Skip to content
Agentmart
Submit a tool

health

Report whether Musubi memory is actually working in this session - settings, identity, transport, capture and delivery queues, recent degradations, and any…

Skill by sourceblender

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying health?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sourceblender-health

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Report whether Musubi memory is actually working in this session - settings, identity, transport, capture and delivery queues, recent degradations, and any stranded records - in plain words.

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/health

Tools it pre-approves 2

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash(musubi-claude-health
  • *)

What's inside

Skill name
health
Description
Report whether Musubi memory is actually working in this session - settings, identity, transport, capture and delivery queues, recent degradations, and any stranded records - in plain words.
License
Apache-2.0
Allowed tools
Bash(musubi-claude-health, *)
Instructions
30 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Musubi memory health

Local state, read-only (no conversation content, no credentials):

```!
musubi-claude-health --plugin-data "${CLAUDE_PLUGIN_DATA}" $ARGUMENTS
```

Explain the report above to the user in a short, plain summary. Rules:

- Lead with one verdict line: **working**, **working with problems**, or
  **not working**, and why.
- `setup: false` → not set up; tell them to run `/musubi-claude:setup`.
- `error: plugin_data_unknown` → the report could not find the plugin's data
  directory, so it says nothing about setup. Do not suggest setup; quote the
  `fix`.
- `identity.ok: false` → quote the error code; point to `/config` →
  musubi-claude (**Musubi actor**, **Seat**, **Zone**).
- Delivery: `delivery_mode: shadow` means nothing has left this machine, by
  design. With `verified`, give the counts: verified vs still pending vs dead.
  **Pending is not stored** — never call pending records remembered.
- `other_root.undelivered` > 0 → say plainly that that many records sit in an
  older state directory and will not be delivered from there; this needs a
  deliberate move, not a retry.
- Degradations: name the top one or two reasons and the latest time. Say they
  are capture skips (a turn that was not recorded), not data loss of stored
  memories.
- `provider` (only with `--probe`): reachable or not. Unreachable is not the
  same as empty memory.
- Do not paste the raw JSON unless the user asks. Do not invent numbers that
  are not in the report.

From sourceblender/musubi-claude, Apache-2.0.

Signals

Stars
0
Forks
2
Open issues
2
Last commit (this folder)
Sep 26, 2026 (1 month ago)
Last release
Sep 29, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sourceblender

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get health running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying health?

CallGet help
Cite this page

health skill. Agent Mart. https://agentmart.dev/skills/sourceblender-health (last updated 2026-10-24)