{"slug":"ops-doctor","title":"ops-doctor","summary":"Health check and auto-repair for the ops plugin. Diagnoses manifest errors, broken permissions, invalid configs, stale caches, and missing files — then spawns an agent to fix everything automatically.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-14T20:43:19.274105Z","repo":{"url":"https://github.com/davepoon/buildwithclaude","stars":3556,"forks":535,"license":"MIT","updatedAt":"2026-09-27T03:56:38Z"},"bodyHtml":"
\n

name: ops-doctor\ndescription: Health check and auto-repair for the ops plugin. Diagnoses manifest errors, broken permissions, invalid configs, stale caches, and missing files — then spawns an agent to fix everything automatically.\nargument-hint: \"[--check-only|--verbose]\"\nallowed-tools:

\n\n
\n

Runtime Context

\n

Before diagnosing, load:

\n
    \n
  1. Preferences: cat ${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json — check all configured channels and services
    2. \n
  2. Daemon health: cat ${CLAUDE_PLUGIN_DATA_DIR}/daemon-health.json — primary diagnostic input
    3. \n
  3. Secrets: Verify secret resolution chain works: Doppler MCP → env → Doppler CLI → password manager
    4. \n
\n

OPS ► DOCTOR

\n

CLI/API Reference

\n

ops-doctor bin script

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
CommandUsageOutput
${CLAUDE_PLUGIN_ROOT}/bin/ops-doctorRun full health diagnosticsJSON with errors, warnings, tools, env_vars, registry
${CLAUDE_PLUGIN_ROOT}/bin/ops-doctor 2>/dev/null \\|\\| echo '{\"errors\":[\"diagnostic_script_failed\"]}'Run with fallbackJSON or error sentinel
\n

Key files read by diagnostics

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
FilePurpose
${CLAUDE_PLUGIN_DATA_DIR}/daemon-health.jsonPrimary daemon health input
${CLAUDE_PLUGIN_DATA_DIR}/preferences.jsonConfigured channels and services
${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.jsonPlugin manifest validation
${CLAUDE_PLUGIN_ROOT}/scripts/registry.jsonProject registry validation
\n
\n

Phase 1 — Run diagnostics

\n

Run the diagnostic script to get a full health report:

\n
${CLAUDE_PLUGIN_ROOT}/bin/ops-doctor 2>/dev/null || echo '{\"errors\":[\"diagnostic_script_failed\"],\"warnings\":[]}'\n
\n

Parse the JSON output. Display a summary:

\n
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n OPS ► DOCTOR — [timestamp]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n Plugin:     [version] at [plugin_root]\n Skills:     [count] defined\n Agents:     [count] defined\n Bin scripts:[count] available\n\n ERRORS      [count]\n [list each error with description]\n\n WARNINGS    [count]\n [list each warning with description]\n\n TOOLS\n [table of CLI tool availability]\n\n ENV VARS\n [table of env var status]\n\n Registry:   [status] ([project_count] projects)\n Preferences:[status]\n Cache:      [versions list]\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n
\n

Agent Teams support

\n

If CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is set, use Agent Teams when multiple independent fix categories are identified (e.g., manifest issues + permission issues + registry issues). This enables:

\n\n

Team setup (only when flag is enabled, multiple issue categories):

\n
TeamCreate(\"doctor-fixers\")\nAgent(team_name=\"doctor-fixers\", name=\"fix-manifest\", subagent_type=\"ops:doctor-agent\", ...)\nAgent(team_name=\"doctor-fixers\", name=\"fix-permissions\", subagent_type=\"ops:doctor-agent\", ...)\nAgent(team_name=\"doctor-fixers\", name=\"fix-registry\", subagent_type=\"ops:doctor-agent\", ...)\n
\n

If the flag is NOT set or only one issue category exists, use a single doctor-agent subagent.

\n

Phase 2 — Decision

\n

If $ARGUMENTS contains --check-only: stop here, display results only.

\n

If there are errors or warnings:

\n

Display: \"Found [N] issues. Spawning doctor agent to auto-fix...\"

\n

Then spawn the doctor agent (or Agent Team — see above):

\n
Agent({\n  subagent_type: \"ops:doctor-agent\",\n  prompt: \"Fix the following ops plugin issues.\\n\\nDIAGNOSTIC_JSON: [paste full JSON]\\nPLUGIN_ROOT: ${CLAUDE_PLUGIN_ROOT}\\nCACHE_DIR: ~/.claude/plugins/cache/ops-marketplace/ops\\n\\nFix all errors and warnings. Re-run diagnostics after to verify.\",\n  description: \"Fix ops plugin issues\"\n})\n
\n

If there are no errors and no warnings:

\n

Display: \"All checks passed. Plugin is healthy.\"

\n

Phase 3 — Post-fix verification

\n

After the agent completes, re-run diagnostics:

\n
${CLAUDE_PLUGIN_ROOT}/bin/ops-doctor 2>/dev/null\n
\n

Display updated results. If errors remain, report them to the user with manual fix instructions.

\n
\n

Native tool usage

\n

WebSearch — known issue lookup

\n

When diagnostics find errors, use WebSearch to check if the issue is a known Claude Code plugin bug, MCP server issue, or configuration problem. Include links to relevant GitHub issues or docs.

\n

WebFetch — MCP health check

\n

For MCP servers that appear disconnected, use WebFetch to test their underlying APIs directly (e.g., https://api.linear.app/graphql with a simple query) to distinguish between \"MCP broken\" and \"API down\".

\n","files":[{"path":"SKILL.md","sizeBytes":5305,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-14T20:43:28.125155Z","sha256":"7FE347EC1D53F74646EA2EE4784DE2DBB2F01712EA7B7B4E051F7E2599C2BD29","sizeBytes":2288},"review":null,"source":{"repositoryUrl":"https://github.com/davepoon/buildwithclaude","path":"plugins/claude-ops/skills/ops-doctor","license":"MIT","commit":"6178ae2b0900b3600419853206de1dddf0f28311","subtreeSha":"A45E9C36A398A8000152E8E5212DCCF52FC3EB40798A3417B4407ED7D823E3B0","lastSyncedAt":"2026-09-27T19:47:46.68834Z"},"reviewedAt":"2026-09-14T20:43:54.952673Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/davepoon/buildwithclaude/tree/main/plugins/claude-ops/skills/ops-doctor"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install davepoon-buildwithclaude@llmmart"},{"target":"git","command":"git clone https://github.com/davepoon/buildwithclaude.git"}]}