From nexus-agents
Runs system reviews triggered by low open issues, epic closures, or 7-day intervals. Checks registry reconciliation, documentation sync, and issue health using GitHub CLI.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nexus-agents:system-reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run when ANY occur:
Run when ANY occur:
epic)# Count techniques by status
grep -c "status: implemented" docs/research/registry/techniques.yaml
grep -c "status: planned" docs/research/registry/techniques.yaml
# Verify RESEARCH_INDEX.md matches actual counts
# Check integration_files exist for implemented techniques
gh issue list --state open --limit 50
wontfix label)Create GitHub issue titled "System Review: YYYY-MM-DD" with findings and action items.
TZ='America/New_York' date '+%Y-%m-%d'
gh issue create --title "System Review: $(TZ='America/New_York' date '+%Y-%m-%d')" \
--label "maintenance" --body "## Findings\n\n[report here]"
| Excuse | Counter |
|---|---|
| "Skip the review, I just looked at this last week" | A week is enough for new alerts, dep advisories, and CI flakes. Run all phases. |
| "No new issues, the review is wasted time" | The review's value isn't in finding new issues — it's in confirming the system isn't drifting silently. Empty reviews are good signal. |
| "I'll skip Phase X, it's never useful" | If a phase is never useful, file an issue to remove it. Don't silently skip — the next reviewer will skip a different phase. |
npx claudepluginhub nexus-substrate/nexus-agentsOrchestrates an autonomous comprehensive review pipeline across health, architecture, security, performance, accessibility, tests, and release-readiness. Supports optional ticket creation for backlog or audit.
Orchestrates periodic repository review cycles by dispatching findings to specialized reviewers, aggregating results, and escalating via reports, issues, or corrective PRs.
Performs cross-cutting reviews of recent git changes via logs, diffs, and automated Python scans, catching specialist gaps in security, performance, observability, data integrity, infrastructure, CI/CD, and consistency.