New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Basemind Doctor

by Goldziher in Goldziher/basemind

Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead.

MITAuto-check passedAgent Workflows

Install Basemind Doctor

skills CLI
$ npx skills add Goldziher/basemind --skill basemind-doctor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Goldziher/basemind basemind-doctor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Goldziher/basemind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/basemind-doctor .claude/skills/basemind-doctor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
basemind-doctor
GitHub stars
108
Token cost
~1.3k tokens
SKILL.md length
686 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead.

  • Works in 4 steps: Is there an index? → Is a server already running (holding the… → Rebuild the index if needed → …
  • Tasks that involve MCP servers
  • SKILL.md covers 1. Is there an index?, 2. Is a server already running…, 3. Rebuild the index if needed and 4. Reconnect the MCP server…, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Basemind Doctor is an agent skill from Goldziher/basemind. Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead. Runs CLI checks (no MCP server required) and gives the client-specific way to reconnect the server.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame… The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “t working — MCP tools missing or erroring,”
  • “no indexed files”
  • “/basemind-doctor”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Is there an index?
  2. Is a server already running (holding the lock)?
  3. Rebuild the index if needed
  4. Reconnect the MCP server (client-specific — this is the only way to restart it)

What it can do on your machine

Read from SKILL.md and the folder at commit b1ac766. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Basemind Doctor loads about 1.3k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 686 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Goldziher/basemind at commit b1ac766, republished under its MIT licence (© Goldziher). 686 words, ~1,262 tokens.

Download SKILL.mdSave it as .claude/skills/basemind-doctor/SKILL.md (or your agent's skills folder).
name
basemind-doctor
description
Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead. Runs CLI checks (no MCP server required) and gives the client-specific way to reconnect the server.

basemind-doctor — diagnose and recover basemind

Use this when basemind isn't behaving: MCP tools aren't available or return errors, the statusline says no index, queries come back empty when they shouldn't, or the basemind serve MCP server appears dead. Every step here uses the CLI, so it works even when the MCP server is down.

Important: a stdio MCP server (what basemind serve is) cannot be restarted by an agent or by basemind itself — a fresh process can't resume the client's MCP initialize handshake. Reconnecting the server is the MCP client's job (see step 4). What you can do from here is make sure the index is healthy and clear anything blocking a restart.

1. Is there an index?

sh
basemind doctor   # root, config, index, grammars, hook, daemon; exits 1 when a check fails
basemind status
  • Errors / "no index" / file_count: 0 with blobs present → the index is missing or lost. Build it: basemind scan (see the basemind-scan skill / /bm-scan).
  • Healthy file_count → the index is fine; the problem is the server connection (step 4).
  • outline says "file not indexed" for a README, JSON, YAML or TOML file → expected, not a fault: those are documents, not code. Use memory { mode: "documents", query } (or Read the file).
  • A notice of warming_up / building_index means the index is still loading: wait and retry (admin { mode: "status" } shows indexing / warming).

2. Is a server already running (holding the lock)?

If basemind scan fails with a lock error, a basemind serve (or watch) already owns the index for this repo. The lock-contention error itself names the live holder (command + pid) — it reads that from the .lock.meta sidecar next to the workspace .lock. Both live in this workspace's directory under the machine-global cache (Linux ~/.local/share/basemind/, macOS ~/Library/Application Support/basemind/; override BASEMIND_DATA_HOME), keyed by workspace — not in the repo.

  • If that pid is alive (ps -p <pid>), the server is up — use the MCP tools, or the admin { mode: "rescan" } or basemind rescan to refresh. Don't run a CLI scan (it will contend on the lock and exit 3).
  • If that pid is dead, the lock is stale. The OS releases the advisory lock when a process dies, so a fresh basemind scan / basemind serve should just work — retry it. (You may delete the stale .lock.meta sidecar in that workspace cache dir to clear the advisory holder record.)

3. Rebuild the index if needed

sh
basemind scan

Non-extractable files are skipped, not failed. After this, both the CLI and (once reconnected) the MCP tools have a fresh index.

Show full SKILL.md (289 more words)Show less

4. Reconnect the MCP server (client-specific — this is the only way to restart it)

basemind can't relaunch its own stdio server; trigger a reconnect in your client:

  • Claude Code: reconnect the basemind MCP server from the MCP UI, or restart the session. The plugin's launcher re-downloads/execs the binary automatically on the next connection.
  • Cursor / others: toggle/reconnect the basemind MCP server in the MCP settings.

While disconnected, you are not blocked: use the basemind-cli skill (basemind code …, basemind git …) — it reads the same machine-global cache directly, no server required.

Agent shells (embedded rmux daemon)

Only when the server was built with --features shells. Spawned shell sessions run under an embedded rmux daemon — basemind re-execs itself (--__internal-daemon) rather than shelling out to any external rmux binary, so there is nothing extra to install. The daemon binds a private per-user socket under the data dir (<data_dir>/basemind/shells/rmux.sock, 0o700), overridable with BASEMIND_SHELLS_SOCKET. It is separate from the comms broker daemon.

  • shell { mode: "list" } enumerates sessions with liveness; a dead-but-listed session was killed or exited — re-run after shell { mode: "kill", session_id: "…" } to confirm it's gone.
  • The daemon self-terminates once it has no sessions left, so an idle daemon disappearing is expected, not a fault. shell mode spawn starts a fresh one.
  • Sessions are independent of serve: they outlive a single MCP call but are torn down by shell mode kill (which also drops the comms lineage row) or when the daemon exits.

When server logs help

basemind serve logs its lifecycle to stderr (captured in your client's MCP server logs): a MCP server starting line with pid/version/view at startup, and an explicit client disconnected, exiting (clean) or exiting on error (with the cause) at shutdown. If serve keeps dying, that log line names the reason.

© Goldziher, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/basemind-doctor of Goldziher/basemind.

Open the folder on GitHubat commit b1ac766

Compare with similar skills

Basemind Doctor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Basemind Doctor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Basemind Doctor this skillGoldziher/basemind108—~1.3kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from Goldziher/basemind

All 10 skills in this repo

  • Basemind Usage Stats

    Goldziher/basemind

    Shows a markdown dashboard of basemind activity in the session: tool call counts, top operations and estimated tokens saved against a grep and Read baseline.

    108 GitHub stars~558 tokensUpdated today
    Auto-check passed

  • Basemind Code Context

    Goldziher/basemind

    Answers structural questions about a repository, such as where a symbol is defined, what calls it and what changed recently, through the basemind MCP server.

    108 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Basemind Index Scan

    Goldziher/basemind

    Builds or refreshes the basemind code index from the command line, for when basemind reports no index or its MCP server is not running.

    108 GitHub stars~1.1k tokensUpdated today
    Auto-check: warnings

  • basemind CLI Codebase Navigator

    Goldziher/basemind

    Drives the basemind code-intelligence tool from the command line for symbol search, callers, git history and blame, document search and web crawling, sharing its cache with the MCP server.

    108 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Basemind Code Search

    Goldziher/basemind

    Answers where code is defined, who calls it and what shape a file has from a pre-built index, returning paths and line numbers instead of file contents.

    108 GitHub stars~1.6k tokensUpdated today
    Auto-check: notes

  • Basemind Documents

    Goldziher/basemind

    Semantic + full-text search over documents and the web via basemind's RAG store — PDFs, Office, HTML, email, images (OCR), plus scraped/crawled web pages, with cross-encoder reranking, keyword and…

    108 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Basemind Doctor

What does Basemind Doctor do?

Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead. Basemind Doctor is an agent skill from Goldziher/basemind. Diagnose and recover basemind when it isn't working — MCP tools missing or erroring, "no index" / "no indexed files", empty results that shouldn't be empty, or the MCP server seems dead.

When should I use Basemind Doctor?

Basemind Doctor fits situations like: tasks that involve MCP servers.

How do I install Basemind Doctor in Claude Code?

Run `npx skills add Goldziher/basemind --skill basemind-doctor -a claude-code`. Or copy the skill folder (skills/basemind-doctor in Goldziher/basemind) into .claude/skills/basemind-doctor in your project. Claude Code loads it when a task matches its description.

How do I install Basemind Doctor in Codex?

Run `npx skills add Goldziher/basemind --skill basemind-doctor -a codex`. Or copy the skill folder (skills/basemind-doctor in Goldziher/basemind) into .agents/skills/basemind-doctor in your project. Codex loads it when a task matches its description.

Can I use Basemind Doctor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Goldziher/basemind --skill basemind-doctor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/basemind-doctor, .gemini/skills/basemind-doctor, .github/skills/basemind-doctor and .opencode/skills/basemind-doctor in your project.

What does Basemind Doctor need to run?

SKILL.md names no scripts, command-line tools or credentials: Basemind Doctor is instructions for the agent only.

Does Basemind Doctor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Basemind Doctor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Basemind Doctor use?

Basemind Doctor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Basemind Doctor use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Basemind Doctor?

Skills that share tags, products or a category with Basemind Doctor: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Basemind Doctor?

Goldziher (a GitHub user) maintains it in Goldziher/basemind, which has 108 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 11, 2026.

Source: Goldziher/basemind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.