doctor

A diagnostic command for a bubbaloop installation, checking authentication, background services, network transport, operating mode, and registered nodes.

In plain words
What is it for?
Use it when bubbaloop cannot connect or behave normally and you need to check its token, daemon, MCP connection, Zenoh router, and available tools.
Why use it?
It helps identify where an installation is failing and gives a specific fix for each failed check.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/kornia/bubbaloop/doctor
Clone the repo
git clone --depth 1 https://github.com/kornia/bubbaloop
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 643 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00643
Opus 5 $0.00019 $0.00321
Sonnet 5 $0.00008 $0.00129
Haiku 4.5 $0.00004 $0.00064

Measured 2d ago against content hash ad03e28dfd03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

bubbaloop-mcp/commands/doctor.md · 30 lines

What it actually says

Run a comprehensive bubbaloop install check. Use the bubbaloop MCP server where the check is in-band; fall back to Bash for things outside the daemon (env vars, Zenoh router process).

For each check below, output ONE line in this exact format:

✓ <check>                           OR
✗ <check> — <one-line fix command>

Sequence (each depends on the previous succeeding):

  1. BUBBALOOP_MCP_TOKEN env var — present, non-empty, length plausible (≥ 16 chars). Fix: export BUBBALOOP_MCP_TOKEN="$(cat ~/.bubbaloop/mcp-token)"
  2. Token file~/.bubbaloop/mcp-token exists and is mode 0600. Fix: bubbaloop daemon run once to regenerate.
  3. Zenoh router — port 7447 listening (check via ss -tlnp 2>/dev/null | grep -q :7447). Fix: ~/.bubbaloop/bin/zenohd > /tmp/zenohd.log 2>&1 &
  4. Bubbaloop daemon — port 8088 listening. Fix: bubbaloop daemon run > /tmp/bubbaloop_daemon.log 2>&1 &
  5. MCP system_status — call returns success. Verifies the entire transport+auth path. Fix path depends on error: 401 → re-export token, connection refused → step 4, anything else → tail /tmp/bubbaloop_daemon.log.
  6. Tool surfacetools/list returns ≥ 40 tools, names use noun_verb (node_list not list_nodes). If old names → daemon is running a pre-rename binary; rebuild cargo build --bin bubbaloop and restart.
  7. node_list — call returns ≥ 1 node.
  8. Failed nodes — count of nodes with status Failed. Surface their names. Fix recommendation: /bubbaloop:diagnose <name> for the first one.
  9. NotInstalled nodes — count + names. Fix: bubbaloop node install <name> (NOT the MCP node_install tool — see alignment-notes #11).
  10. Mode — read BUBBALOOP_MCP_MODE env var (or note it's unset → admin default). Flag if it's readonly or safe so the user knows why some tools may be ceiling-restricted.

End with a single-line summary: <n> passed, <m> failed.

If any check fails, follow it with the exact → next: fix command on its own line. Don't narrate intermediate calls. Keep the response under one screen.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 30 lines · 38 tokens per session scan A ad03e28dfd03

Subscribe to this mod's changes

doctor is a command published in the GitHub repository kornia/bubbaloop (28 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 643 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.