Skill · /nio-report

/nio-report — recent execution audit.

Read the audit log and format the recent guard decisions plus a diagnostics summary.

Invoke: /nio-report (Claude Code) · $nio-report or natural language (Codex) · or via the umbrella /nio report on any platform (incl. OpenClaw / Hermes). See Focused skills.

report

Reads ~/.nio/audit.jsonl and formats the last 50 events as a table, plus a Diagnostics summary aggregated from up to 200 recent events. No arguments.

Event types

Each line is JSON with an event discriminator:

  • guard — one per tool-call evaluation: decision, risk_level, risk_score, per-phase scores, top findings.
  • session_scan — skill/plugin scans fired on session start.
  • lifecycle — subagent spawn/stop events (OpenClaw).
  • diagnostic — config / OAuth / LLM / external / collector / scanner failure; aggregated by (source, kind, component, config_path) in the report's Diagnostics section. See Diagnostics for the full reference.

Output

## Nio Execution Report

**Events**: <count>
**Blocked**: <deny count>
**Confirmed**: <confirm count>

### Recent Events

| Time | Tool | Type | Decision | Risk | Score | Phase | Top Finding |
|------|------|------|----------|------|-------|-------|-------------|
| 14:30 | Bash | exec | DENY | critical | 0.95 | 2 | DANGEROUS_COMMAND |

### Pipeline Stats
| Phase | Invocations | Avg Score | Avg Duration |
| ... 

If ~/.nio/audit.jsonl doesn't exist yet, the skill tells you no events are recorded and suggests enabling hooks via setup.sh.