Who it is forA team lead who wants evidence from real agent traffic before switching a gateway from shadow to enforcement.
The problemTurning on enforcement without data risks blocking legitimate work, and leaving it off leaves the target exposed.
The outcomeA shadow report by action showing what enforcement would have held or refused, and how many of those the upstream accepted as sent.
What you need first
- A terminal on macOS or Linux, with Homebrew, a Linux package, Docker or Helm available
- An HTTP API or tool endpoint you want the gateway to sit in front of, or the local demo target on localhost:3000
- Optional: a Decionis key from `agentsafe login`, if you want decisions from the Decionis control plane instead of the local demo authority
Steps
- Install AgentSafe with Homebrew:
brew tap decionis/agent-safe https://github.com/decionis/agent-safe-pipeline && brew trust decionis/agent-safe && brew install agentsafe - Start the gateway in shadow mode in front of your agent's API:
agentsafe proxy --upstream <your-api-url> --mode shadow(inferred, check the README) - Let the agent run its normal workload through the gateway for a representative period.
- Read the shadow report:
agentsafe status - Review the held and refused actions by type, then decide whether to switch to enforcement mode.
Prompt for your agent
Using the decionis/agent-safe-pipeline repository, install AgentSafe and run it in shadow mode in front of <your-api-url>. After the agent has run its normal tasks, run `agentsafe status` and summarize what enforcement would have held or refused, by action. Verify that the shadow report reflects requests the agent actually sent before recommending enforcement.
Caveat. Shadow results depend on the authority in use; with no Decionis key the report comes from a local demo policy, not your organization's real policy.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page