Skip to content
cccskills
FreePublished on GitHub

install-agentic-stack

Install or update the agentic-stack portable brain in the current project, then verify it. Read by an agent; no human steps required.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md1.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Install agentic-stack (agent-executed)

You are an AI coding agent. Follow these steps in order; stop and report on the first failure.

  1. Detect the harness you are running in (Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Codex, Copilot CLI, Gemini, Hermes, Pi, Antigravity, or standalone Python).
  2. Install the CLI (macOS/Linux):
    brew tap codejunkie99/agentic-stack && brew install agentic-stack
    
    Windows PowerShell: git clone https://github.com/codejunkie99/agentic-stack && .\agentic-stack\install.ps1 <harness>.
  3. From the project root, run agentic-stack <harness> (for example agentic-stack claude-code). Accept the onboarding defaults unless the user told you otherwise.
  4. Verify: agentic-stack doctor . must report no errors, and python3 .agent/tools/show.py --plain must print the brain dashboard.
  5. Optional: register the memory MCP server so other hosts share the brain: claude mcp add agentic-memory -- python3 "$PWD/.agent/tools/memory_mcp.py".
  6. Report the installed version, the adapter wired, and the exact commands you ran. Do not modify .agent/protocols/permissions.md.

Already installed? Run agentic-stack upgrade . to refresh infrastructure without touching memory or skills.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

The English summary is being prepared. Showing the original description.

codejunkie99/agentic-stack2.3KUpdated Oct 13, 2026

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

The English summary is being prepared. Showing the original description.

codejunkie99/agentic-stack2.3KUpdated Oct 13, 2026

See all skills by codejunkie99

Report a problem with this skill