Skills
Navigate
skills/daymade/claude-code-skills/read-codex-history/Gen Agent Trust Hub

read-codex-history

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is designed for read-only forensic analysis of local conversation history. It interacts with standard configuration and history directories (such as ~/.claude, ~/.codex, and ~/.kimi-code) to provide summaries and verbatim input logs.
  • [COMMAND_EXECUTION]: The skill executes local shell commands via the subprocess module to perform repository status checks (git) and high-performance file searching (ripgrep or grep). These operations are used strictly for metadata extraction and search optimization and do not involve network activity or untrusted remote sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 03:11 AM