health-check

/health:check

Single entry point for Claude Code health diagnostics. Runs environment checks (plugin registry, settings, hooks, MCP servers, SessionStart executability, pre-commit validity, permissions coverage, marketplace enrollment) plus optional deeper audits, and routes --fix to the appropriate internal workflow.

When to Use This Skill

Context

• Current project: !pwd
• Project settings exists: !find . -maxdepth 2 -path '*/.claude/settings.json'
• Local settings exists: !find . -maxdepth 2 -path '*/.claude/settings.local.json'

Parameters

Parse these from $ARGUMENTS:

Scope semantics:

Execution

Execute this diagnostic router. Default scope is all when --scope is not provided.

Step 1: Run environment checks (always)

Environment checks run regardless of --scope. They cover the baseline health of the Claude Code installation and the current project's .claude/ directory.

1a. Core environment scripts

bash "${CLAUDE_SKILL_DIR}/scripts/check-plugins.sh" --home-dir "$HOME" --project-dir "$(pwd)"
bash "${CLAUDE_SKILL_DIR}/scripts/check-settings.sh" --home-dir "$HOME" --project-dir "$(pwd)"
bash "${CLAUDE_SKILL_DIR}/scripts/check-hooks.sh" --home-dir "$HOME" --project-dir "$(pwd)"
bash "${CLAUDE_SKILL_DIR}/scripts/check-mcp.sh" --home-dir "$HOME" --project-dir "$(pwd)"

Parse STATUS= and ISSUES: from each. Pass --verbose when set on $ARGUMENTS.

If check-settings.sh emits PROJECT_DIR_RESOLVED=<path>, the workspace root had no .claude/ but a single nested */.claude/settings.json was found one level down (parent-workspace / monorepo layout). Note the resolved path in the report so the user knows which config was checked. If it emits PROJECT_DIR_HINT=<msg>, surface the hint — multiple nested configs were found and the user should re-run with --project-dir to target one.

1b. SessionStart smoke test

Check whether scripts/install_pkgs.sh (or any script registered in the SessionStart hook in .claude/settings.json) is executable and exits cleanly in both remote and local contexts.

1. Locate the SessionStart hook command from .claude/settings.json (look for the command field).
2. If a script is found, run:

   CLAUDE_CODE_REMOTE=true bash <script-path>
   

   Capture exit code. Expected: 0.
3. Run again to verify idempotency — expected: 0.
4. Run with remote guard off:

   CLAUDE_CODE_REMOTE=false bash <script-path>
   

   Expected: 0 (typically a no-op).
5. Report:
   • OK: All three exit 0
   • WARN: Script exists but is not registered in settings.json hook
   • ERROR: Script exits non-zero, or script referenced in hook does not exist

1c. Pre-commit config validator

If .pre-commit-config.yaml exists:

pre-commit validate-config .pre-commit-config.yaml

Report:

• OK: exits 0 (config is valid)
• WARN: pre-commit not installed — skip check, suggest pip install pre-commit
• ERROR: exits non-zero — show validation error

1d. Permissions coverage check

Compare tools referenced in project files against permissions.allow in .claude/settings.json.

1. Read permissions.allow from .claude/settings.json. Extract the command prefix from each Bash(<prefix>:*) entry.
2. Scan these files for tool invocations:
   • justfile / Justfile — commands on recipe lines
   • Makefile — shell commands on recipe lines
   • .pre-commit-config.yaml — entry: fields
3. For each tool found in project files:
   • Flag as MISSING if no matching Bash(<tool>:*) entry exists in permissions.allow
4. For each Bash(<tool>:*) entry in permissions.allow:
   • Flag as UNUSED if the tool is not found in any project file (informational, not an error)

Scoring:

• OK: No missing permissions
• WARN: 1–3 missing permissions
• ERROR: 4+ missing permissions

1e. Marketplace enrollment check

The local marketplace key (set by claude marketplace add <name>) is user-chosen and varies between installs (commonly laurigates-claude-plugins, sometimes claude-plugins). Identify the marketplace by its stable source.repo, not by a hardcoded local key.

1. Read .claude/settings.json.
2. Scan all entries under extraKnownMarketplaces and find the one whose source.repo equals "laurigates/claude-plugins". Capture that entry's key as $MP_KEY.
3. Check that enabledPlugins contains at least one key with the suffix @$MP_KEY.
4. Report:
   • OK: Both checks pass
   • WARN: enabledPlugins has no @$MP_KEY entries (marketplace enrolled but no plugins enabled)
   • ERROR: no extraKnownMarketplaces entry with source.repo = laurigates/claude-plugins (run /configure:claude-plugins --fix to add it)

Reference jq snippet (for verification or fix scripts):

MP_KEY=$(jq -r '.extraKnownMarketplaces // {} | to_entries | map(select(.value.source.repo == "laurigates/claude-plugins")) | .[0].key // empty' .claude/settings.json)
if [ -z "$MP_KEY" ]; then
  echo "ERROR: no extraKnownMarketplaces entry with source.repo = laurigates/claude-plugins"
else
  jq -e --arg k "@$MP_KEY" '.enabledPlugins // {} | to_entries | map(select(.key | endswith($k))) | length > 0' .claude/settings.json >/dev/null \
    && echo "OK: marketplace enrolled as $MP_KEY with enabled plugins" \
    || echo "WARN: marketplace $MP_KEY enrolled but no @${MP_KEY} entries in enabledPlugins"
fi

Step 2: Run scope-specific audits

For --scope=registry or all:

bash "${CLAUDE_PLUGIN_ROOT}/skills/health-plugins/scripts/check-registry.sh" \
  --home-dir "$HOME" --project-dir "$(pwd)"

Parse STATUS=, PLUGIN_COUNT=, ORPHANED_ENTRIES=, STALE_ENABLED_ENTRIES=, and ISSUES:.

For --scope=stack or all: follow the tech-stack audit steps from the internal health-audit skill (see ${CLAUDE_PLUGIN_ROOT}/skills/health-audit/SKILL.md and its REFERENCE.md).

For --scope=agentic or all: follow the skill-quality audit steps from the internal health-agentic-audit skill (see ${CLAUDE_PLUGIN_ROOT}/skills/health-agentic-audit/SKILL.md and its REFERENCE.md).

For --scope=runtime or all:

bash "${CLAUDE_SKILL_DIR}/scripts/check-runtime.sh" --home-dir "$HOME" --project-dir "$(pwd)"

Parse STATUS=, RUNTIME_SIZE_BYTES=, PROJECTS_TOTAL=, PROJECTS_DEAD=, GH_PATHS_TOTAL=, GH_PATHS_DEAD=, ORPHAN_DISABLED_MCP=, DUPLICATE_MCP=, CLEANUP_SUGGESTED=, and ISSUES:. Pass --verbose to list every dead path / orphaned server (default is a single rolled-up issue per category to keep output compact).

The runtime scope audits ~/.claude.json — the harness state file that grows with every session and is never auto-pruned. It reports four classes of bloat: dead projects[] keys, dead githubRepoPaths[*] worktree paths, orphaned disabledMcpServers[] entries, and bare-vs-namespaced duplicate MCP names. The audit is read-only: it prints suggested jq filters for the operator to run manually after closing other Claude Code sessions.

Concurrent-write warning. The harness rewrites ~/.claude.json on session end. Before acting on the audit's suggested cleanups, close every other Claude Code session — otherwise the in-memory state of a live session will clobber your edits when it next writes the file. An automated cleanup writer is out of scope for this audit.

For --scope=usage or all:

bash "${CLAUDE_SKILL_DIR}/scripts/check-usage.sh" --home-dir "$HOME" --project-dir "$(pwd)"

Parse STATUS=, HISTORY_AVAILABLE=, TRANSCRIPTS_SCANNED=, SKILLS_ENABLED=, SKILLS_FIRED=, SKILLS_NEVER_FIRED=, SKILLS_DORMANT=, AGENTS_ENABLED=, AGENTS_FIRED=, AGENTS_NEVER_FIRED=, AGENTS_DORMANT=, SCHEMA_DRIFT_SUSPECTED=, and ISSUES:. Pass --verbose to list every never-fired / dormant skill and agent (default rolls each category into one issue line). Pass --window-days N to change the dormancy threshold (default 30).

The usage scope mines local session transcripts (~/.claude/projects/*/*.jsonl) for skill- and agent-invocation recency: never-fired skills/agents (installed but zero invocations in history) and dormant skills/agents (last invoked more than the window ago). Agent invocations are read from Agent/Task tool_use events keyed by subagent_type. Findings are advisory review candidates, not a delete list — a skill or agent can be correct yet rarely needed (recovery, migration, on-demand subagents gated behind a parent skill). The audit is read-only (no --fix path).

This scope does not read ~/.claude.json's pluginUsage.usageCount, and must not start. That counter tallies hook fires in the same number as skill/agent/command deliveries, so it ranks a plugin by hook-trigger cadence rather than by use — see .claude/rules/plugin-usage-telemetry.md. Transcript mining is the delivery signal; the runtime scope's use of ~/.claude.json is unrelated (file bloat only).

Local-leaning. Session history is local and long-lived, so this scope is near-useless in a remote/web sandbox (a fresh clone has ≤1 transcript). It emits STATUS=SKIP with HISTORY_AVAILABLE=false when there are fewer than two transcripts rather than reporting every skill as never-fired. If TRANSCRIPTS_SCANNED>0 but zero tool calls parse, it emits STATUS=WARN TYPE=schema_drift (the transcript JSON shape changed) instead of a bogus all-never-fired result.

Step 3: Report findings

Print a consolidated report grouped by scope:

1. Environment — plugins/settings/hooks/MCP status + counts, SessionStart smoke test, pre-commit validity, permissions coverage, marketplace enrollment
2. Registry — orphaned projectPath entries, stale enabledPlugins keys, registry-vs-settings drift
3. Stack — detected stack + relevant/irrelevant/missing plugin recommendations
4. Agentic — skills missing optimisation tables, bare CLI commands, stale reviews
5. Runtime — ~/.claude.json size, dead projects/githubRepoPaths, orphaned disabledMcpServers, duplicate MCP naming (read-only — no --fix path)
6. Usage — never-fired and dormant skills from session telemetry (read-only — no --fix path; SKIPs when history is insufficient)

Use STATUS= indicators (OK/WARN/ERROR) and issue counts per scope. Include a summary table:

See REFERENCE.md for the full report template.

Step 4: Apply fixes (if --fix)

If --fix is set:

1. If --scope=all AND findings exist in multiple scopes, use AskUserQuestion to let the user pick which scopes to fix (multi-select: registry, stack, agentic).

2. For each selected scope, delegate:

   Scope	Delegate to
   registry	bash "${CLAUDE_PLUGIN_ROOT}/skills/health-plugins/scripts/fix-registry.sh" --home-dir "$HOME" --project-dir "$(pwd)" (pass --dry-run when set)
   stack	Follow the --fix flow in ${CLAUDE_PLUGIN_ROOT}/skills/health-audit/SKILL.md (Step 6)
   agentic	Follow the --fix flow in ${CLAUDE_PLUGIN_ROOT}/skills/health-agentic-audit/SKILL.md (Step 6)

3. Parse each script's output (STATUS=, REMOVED_COUNT=, MESSAGE=, RESTART_REQUIRED=) and report what changed.

4. If any fix reports RESTART_REQUIRED=true, remind the user to restart Claude Code.

Step 5: Verify

Re-run the relevant checks and confirm issue counts have dropped.

Agentic Optimizations

Known Issues