agentleFS
Marwan-Ahmed-devMarwan-Ahmed-dev/vibecode-pro-max/.claude/skills/vc-setup/SKILL.md

vc:setup

Skill0 starsChanged 3 months agoMITView on GitHub

Interactive agent harness setup for any project. Detects your stack, asks about your project, scaffolds process directories, deep-scans the codebase, and populates context with real content. Works on fresh projects and existing projects with pre-existing configs — always asks before reorganizing.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Read package.json to detect package manager (packageManager field, lockfile), framework (dependencies), and test commands (scripts)

    line 21
  2. Very specific:

    Create the process folder structure (process/context/, process/development-protocols/, process/features/{name}/active/, …

    line 33
  3. Very specific:

    When the project already has process/, CLAUDE.md with project content, or other prior context:

    line 41
  4. Distinctive:

    Use helper skills when the assigned setup task actually needs them:

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

VibeCo Agent Harness Setup

Interactive setup for the agent development harness. Works on fresh projects and existing projects with pre-existing .claude/ or process/ configs. Asks questions and waits for approval at every major step — never silently reorganizes files or overwrites good content.

CLAUDE.md and AGENTS.md are managed protocol files (orchestrator, RIPER-5, routing). They contain zero project-specific content and should NOT be adapted. Project-specific information lives in process/context/all-context.md, populated during the STUDY phase.

Prerequisite: target repo has a package.json or equivalent manifest.

Workflow (4 phases, see references/vc-setup.md for detail)

Phase 1: DETECT

  1. Read package.json to detect package manager (packageManager field, lockfile), framework (dependencies), and test commands (scripts)
  2. Detect monorepo structure: workspaces, pnpm-workspace.yaml, apps/, packages/
  3. Scan for existing process/, docs/, .github/ and any context files
  4. Classify as New (no process/, no all-context.md) or Existing (has prior context)
  5. Present detection summary, wait for confirmation before proceeding

Phase 2: ASK

For new projects, have an open-ended discovery conversation with the user — start with project identity, then drill into architecture/scope, then workflow/conventions. For existing projects, present findings and ask what to keep vs change. Do not guess when you can ask. Continue until you have thorough understanding.

Phase 3: SCAFFOLD

Create the process folder structure (process/context/, process/development-protocols/, process/features/{name}/active/, process/general-plans/active/). For existing projects, merge with what's already there — never overwrite good content. The install.sh script handles harness file install (.claude/, .codex/, .agents/); process/ layout migration happens here.

Phase 4: STUDY + VALIDATE

Deep-scan the codebase via parallel subagents. Populate process/context/all-context.md with real content (stack, architecture, patterns, conventions). Run validators (vc-audit-context, vc-audit-vc) and fix any routing/discoverability issues.

Existing Project Migration

When the project already has process/, CLAUDE.md with project content, or other prior context:

  1. Study what exists FIRST — never overwrite
  2. Present findings, ask what to keep vs change
  3. Scaffold additions with approval
  4. Re-study to fill gaps in all-context.md
  5. Validate

Helpers

Use helper skills when the assigned setup task actually needs them:

  • vc-scout for codebase discovery
  • vc-audit-context for context routing validation
  • vc-audit-vc for harness health
  • vc-generate-context for filling all-context.md from real content

End every response with the subagent status block:

**Status:** DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
**Summary:** [1-2 sentence summary]
**Files modified:** [comma-separated list]
**Concerns/Blockers:** [if applicable]

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.

Reviews can't be read right now.

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.