Mlscp

Parse and generate MLSCP (Micro LLM Swarm Communication Protocol) commands. Use when communicating with other agents efficiently, parsing compressed commands, or generating token-efficient instructions. Reduces token usage by 70-80% compared to natural language.

Security Scan

The skill's documentation describes CLI scripts and a Python module but there are no code files or install instructions included — the runtime instructions expect local tooling that isn't provided, which is an incoherence you should resolve before trusting it.

Purpose & Capability

The skill claims to parse/generate MLSCP and shows examples invoking ./scripts/mlscp.sh and a Python mlscp module; however the package contains no scripts, modules, or install spec. Either the skill relies on external, preinstalled tooling (not documented) or the submission is incomplete. Requesting no credentials and no binaries is consistent with the stated purpose, but the absence of the actual implementation is inconsistent.

Instruction Scope

SKILL.md instructs the agent to run shell scripts (parse/validate/compress/vocab) and to read a project path to generate vocabulary (which implies reading repository files). Those operations are reasonable for a parser/generator, but the instructions give the agent permission to execute arbitrary local scripts and access project files — and the referenced scripts are not present. This open-ended execution of local scripts is a risk if the referenced tooling is substituted or malicious.

Install Mechanism

No install spec is provided (lowest risk from an installer perspective). However, because the instructions reference local scripts and a Python package, a missing install step is a functional and security concern: the skill either expects preinstalled third-party tooling (not documented) or the submission omitted implementation artifacts.

Credentials

The skill declares no required environment variables, credentials, or config paths. The SKILL.md uses a single environment variable example ($INCOMING_COMMAND) which is reasonable. There are no requests for unrelated secrets or system credentials.

Persistence & Privilege

The skill does not request always: true and makes no persistence or system-wide changes. Autonomous invocation is allowed (platform default) but not combined with other high-privilege requests.

What to consider before installing

This skill's docs show CLI scripts and a Python module but the skill bundle contains only SKILL.md and no code or install instructions. Before installing or enabling it: 1) ask the publisher for the missing scripts or a clear install procedure (or a verified GitHub release link). 2) If the skill will run local scripts, inspect those scripts first — they could execute arbitrary commands. 3) If you must test it, do so in an isolated environment (sandbox/VM) with no sensitive files mounted. 4) Prefer a version that includes its implementation or links to an audited release; do not grant it broad autonomous privileges until you confirm what it will execute.

MLSCP Skill

MLSCP (Micro LLM Swarm Communication Protocol) is a token-efficient command language for agent-to-agent communication. This skill lets you parse, validate, and generate MLSCP commands without any LLM overhead.

Why Use MLSCP?

Natural Language	MLSCP	Savings
"Please modify the file src/chain_orchestrator.py by adding retry logic at line 47"	F+ s/co > ln47 + 'retry logic'	~75%
"Read the contents of utils/file_manager.py from lines 10 to 50"	F? u/fm > ln10-50	~80%
"Delete the variable 'temp_cache' from config.py"	V- c/c > 'temp_cache'	~70%

Quick Start

Parse a Command

./scripts/mlscp.sh parse "F+ s/co > ln47 + 'retry logic'"

Validate Syntax

./scripts/mlscp.sh validate "F+ s/co > ln47 + 'retry logic'"

Generate Vocabulary

./scripts/mlscp.sh vocab /path/to/project

Compress Natural Language

./scripts/mlscp.sh compress "Add error handling to the main function in app.py"

Command Reference

Operations

Code	Meaning	Example
F+	File add/insert	F+ s/app > ln10 + 'new code'
F~	File modify	F~ s/app > ln10-20 ~ 'updated code'
F-	File delete	F- s/app > ln10-15
F?	File query/read	F? s/app > ln1-100
V+	Variable add	V+ s/app + 'new_var = 42'
V~	Variable modify	V~ s/app > 'old_var' ~ 'new_value'
V-	Variable delete	V- s/app > 'temp_var'
V?	Variable query	V? s/app > 'config_*'

Location Specifiers

• ln47 - Single line
• ln10-50 - Line range
• fn:main - Function name
• cls:MyClass - Class name

Context Blocks

CTX{"intent":"resilience","priority":"high","confidence":0.9}

Scripts

• mlscp.sh - Main CLI tool
• vocab.py - Vocabulary generator (Python)

Integration

With Other Agents

When receiving commands from MLSCP-enabled agents:

./scripts/mlscp.sh parse "$INCOMING_COMMAND"

Sending Commands

Generate compact commands for other agents:

./scripts/mlscp.sh compress "Your natural language instruction"

API (Python)

from mlscp import parse, MLSCPParser

# Quick parse
cmd = parse("F+ s/co > ln47 + 'retry logic'")
print(cmd.operation)  # OperationType.FILE_ADD
print(cmd.target)     # "s/co"

# With vocabulary
parser = MLSCPParser(vocab_lookup)
cmd = parser.parse("F+ s/co > ln47 + 'code'")
full_path = vocab_lookup.get("s/co")  # "src/chain_orchestrator.py"

Resources

• GitHub: https://github.com/sirkrouph-dev/mlcp
• Grammar Spec: See references/grammar.abnf
• Protocol Definition: See references/protocol.md