Silence all Hermes agent tool progress output. Stop agents from exposing internal tool calls, paths, commands, and iteration details to the user.
npx skills add crazycompanyinc/hermes-silent-agentsSilence all Hermes agent tool progress output. Stop agents from exposing internal tool calls, paths, commands, and iteration details to the user.
Source: https://github.com/crazycompanyinc/hermes-silent-agents
Discovered from GitHub repositories pushed in the last 24 hours for agent skills, Claude/Codex/Gemini workflows, MCP tooling, and adjacent AI-agent automation.
A Claude Code skill for keeping long-running sessions under 30% context spend through architectural patterns. Patterns extracted from hacker-bob's autonomous bug bounty agent (1+ hour run at 12% main thread spend).
只适合作为 GPT-5.5 的主代理技能使用，用于把 GPT-5.5 主代理锁定为“顾问 / 调度 / 验收”角色，并统一 GPT-5.x 子代理的边界、证据、返工和验收规则。
Codex Skills
bro-skills - Spec-Driven Development CLI
Codex skill for human-approved cross-review with external AI reviewers
Terraform & OpenTofu Skill for AI Agents - testing, modules, CI/CD, and production patterns