Unverified50% confidenceDecision RuleExact time
Under the Confirm before run policy, read-only commands execute directly, change-type commands require confirmation, and high-risk commands require secondary confirmation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedThe /plan command first restates the requirements, assesses risks, and breaks out a step-by-step plan, then stops to wait for confirmation and writes no code before confirmation is received.77% similarUnverifiedTo verify whether a rule is in effect, switch to manual mode in a practice copy, temporarily add a prompt rule for the same command, then have it check the repository status; a confirmation dialog is expected to appear (because prompt takes priority over allow)74% similarUnverifiedThe article distinguishes advisory instructions from deterministic instructions: prompts or CLAUDE.md content are still part of the model's input and can be ignored, whereas hooks, CI checks, and branch protection rules execute outside the model and are guaranteed to trigger.71% similarUnverifiedThe industry-standard practice is progressive authorization: first run in read-only or per-item confirmation mode for several weeks, and after confirming the agent is stable and reliable on specific tasks, open auto-approve only for a single, reversible command type with no side effects, rather than a global switch.70% similarUnverifiedCommand-level risk identification should perform semantic analysis before command execution to detect high-risk patterns such as DROP TABLE and rm -rf and automatically block them.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074172API
curl https://kongchang.com/api/v1/knowledge/claims/1074172MCP
get_claim(id=1074172)