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
- Very specific: line 21
Read package.json to detect package manager (packageManager field, lockfile), framework (dependencies), and test commands (scripts)
- Very specific: line 33
Create the process folder structure (process/context/, process/development-protocols/, process/features/{name}/active/, …
- Very specific: line 41
When the project already has process/, CLAUDE.md with project content, or other prior context:
- Distinctive: line 51
Use helper skills when the assigned setup task actually needs them:
≈ “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.
Files
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
- Read
package.jsonto detect package manager (packageManagerfield, lockfile), framework (dependencies), and test commands (scripts) - Detect monorepo structure:
workspaces,pnpm-workspace.yaml,apps/,packages/ - Scan for existing
process/,docs/,.github/and any context files - Classify as New (no
process/, noall-context.md) or Existing (has prior context) - 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:
- Study what exists FIRST — never overwrite
- Present findings, ask what to keep vs change
- Scaffold additions with approval
- Re-study to fill gaps in
all-context.md - Validate
Helpers
Use helper skills when the assigned setup task actually needs them:
vc-scoutfor codebase discoveryvc-audit-contextfor context routing validationvc-audit-vcfor harness healthvc-generate-contextfor fillingall-context.mdfrom 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]Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- opencue/cuecards★ 6same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- vc:kitSkill
- vc:auditSkill
- vc:autoresearchSkill
- vc:chrome-devtoolsSkill
- vc:context-engineeringSkill
- vc:debugSkill
- vc:docs-seekerSkill
- vc:generate-contextSkill
- vc:generate-planSkill
- vc:mcp-managementSkill
- vc:merge-worktreeSkill
- vc:previewSkill
- vc:problem-solvingSkill
- vc:publishSkill
- vc:repomixSkill
- vc:scoutSkill
- vc:securitySkill
- vc:sequential-thinkingSkill
- vc:stress-testSkill
- vc:tech-graphSkill
- vc:updateSkill
- vc:watzupSkill
- vc:web-testingSkill
- vc:xiaSkill
- vc:kitSkill
- vc:auditSkill
- vc:autoresearchSkill
- vc:chrome-devtoolsSkill
- vc:context-engineeringSkill
- vc:debugSkill
- vc:docs-seekerSkill
- vc:generate-contextSkill
- vc:generate-planSkill
- vc:mcp-managementSkill
- vc:merge-worktreeSkill
- vc:previewSkill
- vc:problem-solvingSkill
- vc:publishSkill
- vc:repomixSkill
- vc:scoutSkill
- vc:securitySkill
- vc:sequential-thinkingSkill
- vc:setupSkill
- vc:stress-testSkill
- vc:tech-graphSkill
- vc:updateSkill
- vc:watzupSkill
- vc:web-testingSkill
- vc:xiaSkill
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.

