Status logo

Status

Community
dsifry
status

Diagnostic status report — shows metaswarm installation state, project setup, and potential issues

Overview

Publisherdsifry
Repositorymetaswarm
Skill namestatus
Stars
421
Forks
54
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dsifry on GitHub. Read the source before you install it.

Installation

Install the Status AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dsifry/metaswarm/tree/main/skills/status
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dsifry/metaswarm.git /tmp/metaswarm
mkdir -p .claude/skills
cp -r /tmp/metaswarm/skills/status .claude/skills/status
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Status in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Status on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Status is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Status Skill

Generate a diagnostic report of the metaswarm installation, project configuration, and potential issues across Claude Code, Codex, and Gemini. Useful for troubleshooting and verifying setup or migration.


Checks

Run each check below and present results in a single formatted report. Detect the active platform first:

  • Codex: PLUGIN_ROOT or CODEX_HOME is present, .codex-plugin/plugin.json is the active manifest, or the user invoked $status
  • Claude Code: CLAUDE_PLUGIN_ROOT is present, .claude-plugin/plugin.json is the active manifest, or the user invoked $status
  • Gemini: extensionPath is present, gemini-extension.json is the active manifest, or the user invoked $status

1. Plugin Version

  • Codex: read .codex-plugin/plugin.json from the plugin root and report version
  • Claude Code: read .claude-plugin/plugin.json from the plugin root and report version
  • Gemini: read gemini-extension.json from the plugin root and report version
  • Fallback: read package.json at plugin root for version
  • If neither found: Plugin version: UNKNOWN

2. Project Setup State

  • Check if .metaswarm/project-profile.json exists in the working directory
  • If present, report key fields: distribution, metaswarm_version, language, framework, test_runner
  • If absent, report the platform-specific setup command:
    • Codex: Project setup: NOT CONFIGURED -- run $setup
    • Claude Code: Project setup: NOT CONFIGURED -- run $setup
    • Gemini: Project setup: NOT CONFIGURED -- run $setup

3. Platform Install State

Codex

  • Check .codex-plugin/plugin.json exists in the plugin root
  • Check ~/.codex/config.toml for an enabled metaswarm@... plugin entry when accessible
  • Scan ~/.codex/plugins/cache/ for .codex-plugin/plugin.json with "name": "metaswarm"
  • If installed from a local marketplace, report cache version as local

Claude Code

  • Check .claude-plugin/plugin.json exists in the plugin root
  • Scan ~/.claude/plugins/cache/ for .claude-plugin/plugin.json with "name": "metaswarm"
  • Report marketplace/plugin cache status when accessible

Gemini

  • Check gemini-extension.json exists in the plugin root
  • Report extension status when discoverable from the local Gemini config

4. Claude Command Shims

When checking a Claude project, check these files in .claude/commands/:

ShimExpected
start-task.mdRoutes to /metaswarm:start-task
prime.mdRoutes to /metaswarm:prime
review-design.mdRoutes to /metaswarm:review-design
self-reflect.mdRoutes to /metaswarm:self-reflect
pr-shepherd.mdRoutes to /metaswarm:pr-shepherd
brainstorm.mdRoutes to /metaswarm:brainstorm

For each: report Present/Missing. If the file exists but does not contain "metaswarm" routing, flag as present (non-metaswarm content).

When checking a Codex project, report not applicable (Codex uses $skill-name invocation) instead of treating missing .claude/commands/ files as errors.

5. Legacy Embedded Plugin

  • Check for .claude/plugins/metaswarm/.claude-plugin/plugin.json
  • If found: DETECTED -- run $migrate
  • If found alongside the marketplace plugin, flag prominently as a conflict

6. BEADS Plugin

  • Scan ~/.claude/plugins/cache/ and ~/.codex/plugins/cache/ for a directory containing .claude-plugin/plugin.json or .codex-plugin/plugin.json with "name": "beads"
  • If found: installed (standalone) -- metaswarm defers priming to BEADS
  • If not found: not separately installed

7. bd CLI

bash
command -v bd && bd --version 2>/dev/null
  • If found: report path and version
  • If not found: not installed -- knowledge priming and self-reflect require bd. Core orchestration works without it.

8. gtg CLI

bash
command -v gtg && gtg --help >/dev/null 2>&1
  • If found: report path
  • If not found: not installed -- pr-shepherd will fall back to manual gh checks.

9. External Tools

  • Read .metaswarm/external-tools.yaml -- if absent: not configured (optional)
  • If present, check each enabled adapter's availability:
bash
command -v codex    # Codex CLI
command -v gemini   # Gemini CLI

Report per-tool: enabled (yes/no), status (available/not installed).

10. Coverage Thresholds

  • Read .coverage-thresholds.json -- if absent: not configured
  • If present, report threshold values (lines, branches, functions, statements) and enforcement command

11. Node.js

bash
node --version 2>/dev/null
  • If found: report version
  • If not found: not installed -- scripts/beads-*.ts require Node.js. Core orchestration works without it.

Output Format

markdown
## Metaswarm Status Report

| Component | Status |
|---|---|
| Active platform | Codex |
| Plugin version | 0.11.0 |
| Project setup | Configured (distribution: plugin) |
| Platform install | Codex plugin installed and enabled |
| Command shims | Not applicable (Codex uses $skill-name) |
| Legacy embedded plugin | Not detected |
| BEADS plugin | Not separately installed |
| bd CLI | Available (v0.5.2) |
| gtg CLI | Available |
| External tools | Codex: available, Gemini: not installed |
| Coverage thresholds | 100% (all categories) |
| Node.js | Available (v22.4.0) |

### Issues Found
- None

### Recommendations
- None

When issues are found:

markdown
### Issues Found
1. Legacy embedded plugin detected alongside marketplace plugin -- run `$migrate`
2. Codex plugin not installed from a marketplace -- install from `/plugins` after adding the marketplace

### Recommendations
1. Install `bd` CLI for knowledge priming and self-reflect
2. Install `gtg` for the fastest `$pr-shepherd` readiness checks
3. Configure external tools for cross-model review (`.metaswarm/external-tools.yaml`)

Error Handling

This skill is diagnostic-only and never fails fatally. If any individual check errors, report the failure for that check (for example, Plugin version: ERROR -- could not read plugin.json) and continue with remaining checks.

Frequently asked questions

What does the Status AI skill do?

Diagnostic status report — shows metaswarm installation state, project setup, and potential issues

Why use Status on TypingMind?

Because you install it once and use it with any model. Status is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Status in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dsifry/metaswarm/tree/main/skills/status. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Status?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Status?

As many as you like. As long as a model supports skills, you can use Status with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Status AI skill free?

Yes. It is published on GitHub by dsifry under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇