repo-cleanup-agent-directories

Sub-skill of repo-cleanup: Agent Directories (+4).

5 stars

Best use case

repo-cleanup-agent-directories is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Sub-skill of repo-cleanup: Agent Directories (+4).

Teams using repo-cleanup-agent-directories should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agent-directories/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_internal/meta/repo-cleanup/agent-directories/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/agent-directories/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How repo-cleanup-agent-directories Compares

Feature / Agent	repo-cleanup-agent-directories	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Sub-skill of repo-cleanup: Agent Directories (+4).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Agent Directories (+4)

## Agent Directories


Multiple agent-related directories should consolidate to `.Codex/agents/`.

**Before:**
```
root/
├── agents/
├── .agents/
├── agent_configs/
└── .agent-os/
```

*See sub-skills for full details.*

## Runtime/Coordination Data


- Session state files
- Coordination lock files
- Runtime cache
- Worker state

**Commands:**
```bash
# Create runtime directory

# Move runtime files (don't use git mv - these are untracked)
```

## Prototype Code


Prototype and experimental code should go to `examples/prototypes/`.

**Commands:**
```bash
mkdir -p examples/prototypes
git mv prototype_*.py examples/prototypes/
git mv experimental/ examples/prototypes/
```

## Test Outputs


Test output files should go to `tests/outputs/` (gitignored).

**Commands:**
```bash
mkdir -p tests/outputs
mv tests/*.html tests/outputs/
mv tests/*.json tests/outputs/
mv tests/test_results/ tests/outputs/
```

## Plan Files


Completed specification plans should be archived.

**Pattern:**
- Active plans: `specs/modules/<plan>.md`
- Completed plans: `specs/archive/<plan>.md`

**Commands:**
```bash
# Archive completed plan (check status: completed in YAML frontmatter)
mkdir -p specs/archive
git mv specs/modules/<completed-plan>.md specs/archive/
```

Related Skills

interactive-report-generator

from vamseeachanta/workspace-hub

Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.

data-validation-reporter

from vamseeachanta/workspace-hub

Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.

repo-ecosystem-hygiene

from vamseeachanta/workspace-hub

Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.

mnt-analysis-cleanup

from vamseeachanta/workspace-hub

Survey, classify, and clean up `/mnt/local-analysis/` (or any sibling-to-workspace-hub directory holding orphan worktrees, codex-burn artifacts, agent log accumulations, and outer-clone duplicates) without losing useful code/work. Surfaces a tiered approval menu rather than baking decisions; defers all destructive ops until user confirms.

orcaflex-reporting-fixture-proof-pattern

from vamseeachanta/workspace-hub

Build and extend fixture-backed OrcaFlex reporting proof paths in digitalmodel using stable metadata baselines, normalized HTML snapshots, and reusable reporting test helpers.

pre-completion-cleanup-audit

from vamseeachanta/workspace-hub

Audit and dispose of session residue (orphan files, scratch dirs, sibling-repo state, locks, trash-stages) BEFORE claiming a task complete. Required gate before any agent says "all done", "task complete", or hands work back to user/orchestrator.

repo-sync

from vamseeachanta/workspace-hub

Smart repository synchronization across workspace-hub ecosystem — diagnoses and fixes pull failures (detached HEAD, diverged branches, uncommitted changes)

repo-structure

from vamseeachanta/workspace-hub

Canonical source layout, test mirroring, root cleanliness, gitignore, docs classification, and committed artifact rules for all workspace-hub tier-1 repos. Consult before creating directories or files in any submodule.

repo-portfolio-steering

from vamseeachanta/workspace-hub

Generate a one-page portfolio steering report for workspace-hub. Use when the user invokes /repo-portfolio-steering, asks about harness vs engineering balance, wants a portfolio health check, or asks which repos to fund next. Reports on portfolio steering, GTM readiness, and provider activity balance.

repo-mission-portfolio-audit

from vamseeachanta/workspace-hub

Audit the workspace-hub repo portfolio to extract each repo's mission, identify documentation gaps, and prioritize a plan/approval sequence with explicit LLM-wiki weighting for future issue triage.

mixed-ops-vs-repo-fix-plan-boundary

from vamseeachanta/workspace-hub

Plan mixed operational-vs-repo remediation issues by proving live-state classification first, then only proposing code changes for confirmed repo-owned failure paths.

repo-separation-for-sensitive-data

from vamseeachanta/workspace-hub

Architecture pattern for splitting confidential data and reusable algorithms across repos