.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16