audit-install-stateRead-only audit of `~/.claude` and `~/.claude.json`: the deep inventory of unmanaged files. Use when: 'what is in my ~/.claude', 'why is my Claude Code install so big', 'does Claude Code clean up after itself', 'check cleanupPeriodDays', 'is this lock file dead', 'tidy my Claude Code install'. Delet
audit-mod-postureRead-only audit of the mods this Claude Code can run: installed and built-in mods, their hooks and calls, and whether the built-in guard is seated. Use when: 'which mods run on my machine', 'mod posture', 'is the sec-default guard on', 'can a mod bypass my deny rules', 'audit my mods'. Never loads a
audit-native-overlapMap of where this repo's skills and agents duplicate a native Claude Code surface; read-only unless `apply` bakes an approved reference. Use when: 'does this skill duplicate a built-in', 'what does Claude Code already ship for this', 'is our install-state audit the same as /doctor', 'refresh the nat
audit-performanceSlowness diagnostic that never 'fixes', run before restarting or deleting: version, retention sweep, install bloat, hook/subagent fan-out, kernel-leak census. Use when: 'Claude Code is slow', 'typing lags', 'my machine freezes when Claude runs', 'why is this session sluggish', 'my hooks are slowing
audit-plugin-landscapeOn-demand, read-only report on which installed plugins and marketplaces have gone stale, which overlap, and what to adopt, adapt or drop. Use when: 'are my plugins stale', 'plugin landscape', 'which plugins overlap', 'is there a better alternative to this plugin', 'which marketplaces are dead'. Brin
audit-skill-visibilityWhen the built-in skill-doctor command resolves in this session, prefer it for cost; this skill for unseen ones. Use when: 'why do I never use most of my skills', 'why does Claude never suggest this skill', 'are my skill descriptions being dropped', 'is my skill listing over budget', 'which skills c
behavior-probesLive probes of Claude Code permission, auto-mode, hook, worktree, subagent and sandbox behavior as cases with paired controls, each reported pass, fail or inconclusive with the Claude Code version; dry run by default, live runs opt-in and capped. Use when: 'rerun the behavior probes', 'does auto mod
changelogClaude Code changelog ingestion into the current repo: fetch (read-only display), diff (impact analysis over a release range, no edits), status (read marker, default range, replay cap), and apply (one PR per owner plugin, larger decisions handed off as work items, explicit user intent only). Use whe
control-claude-codeControl skill /app-control:drive reads to run Claude Code's terminal UI with a plugin loaded and record screenshots, video and stream-json logs of its mods, skills, hooks and commands.
inventoryList of every Claude Code surface this machine can invoke: built-in commands, subagents, tools, bundled skills and workflows, and installed plugin components. Use when: 'what slash commands do I have', 'what agents are available', 'is /foo a real command', 'what changed after the update', 'what does
known-issuesLookup and tracking of known Claude product issues: GitHub bug search, service health and model quality checks, and a persistent registry of tracked issues. Use when: 'is this broken', 'any workarounds', 'troubleshoot Claude Code', 'feature behaves unexpectedly', 'scan repo for issues', 'file a bug'
lanesStart, restart, stop, and check loop lanes as named background Claude Code sessions seeded from canonical prompt files, the scripted replacement for the manual morning refresh (cancel loop, clear, re-paste the canonical prompt) across N lanes on a machine. `start`/`restart` first pull the repo and r
machine-profileRe-runnable profile of this machine's facts and identity domains, with drift between the stored profile and the host now; read-only unless the operator confirms a write, never installs, never reapplies a stored value on its own. Use when: 'profile this machine', 'what does this host have configured'
observabilityWhen the bundled explain-usage skill resolves in this session, prefer it for a plain-language breakdown of this session's tokens; this skill for cross-session reports from the local telemetry stores (OTEL DuckDB, hook event log, ccusage): token burn, cost, hook latency, per-session activity, usage p
plugins-auditRead-only dry run of /harness-ops:plugins sync: predicts the marketplace refreshes, updates, installs, enables and scope divergences sync or converge would act on, and issues none of those calls. Its update count is a lower bound against the unrefreshed catalog. Use when: 'are my plugins current', '
pluginsBring a machine's plugin fleet current on demand: marketplace refresh, update the plugins that actually load (including in-repo project/local-scope installs), install new catalog plugins per policy, detect scope divergence, and surface (never silently fix) drift, with a terse actionable report; refu
prerequisitesRead-only report of external tools the enabled plugin fleet declares, and which of them are missing. Use when a hook says a formatter or CLI is missing, or when asking whether this machine has what the enabled plugins need. Never installs.
setupVerify harness-ops's path configuration for this repository (where the known-issues registry resolves and which layer set it, and where the skill-usage log and the per-session hook event log resolve), check the self-ignoring guard on the hook log root, check that node and jq resolve for the hooks, d