Notifications
Clear all
Topic starter
06/09/2026 6:21 pm
TL;DR: Claude Code’s move to auto mode shifts new sessions on Pro, Max, and Team plans away from per-action approval prompts, while Anthropic says humans approved 97% of prompts and classifier-based blocking caught 89% of dangerous commands in a controlled study, according to Arnica’s analysis. The governance problem is no longer just code review, but how to control AI coding agents that can act through tool calls faster than people can approve them.
NHIMG editorial — based on content published by Arnica: Arnica named in Gartner First Take on Claude Code's shift to automated permissions
By the numbers:
- Anthropic says 62% of users have bypassed permission prompts or clicked "don't ask again" on Bash.
Questions worth separating out
Q: What breaks when an AI agent can switch off its own approval prompts?
A: The approval control stops being a governance barrier and becomes a preference.
Q: Why do AI agents change access management requirements?
A: AI agents change access management because they can make runtime decisions, select tools, and continue actions without a human approving each step.
Q: How should teams govern AI-assisted development workflows that use coding agents?
A: Treat them as identity-governed execution paths, not just productivity tools.
Practitioner guidance
- Define agent permission boundaries before enabling auto mode Classify each AI coding agent by allowed tools, repositories, shells, and deployment actions, then block anything outside that scope by default.
- Build an inventory of agentic assets and delegated rules Track every AI coding agent, MCP connection, skill, and policy override in one place so review and revocation are possible across the environment.
- Shift from prompt review to policy enforcement Move high-risk operations such as code writes, destructive commands, and environment changes into pre-execution policy checks instead of relying on approval prompts.
What's in the full article
Arnica's full blog post covers the operational detail this post intentionally leaves for the source:
- Specific policy settings for Claude Code auto mode, including defaultMode and disableAutoMode management options.
- Arnica's source-side framing of agentic development lifecycle controls across source control and review workflows.
- Details on how agentic rules, AI SAST, and posture scanning are combined across enterprise development environments.
- Examples of how teams can inventory MCPs, skills, and agentic rules without relying on manual tracking.
👉 Read Arnica's analysis of Claude Code auto mode and AI coding agent permissions →
Claude Code auto mode: are approval prompts still enough for AI coding agents?
Explore further
06/09/2026 6:22 pm
Approval prompts are no longer a sufficient governance model for AI coding agents. The article shows a shift from human-in-the-loop approval to classifier-mediated action, which changes the control problem from review to policy enforcement. In IAM terms, the permission model now has to govern runtime behaviour, not just user intent. Practitioners should stop treating prompts as a control boundary and start treating them as an interaction artifact.
A question worth separating out:
Q: Should organisations treat AI coding agents as part of IAM and PAM governance?
A: Yes, when those agents can act on code, data, or tools in ways that affect production risk. Their permissions should be scoped, reviewed, and audited like other privileged systems, especially when they interact with sensitive routes, secrets, or regulated data. The governance question is who can let the agent act, and under what policy.
👉 Read our full editorial: Claude Code’s auto mode exposes the limits of approval-based governance
