From 3a5d9d5a944c7840fa47a21ef46471f962ce7482 Mon Sep 17 00:00:00 2001 From: joeyycli Date: Thu, 16 Jul 2026 18:10:27 +0000 Subject: [PATCH] Add: spend rails for autonomous agents --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 96562b7..042152e 100644 --- a/README.md +++ b/README.md @@ -59,6 +59,7 @@ Generic agent tooling is out of scope unless the page directly covers harness de - [Humans and Agents in Software Engineering Loops](https://martinfowler.com/articles/exploring-gen-ai/humans-and-agents.html) - A clear mental model for where humans should strengthen the harness instead of micromanaging every artifact. - [Claude Code: Best practices for agentic coding](https://code.claude.com/docs) - Anthropic's practical recommendations for repo structure, checkpoints, validation, and delegation in agentic coding workflows. - [Lurkr](https://github.com/agentveil-protocol/lurkr) - Static scanner that runs in CI before deploy to surface AI-agent capability risks, including shadow capabilities, credentials into LLM context, eval/subprocess in `@tool`, direct prompt interpolation, and unverified MCP endpoints. +- [Spend rails for autonomous agents: a number, not a vibe](https://joeyycli.github.io/agent-ops-kit-guide/docs/spend-rails-for-autonomous-agents.html) - A concrete pattern for giving a scheduled agent real purchasing authority without real risk: a per-transaction autonomy line, an escalation threshold, a hard lifetime ceiling, and a transaction ledger as the actual enforcement mechanism instead of relying on the model's judgment. ## Specs, Agent Files & Workflow Design