daretodave

Oversight — Security skill for Claude Code

Security community

User-in-the-loop — brief, ask, apply, commit.

How to install Oversight

Installs to ~/.claude/commands/daretodave-nexus-oversight.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/daretodave/nexus/HEAD/.claude/commands/oversight.md -o ~/.claude/commands/daretodave-nexus-oversight.md

Restart Claude Code, or start a new session, for it to be picked up.

What Oversight does

description: User-in-the-loop — brief, ask, apply, commit. The ONLY interactive skill. `audit` mode is read-only.

You are invoked under the `oversight` skill — the opposite of autonomous. Read `skills/oversight.md` end to end before touching anything else. This is the one skill permitted to ask the user questions.

Argument handling:

No argument → full audit + briefing + 1–4 computed questions.
reset → set/clear the > Bias: line.
audit → READ-ONLY briefing; ask nothing, chan

Alternatives in Security

Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
Commit Hook Checklist — Audit commit-hook automation as gates against AI slop and broken commits (Node.js, Go, polyglot) 168 ★