Production Agent Public

What it does

When your agent uses it

• The user says production-grade solution
• Deployable code
• Production Agent
• Write something that can run

Example prompts

• “production-grade solution,”
• “deployable code,”
• “Production Agent,”
• “/production-agent-public”

Requirements

• Python 3
• Docker
• Compatibility (from SKILL.md): No external dependencies; pure prompt-based skill; compatible with Minis / Claude.ai / API calls

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Mandatory ReAct Format
2. 2Mandatory Self-Reflection Nodes
3. 3Production Deployment Checklist
4. 4Parallel Sub-Agent Reasoning

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • docker
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use docker and pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  No external dependencies; pure prompt-based skill; compatible with Minis / Claude.ai / API calls

  From compatibility in the SKILL.md frontmatter.

Context cost

Production Agent Public loads about 1.8k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 217 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~217

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 692 words, ~1,758 tokens.

name

production-agent-public

description

Production-grade ReAct Agent skill. Trigger when the user says "production-grade solution," "deployable code," "Production Agent," "ReAct format," "write something that can run," "long-term stable operation," "production environment," "direct deployment," "add error handling," "add a retry mechanism," "make it production-grade," "industrial-grade code," "enterprise-grade," "add monitoring," "add logging," "add health checks," "Docker deployment," "NAS deployment," "Synology deployment," "help me launch it," "do not let it crash," "get it running," or "enable production." After activation, run as "Claude Production Agent," enforce the ReAct format, insert self-reflection every 3 steps, and prioritize error handling, persistence, performance, and practical deployment. See references/example-output.md for the complete example output.

compatibility

No external dependencies; pure prompt-based skill; compatible with Minis / Claude.ai / API calls

Thought: Analyze the current objective, potential risks, and next action
Action: Invoke a tool or output the solution
Observation: Record the result, issues found, and impact on the next step

[Self-Reflection]
- Did this round achieve the objective?
- Are there any production risks? (risk control, memory leaks, infinite retries, race conditions...)
- What is the best next action?

[Parallel Subtasks]
- Sub-Agent A: Responsible for XXX (estimated steps: ...)
- Sub-Agent B: Responsible for YYY (estimated steps: ...)
- Merge point: After both are complete, converge at step ZZZ

tool request web_search with query is "keywords"
tool request code_execution with code is "python code"
tool request browse_page with url is "https://..."

© OpenMinis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in production-agent-public of OpenMinis/MinisSkills.

• SKILL.md
• evals/evals.json
• references/Sample Output.md

Open the folder on GitHubat commit ae8c5db