Cli Anything Nslogger logo

Cli Anything Nslogger

OrganizationPopular
HKUDS
cli-anything-nslogger

CLI harness for NSLogger — parse, filter, export, and monitor NSLogger log files (.rawnsloggerdata / .nsloggerdata)

Overview

PublisherHKUDS
RepositoryCLI-Anything
Skill namecli-anything-nslogger
Stars
49.5K
Forks
4.6K
Bundled files
Instructions only
LicenseApache-2.0
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 HKUDS on GitHub. Read the source before you install it.

Installation

Install the Cli Anything Nslogger 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.
  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/HKUDS/CLI-Anything.git /tmp/CLI-Anything
mkdir -p .claude/skills
cp -r /tmp/CLI-Anything/nslogger/agent-harness/cli_anything/nslogger/skills .claude/skills/cli-anything-nslogger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cli Anything Nslogger 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 Cli Anything Nslogger 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 Cli Anything Nslogger 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.

cli-anything-nslogger

A complete CLI harness for NSLogger, the macOS log viewer for iOS/macOS apps.

Installation

bash
cd nslogger/agent-harness
pip install -e .
# Verify
cli-anything-nslogger --help

Command Reference

generate — Create sample files for testing

bash
cli-anything-nslogger generate sample.rawnsloggerdata --count 50

read — Display messages from a file

bash
# All messages
cli-anything-nslogger read session.rawnsloggerdata

# Errors only (level 0)
cli-anything-nslogger read session.rawnsloggerdata --level 0

# Filter by tag and text search
cli-anything-nslogger read session.rawnsloggerdata --tag Network --search "timeout"

# First 20 messages as JSON
cli-anything-nslogger read session.rawnsloggerdata --limit 20 --json

filter — Advanced filtering

bash
# Errors and warnings only
cli-anything-nslogger filter session.rawnsloggerdata --level 1

# By tag
cli-anything-nslogger filter session.rawnsloggerdata --tag Auth --tag Network

# Regex search
cli-anything-nslogger filter session.rawnsloggerdata --regex "(timeout|failed|error)"

# By thread
cli-anything-nslogger filter session.rawnsloggerdata --thread "main"

# JSON output
cli-anything-nslogger filter session.rawnsloggerdata --level 0 --json

export — Export to text/JSON/CSV

bash
# JSON to stdout
cli-anything-nslogger export session.rawnsloggerdata --format json

# CSV to file
cli-anything-nslogger export session.rawnsloggerdata --format csv --output logs.csv

# Filtered text export
cli-anything-nslogger export session.rawnsloggerdata --format text --level 1 --tag Network

stats — Summary statistics

bash
# Human-readable summary
cli-anything-nslogger stats session.rawnsloggerdata

# JSON for agent consumption
cli-anything-nslogger stats session.rawnsloggerdata --json

JSON output shape:

json
{
  "total": 342,
  "by_level": {"ERROR": 12, "WARNING": 34, "INFO": 200, "DEBUG": 96},
  "by_tag": {"Network": 89, "Auth": 45, "UI": 120},
  "by_thread": {"main": 200, "bg-queue": 142},
  "by_type": {"text": 340, "client_info": 1, "disconnect": 1},
  "clients": ["MyApp"],
  "first_timestamp": "2024-01-01T10:00:00+00:00",
  "last_timestamp": "2024-01-01T10:05:30+00:00",
  "duration_seconds": 330.0
}

listen — Receive live connections

bash
# Match the NSLogger.app GUI Bonjour behavior for iOS auto-discovery
cli-anything-nslogger listen --bonjour --name bazinga --debug

# Mirror live logs to a text file while still printing stdout
cli-anything-nslogger listen --bonjour --name bazinga --output app.log

# Write machine-readable JSON Lines
cli-anything-nslogger listen --bonjour --name bazinga --output app.jsonl --output-format jsonl

# Direct TCP/TLS mode for manually configured clients
cli-anything-nslogger listen --port 50000 --ssl --debug

# Show only errors while listening, output as JSON stream
cli-anything-nslogger listen --bonjour --name bazinga --level 0 --json

# Run until Ctrl-C
cli-anything-nslogger listen --bonjour --name bazinga

Use Bonjour mode first for iOS apps because it matches the desktop NSLogger GUI: the CLI publishes a native macOS NetService with _nslogger-ssl._tcp and accepts TLS NSLogger frames. Use direct TCP/TLS only when the app is manually configured with the Mac host and port.

repl — Interactive Command REPL

bash
cli-anything-nslogger repl session.rawnsloggerdata
# Or launch it by running cli-anything-nslogger with no subcommand.

Log Levels

ValueNameUse for
0ERRORUnrecoverable failures
1WARNINGRecoverable issues
2INFONormal operation
3DEBUGDeveloper details
4VERBOSETrace-level noise

Message JSON Shape

json
{
  "sequence": 42,
  "timestamp": "2024-01-01T10:01:23+00:00",
  "timestamp_ms": 456,
  "thread_id": "main",
  "tag": "Network",
  "level": 0,
  "level_name": "ERROR",
  "type": "text",
  "text": "Connection timed out after 30s",
  "image_width": 0,
  "image_height": 0,
  "client_name": "MyApp",
  "client_version": "2.1.0",
  "os_name": "iOS",
  "os_version": "17.0",
  "machine": "iPhone15,2"
}

Agent Workflow Examples

bash
# 1. Inspect a captured crash session
cli-anything-nslogger stats crash.rawnsloggerdata --json

# 2. Find all errors in the 5 minutes before crash
cli-anything-nslogger filter crash.rawnsloggerdata --level 0 --json

# 3. Get network failures only
cli-anything-nslogger filter crash.rawnsloggerdata --tag Network --regex "fail|timeout|error" --json

# 4. Export full log for offline analysis
cli-anything-nslogger export crash.rawnsloggerdata --format json --output crash_log.json

# 5. Monitor an iOS app live and keep a local copy
cli-anything-nslogger listen --bonjour --name bazinga --output app.log --debug

Frequently asked questions

What does the Cli Anything Nslogger AI skill do?

CLI harness for NSLogger — parse, filter, export, and monitor NSLogger log files (.rawnsloggerdata / .nsloggerdata)

Why use Cli Anything Nslogger on TypingMind?

Because you install it once and use it with any model. Cli Anything Nslogger 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 Cli Anything Nslogger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/CLI-Anything/tree/main/nslogger/agent-harness/cli_anything/nslogger/skills. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cli Anything Nslogger?

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 Cli Anything Nslogger?

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

Is the Cli Anything Nslogger AI skill free?

Yes. It is published on GitHub by HKUDS under the Apache-2.0 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 👇