Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/decionis/agent-safe-pipeline && cp agent-safe-pipeline/*.md ~/.claude/agents/Subagents overview
What people ask about agent-safe-pipeline
What is decionis/agent-safe-pipeline?
+
decionis/agent-safe-pipeline is subagents for the Claude AI ecosystem. Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant. It has 532 GitHub stars and its last recorded update is dated 2026-09-10.
How do I install agent-safe-pipeline?
+
You can install agent-safe-pipeline by cloning the repository (https://github.com/decionis/agent-safe-pipeline) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is decionis/agent-safe-pipeline safe to use?
+
Our security agent has analyzed decionis/agent-safe-pipeline and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains decionis/agent-safe-pipeline?
+
decionis/agent-safe-pipeline is maintained by decionis. The last recorded GitHub activity is dated 2026-09-10, with 13 open issues.
Are there alternatives to agent-safe-pipeline?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy agent-safe-pipeline to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/decionis-agent-safe-pipeline)<a href="https://claudewave.com/repo/decionis-agent-safe-pipeline"><img src="https://claudewave.com/api/badge/decionis-agent-safe-pipeline" alt="Featured on ClaudeWave: decionis/agent-safe-pipeline" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.