← Back to Skills Marketplace
427
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install lobster-farmer-feeder
Description
Feed lobsters in the Lobster Farmer game by calling the local CLI command `lobster-farmer feed` with `--model`, `--input-tokens`, `--output-tokens`, and opti...
README (SKILL.md)
Lobster Farmer Feeder
Feed model-specific lobsters by invoking the local CLI and report the resulting growth metrics.
Workflow
- Confirm command context.
- Run from the Lobster Farmer project root where
bin/lobster-farmer.cjsexists. - Prefer the installed command
lobster-farmer; usenode ./bin/lobster-farmer.cjsas fallback.
- Ensure service is reachable.
- Check status first:
lobster-farmer status
- If stopped, start service:
lobster-farmer start
- Respect explicit user port preference with
--port.
- Execute feed command.
- Single feed:
lobster-farmer feed --model "\x3Cmodel>" --input-tokens \x3Cn> --output-tokens \x3Cm> [--emotion "\x3Ctext>"] [--port \x3Cp>]
- Short flags:
lobster-farmer feed -m "\x3Cmodel>" -i \x3Cn> -o \x3Cm> [-e "\x3Ctext>"] -p \x3Cp>
- Return result to user.
- Include model name, input/output token values, emotion, lobster total tokens, feed count, and size.
- If requested, run multiple feed commands sequentially and summarize each result.
Parameter Rules
- Require
modelas non-empty string. - Require
input_tokens + output_tokens > 0. emotionis optional; if omitted, UI should show?.- Keep token values as integers and non-negative.
- If user gives only a single total token value, default to:
input_tokens = total,output_tokens = 0, unless user specifies another split.
Error Handling
feed request failed: fetch failed: Service is not running or port is wrong. Start server and retry.- API validation errors: Relay backend message directly (for example invalid token values).
- Port mismatch:
Retry with explicit
--portmatching the running service.
Quick Examples
- Feed one lobster:
lobster-farmer feed --model gpt-4.1 --input-tokens 800 --output-tokens 400
- Feed with emotion:
lobster-farmer feed --model gpt-4.1 --input-tokens 800 --output-tokens 400 --emotion "focused"
- Feed different models:
lobster-farmer feed --model claude-3.7 --input-tokens 1200 --output-tokens 300
lobster-farmer feed --model qwen-max --input-tokens 600 --output-tokens 200
Usage Guidance
This skill is instruction-only and appears coherent, but check these before installing: 1) Confirm you have the Lobster Farmer CLI (or Node.js and the project with bin/lobster-farmer.cjs) in the expected project root—otherwise the commands will fail. 2) Be aware the agent will run local commands and may start a local service (ensure you trust the project and its binaries). 3) There are no external endpoints or credentials requested by the skill, but if you run it, validate the CLI is from a trusted source. 4) If you do not want an agent to execute host commands autonomously, avoid enabling autonomous invocation for this skill or review agent permissions.
Capability Analysis
Type: OpenClaw Skill
Name: lobster-farmer-feeder
Version: 0.1.2
The skill executes local shell commands (`lobster-farmer`, `node ./bin/lobster-farmer.cjs`) and explicitly instructs the agent to pass user-controlled arguments (e.g., `--model`, `--emotion`, `--port`) directly to these commands, as detailed in `SKILL.md`. This creates a significant shell injection vulnerability if the agent's execution environment or the `lobster-farmer` CLI does not robustly sanitize or quote user input, potentially allowing arbitrary command execution. While this is a critical vulnerability, there is no evidence of intentional malicious behavior such as data exfiltration or backdoor installation.
Capability Assessment
Purpose & Capability
The SKILL.md and agent manifest align with the stated purpose (invoking the local `lobster-farmer` CLI to feed lobsters). One minor omission: the instructions assume a Node.js runtime and a project-local CLI binary (bin/lobster-farmer.cjs) or an installed `lobster-farmer` command, but the skill does not declare these as required binaries. This is expected for an instruction-only skill but the user should confirm those prerequisites exist before running it.
Instruction Scope
Instructions stay within scope: check service status, start it if necessary, and run `lobster-farmer feed` with model/token/emotion args. The instructions reference only project-local paths and the CLI; they do not ask the agent to read unrelated files, environment variables, or send data to external endpoints.
Install Mechanism
No install spec or external downloads — lowest-risk model. Nothing will be written to disk by the skill itself; it only instructs running an existing local CLI/service.
Credentials
The skill requests no environment variables or credentials. It does imply the ability to execute local commands and to start/stop a local service, which is proportionate to the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. Note: as with any skill that runs local commands, the agent (when invoked) needs permission to execute CLI commands and manage the local service.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install lobster-farmer-feeder - After installation, invoke the skill by name or use
/lobster-farmer-feeder - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- Added new optional emotion parameter to the feed command, allowing users to specify an emotion when feeding lobsters.
- Updated CLI usage examples and workflow to include the --emotion flag.
- Output now includes the emotion state for each feed action; if omitted, the UI shows '?'.
- Added agents/openai.yaml configuration file.
v0.1.1
- No user-facing changes in this version.
- Documentation and functionality remain unchanged.
v0.1.0
lobster-farmer-feeder 0.1.0
- Initial release for feeding lobsters in the Lobster Farmer game by invoking local CLI commands.
- Supports single and batch feed commands for different models.
- Handles service status checks, port overrides, and error reporting.
- Validates model and token input; summarizes results after each feed.
Metadata
Frequently Asked Questions
What is Lobster Farmer Feeder?
Feed lobsters in the Lobster Farmer game by calling the local CLI command `lobster-farmer feed` with `--model`, `--input-tokens`, `--output-tokens`, and opti... It is an AI Agent Skill for Claude Code / OpenClaw, with 427 downloads so far.
How do I install Lobster Farmer Feeder?
Run "/install lobster-farmer-feeder" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Lobster Farmer Feeder free?
Yes, Lobster Farmer Feeder is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Lobster Farmer Feeder support?
Lobster Farmer Feeder is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Lobster Farmer Feeder?
It is built and maintained by MuRong (@murongg); the current version is v0.1.2.
More Skills