agentleFS
Sign inStart free
AIWanderAIWander/Programmer-Wander/skills/programmer-getting-started/SKILL.md

programmer-getting-started

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

Install, connect, verify, and troubleshoot AIWander Programmer-Wander as a local Windows MCP server and optional Codex or Claude plugin. Use when setting up Programmer-Wander, choosing an x64 or ARM64 build, registering its MCP process with an AI host, checking whether the tools loaded, or diagnosing a missing or mismatched Programmer tool surface.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Treat the plugin, skill, executable, and host connection as separate layers.

    line 8
  2. Very specific:

    Do not silently edit another AI's config or hooks.

    line 15
  3. Distinctive:

    Read the host application guide when the target UI is unclear.

    line 18
  4. Very specific:

    Run programmer.exe --version in a terminal to prove the executable resolves.

    line 22
  5. Very specific:

    Treat live tools/list as authoritative.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Programmer Getting Started

Treat the plugin, skill, executable, and host connection as separate layers. The plugin supplies guidance and MCP registration metadata; programmer.exe supplies the tools; the AI host decides whether either is loaded.

Connect it safely

  1. Obtain the release matching the Windows architecture and place programmer.exe in a stable directory on PATH.
  2. For a plugin-capable local host, install this repository as the plugin root so it can discover .codex-plugin/ or .claude-plugin/, .mcp.json, and skills/.
  3. For a local MCP host without plugin support, use .mcp.json as the template and add the entry through that host's own UI or documented configuration flow.
  4. Do not silently edit another AI's config or hooks. The executable's install --target command is an explicit config mutation; run it only when the user asks for that target to be changed.
  5. Restart or reload the host, request tools/list, and confirm the server identity before using mutation or command tools.

Read the host application guide when the target UI is unclear.

Verify the connection

  • Run programmer.exe --version in a terminal to prove the executable resolves.
  • Inspect the host's MCP status or logs for a successful stdio launch.
  • Treat live tools/list as authoritative. This release candidate defines exactly 49 unique tools in src/tools/mod.rs, including cmd; a different live count or legacy command-tool name means the binary and source revision differ.
  • Confirm the target architecture when Windows reports an invalid executable or immediate process exit.

Diagnose by layer

SymptomCheck
Skill appears but no Programmer tools.mcp.json, executable resolution, host MCP logs
Tools appear but skill does notPlugin or skill installation path and host skill discovery
Local terminal works but a web AI cannot connectA local stdio process is not remotely reachable; use an authenticated remote MCP bridge
Tool count or schema differsCompare live tools/list with the installed binary version and source revision
A command is deniedRead the returned safety reason; do not bypass it with another shell wrapper

Boundaries

Programmer-Wander is a local development surface. It does not add browser clicking, OCR, credential storage, durable knowledge recall, or multi-agent orchestration. Route those abilities to a tool that actually owns them.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free