files-buddy

Safe filesystem organization, deduplication, renaming, and cleanup with cloud drive support. Delegates to best-in-class CLI tools. Use for file management. NOT for shell scripts (shell-scripter).

files-buddy 2461 words MIT v1.0.0 wyattowalsh sonnet Custom

Safe filesystem organization, deduplication, renaming, and cleanup with cloud drive support. Delegates to best-in-class CLI tools. Use for file management. NOT for shell scripts (shell-scripter).

Quick Start

Install:

npx skills add wyattowalsh/agents/skills/files-buddy -g

Use: /files-buddy <mode> <path> [options]

Works with Claude Code, Gemini CLI, and other agentskills.io-compatible agents.

What It Does

Safe filesystem organization and cleanup. Delegates to best-in-class CLI tools for deduplication, renaming, archiving, and analysis. Cloud drives (iCloud, Google Drive, Dropbox, OneDrive) are first-class citizens with auto-detection and adjusted safety.

Modes

$ARGUMENTS	Mode	Destructive?
`organize <path>`	organize	Yes (moves)
`clean <path>`	clean	Yes (trash)
`audit <path>`	audit	No (read-only)
`rename <path> <pattern>`	rename	Yes (renames)
`flatten <path>`	flatten	Yes (moves)
`archive <path>`	archive	Yes (moves)
`sanitize <path>`	sanitize	Yes (renames)
`find <path> <query>`	find	No (read-only)
`watch <path> [rules]`	watch	Yes (moves)
`undo <manifest>`	undo	Yes (restores)
`dashboard [path]`	dashboard	No (writes report)
Empty or unrecognized	—	Show mode menu

Critical Rules

Never delete without confirmation — tier determines friction level
Never use rm — local paths go to gomi / OS trash or .files-buddy-trash/ fallback; cloud-tagged paths stage only to .files-buddy-trash/
Never operate outside scope-pinned directory
Never modify hard-blocked paths
Never follow symlinks outside operation boundary
Always create manifest (atomic write) before first operation
Always show blast radius before destructive operations
Respect .gitignore — never move tracked files without confirmation
Audit and find modes are strictly read-only; dashboard only writes a local report file
Prefer CLI tool delegation over reimplementation
Exclude dotfiles by default; .git/ always excluded
Warn about restricted-permission files
Undo must verify BLAKE3 hashes for completed file ops — abort on mismatch or missing hash metadata
Load ONE reference at a time — do not preload all references
Operation whitelist: move, rename, copy, trash, mkdir
TOCTOU: re-validate filesystem state before each batch
Record st_mode and st_ino in manifest metadata
Validate manifest paths on undo — reject paths outside ~/.files-buddy/manifests/
Check tool availability at mode start — fall back to Python, report install command
NEVER auto-delete cloud-synced files — deletion syncs to all devices
Materialize evicted files before size or hash analysis
Rate-limit cloud batch ops — use pueue with throttled parallelism

General
Claude Code

Field	Value
Name	`files-buddy`
License	MIT
Version	1.0.0
Author	wyattowalsh

Field	Value
Model	`sonnet`
Argument Hint	`[mode] [path] [options]`

View Full SKILL.md

---
name: files-buddy
description: >-
  Safe filesystem organization, deduplication, renaming, and cleanup with
  cloud drive support. Delegates to best-in-class CLI tools. Use for file
  management. NOT for shell scripts (shell-scripter).
argument-hint: "<mode> <path> [options]"
model: sonnet
license: MIT
metadata:
  author: wyattowalsh
  version: "1.0.0"
---

# Files Buddy

Safe filesystem organization and cleanup. Delegates to best-in-class CLI tools for
deduplication, renaming, archiving, and analysis. Cloud drives (iCloud, Google Drive,
Dropbox, OneDrive) are first-class citizens with auto-detection and adjusted safety.

**Scope:** File organization, cleanup, renaming, deduplication, archiving, and analysis.
NOT for shell script generation (shell-scripter), CI/CD pipelines (devops-engineer),
or database work (database-architect).

## Canonical Vocabulary

| Term | Definition |
|------|-----------|
| **dry-run** | Preview via tool's native mode (fclones group, f2 default, organize sim, detox -n) |
| **manifest** | JSON log at `~/.files-buddy/manifests/` enabling undo and discovery |
| **blast radius** | Total file count and size affected by an operation |
| **protected path** | Hard-blocked (system) or escalated-confirmation directory |
| **trash** | Reversible deletion via gomi / OS trash / `.files-buddy-trash/` |
| **scope pin** | Hard boundary = user-referenced directory only |
| **material drift** | Filesystem changed >10% between preview and execution |
| **batch** | Non-overlapping operations; rollback unit |
| **intent contract** | User-confirmed description (not individual file list) |
| **hardlink cluster** | Files sharing same inode — NOT duplicates |
| **tool delegation** | Invoking CLI tool via subprocess; prefer over reimplementation |
| **fallback** | Python stdlib when CLI tool is not installed |
| **evicted file** | Cloud placeholder; must materialize before size/hash analysis |
| **cloud-safe** | Operations adjusted for sync implications |
| **conflict copy** | Duplicate from sync conflict (e.g., `file (1).txt`) |
| **dashboard** | Self-contained HTML visualization opened in browser |

## Dispatch

| $ARGUMENTS | Mode | Destructive? |
|------------|------|-------------|
| `organize <path>` | organize | Yes (moves) |
| `clean <path>` | clean | Yes (trash) |
| `audit <path>` | audit | No (read-only) |
| `rename <path> <pattern>` | rename | Yes (renames) |
| `flatten <path>` | flatten | Yes (moves) |
| `archive <path>` | archive | Yes (moves) |
| `sanitize <path>` | sanitize | Yes (renames) |
| `find <path> <query>` | find | No (read-only) |
| `watch <path> [rules]` | watch | Yes (moves) |
| `undo <manifest>` | undo | Yes (restores) |
| `dashboard [path]` | dashboard | No (writes report) |
| Empty or unrecognized | — | Show mode menu |

### Auto-Detection Heuristic

1. "sort", "organize", "tidy" + path -> **organize**
2. "duplicates", "clean", "dedup", "lint" + path -> **clean**
3. "how big", "usage", "analyze", "scan" + path -> **audit**
4. "rename", "batch rename" + pattern -> **rename**
5. "flatten", "collapse" + path -> **flatten**
6. "archive", "compress", "old files" + path -> **archive**
7. "fix names", "sanitize", "encoding" + path -> **sanitize**
8. "find", "search", "where is" + query -> **find**
9. "watch", "auto-organize", "monitor" + path -> **watch**
10. "undo", "reverse", "restore" + manifest -> **undo**
11. "dashboard", "visualize", "report" -> **dashboard**
12. Ambiguous -> ask which mode

## Structural Constraints

1. **Operation whitelist:** move, rename, copy, trash, mkdir. NEVER `rm`, `chmod`, `chown`.
2. **Scope pinning:** boundary = user-referenced directory only.
3. **Hard-blocked paths:** root/system directories from `references/protected-paths.md`, including `/`, `/System`, `/Library`, `/Applications`, `/usr`, `/bin`, `/sbin`, `/var`, `/etc`, `/private`, `/boot`, `/dev`, `/proc`, `/sys`, `/run`, `/lib`, `/lib64`
4. **Symlink resolution:** `os.path.realpath()` before plan gen. Cycles detected (max 40 hops).
5. **`.git/` always excluded.**
6. **Cloud-safe:** NEVER auto-delete cloud files. Materialize evicted files before analysis.

## Escalated-Confirmation Paths

`~/.ssh`, `~/.gnupg`, `~/.aws`, `~/.config`, `~/.kube`, `~/.local/share/keyrings`, any directory containing `.env`

Require full preview + explicit path naming + warning before any operation.

## Tiered Friction Model

| Tier | Trigger | Friction |
|------|---------|----------|
| **Low** | Rename, move within parent, <10 files | Inline plan, `[y/N]` |
| **Medium** | Cross-dir move, 10-100 files, archive | Summary preview, confirmation |
| **High** | Any trash, recursive, 100+ files, 1 GB+ | Full preview, blast radius, type "yes" |
| **Critical** | Escalated paths, cloud directories | Full preview + path naming + warning |

AI-initiated ops bias one tier higher. Cloud ops always at least Medium.

## Pre-Flight Checks

Run before every mode:

1. **Path resolution** — reject hard-blocked and escalated paths (or escalate friction)
2. **Scope boundary** — confirm scope pin to user-referenced directory
3. **Cloud detection** — check `~/Library/CloudStorage/*`, `~/Library/Mobile Documents/com~apple~CloudDocs`; tag cloud-synced dirs, adjust behavior
4. **Symlink inventory** — flag escapes outside scope, detect cycles
5. **Tool availability** — `command -v fd fclones rmlint f2 dust erd gomi ouch zstd b3sum detox convmv rclone pueue bat watchexec organize 2>/dev/null`; report missing, suggest install
6. **Permission check** — flag restricted files (`stat` for read/write access)
7. **Disk space** — verify free space >= estimated operation size
8. **Git awareness** — detect `.gitignore`, warn before moving tracked files
9. **Case sensitivity** — detect APFS case-insensitive volumes, flag rename collisions
10. **Eviction check** — materialize placeholder files before analysis (`brctl download` for iCloud, access for GDrive stream)

## Mode: organize

Sort files by type, date, project, or custom rules using organize-tool.

1. Generate organize-tool YAML config from user intent. Read `references/organization-strategies.md`
2. Run `organize sim <config>` (dry-run) — parse output, present preview
3. Show blast radius: file count, size, destination structure as tree
4. On confirmation, run `organize run <config>` with manifest logging
5. Report: operations completed, manifest path, `open <dest>` to verify
6. **Fallback:** `shutil.move` with manual rule matching if organize-tool not installed

## Mode: clean

Remove duplicates, lint filesystem, trash temp files.

1. Read `references/duplicate-detection.md`. Run `fclones group --format json <path>` for duplicates
2. Run `rmlint -o json:<tmpfile> <path>` for empty dirs, broken symlinks, orphan files
3. For cloud dirs: use `rclone dedupe --dry-run <remote>:path` (Google Drive duplicate filenames)
4. Present grouped findings: duplicates (with sizes), lint issues, reclaimable space
5. On confirmation, trash selected items via `gomi` (never `rm`). Log to manifest
6. **Fallback:** `hashlib` + `os.walk` for dedup; `os.listdir` for empty dirs

## Mode: audit

Analyze disk usage and find issues. Strictly read-only.

1. Run `dust -j <path>` for disk usage summary (JSON output)
2. Run `erd -l -s rsize <path>` for directory tree with sizes
3. Run `rmlint -o json:<tmpfile> <path>` for lint issues (empty dirs, broken symlinks)
4. For cloud dirs: `rclone size <remote>:path` + `rclone lsjson` (materialize evicted files first)
5. Present: top space consumers, file type distribution, stale files (>1yr untouched), issues
6. Offer transitions: "Clean duplicates?" / "Archive old files?"
7. **Fallback:** `os.stat` + `os.walk` for sizes; `pathlib` for file listing

## Mode: rename

Batch rename with regex, EXIF, ID3 templates using f2.

1. Read `references/rename-patterns.md`. Construct `f2` command from user pattern
2. Run `f2 <flags> <path>` (dry-run by default) — parse rename table
3. Present before/after diff:
   ```diff
   - old-ugly-name_FINAL_v2.pdf
   + 2024-01-project-report.pdf
   ```
4. On confirmation, run `f2 -x <flags>` (execute). Log to manifest
5. For undo: `f2 -u` using f2's native undo support
6. **Fallback:** `re.sub` + `os.rename` with collision detection

## Mode: flatten

Collapse nested directories to a single level.

1. Inventory target dir — build tree, count files, detect naming collisions
2. Plan flat destination with collision resolution (append `-1`, `-2`, etc.)
3. Present preview: tree before vs flat list after, collision resolutions
4. On confirmation, `shutil.move` each file. Log to manifest
5. Clean up empty directories (bottom-up traversal)
6. No CLI tool dependency — Python stdlib only

## Mode: archive

Compress old or unused files.

1. Identify candidates: files untouched >N days (user-specified or default 365)
2. Group by directory or type for archive bundles
3. Run `ouch compress <files> <archive.tar.zst>` (or `zstd` for single files)
4. Present preview: files to archive, compressed size estimate, destination
5. On confirmation, compress and optionally move originals to trash. Log to manifest
6. For cloud: `rclone move <local> <remote>:archive/` for cloud archiving
7. **Fallback:** `tarfile` + `gzip` from Python stdlib

## Mode: sanitize

Fix filenames: remove special characters, fix encoding, normalize Unicode.

1. Run `detox -n <path>` (dry-run) for character cleanup preview
2. Run `convmv -f <from> -t utf-8 --nfc <path>` for encoding normalization preview
3. Present before/after rename table with changes highlighted
4. On confirmation, run `detox <path>` and `convmv --notest -f <from> -t utf-8 --nfc <path>`. Log to manifest
5. **Fallback:** `re.sub` for character cleanup; `unicodedata.normalize` for NFC/NFD

## Mode: find

Smart file search with rich output. Strictly read-only.

1. Translate natural language to `fd` flags: "large PDFs" -> `fd -e pdf --size +10m <path>`
2. Run `fd` command, pipe matches through `bat` for syntax-highlighted preview
3. Present results as markdown table: name, size, modified date, path
4. Offer transitions: "Found 42 PDFs -> organize them?" / "Found duplicates -> clean them?"
5. For cloud dirs: `rclone lsjson <remote>:path --recursive` with `--include`/`--exclude`
6. **Fallback:** `os.walk` with `fnmatch` filtering

## Mode: watch

Auto-organize files on creation using watchexec + organize-tool.

1. Generate organize-tool YAML config from user rules. Read `references/organization-strategies.md`
2. Start watcher: `watchexec -e jpg,png,pdf -- organize run <config>` (background)
3. Register in `~/.files-buddy/watchers.json` for persistence
4. Log all auto-organized files to manifest
5. Subcommands: `watch start <path>`, `watch stop <id>`, `watch list`, `watch status`
6. **Requires:** watchexec + organize-tool (no fallback — notify user to install)

## Mode: undo

Reverse a previous operation using manifest records.

1. If no manifest specified, run `manifest-manager.py list` — show recent operations
2. Load manifest, validate paths are within `~/.files-buddy/manifests/`
3. Verify completed file ops include recorded BLAKE3 hashes and that current files match manifest records — abort on mismatch or missing integrity metadata
4. Reverse operations in reverse order. Restore cloud-tagged manifests from `.files-buddy-trash/`; otherwise restore from gomi / OS trash or `.files-buddy-trash/` fallback
5. Mark manifest status = `undone`. Report restored files
6. **Fallback:** `mv` from `.files-buddy-trash/` if gomi unavailable

## Mode: dashboard

Open a visual HTML dashboard. Analysis stays read-only, but rendering writes a local report file.

1. Run audit analysis (dust, rmlint, fd) to collect data for target path
2. Generate JSON: disk usage treemap, file type distribution, duplicates, large files, stale files, operation history from manifests
3. Run `uv run python skills/files-buddy/scripts/dashboard-renderer.py --data <json-file|-> --output <path> --open`
4. Default dashboard path is `~/.claude/files-buddy/{YYYY-MM-DD}-dashboard.html` unless `--output` is provided
5. Opens in default browser. Includes a self-contained treemap, sortable tables, dark/light theme
6. **Fallback:** Print summary tables in terminal if browser unavailable

## Dry-Run Preview Protocol

Every destructive mode produces a preview before execution:

1. **Tool native dry-run:** `fclones group` (no `--delete`), `f2` (default), `organize sim`, `detox -n`, `ouch compress --dry-run`
2. **Preview table:** Source, destination, operation type, size
3. **Blast radius summary:** Total files, total size, directories affected
4. **Risk indicators:** `🔴` Critical, `🟠` High, `🟡` Medium, `🟢` Low
5. **Confirmation gate:** Tier-appropriate friction (see Tiered Friction Model)

## Execution Protocol

Transaction-batched execution for all destructive modes:

1. **Manifest** — atomic write (`.tmp` -> `os.rename()`) at `~/.files-buddy/manifests/{ts}-{uuid8}-{mode}.json` via `manifest-manager.py create`
2. **Batches** — dirs (parallel) -> files (parallel non-overlapping, `pueue` for cloud) -> empty dir cleanup (sequential)
3. **TOCTOU check** — if material drift >10% between preview and execution, halt and re-preview
4. **State tracking** — runtime may track preview / in-progress state internally, but manifest rows are appended once per finalized operation: `completed` or `failed`
5. **Trash** — local paths: gomi -> OS trash -> `.files-buddy-trash/`; cloud-tagged paths: `.files-buddy-trash/` only. NEVER `rm`
6. **Metadata** — finalized file ops record: source, dest, type, timestamp, BLAKE3 hash (b3sum), size, st_mode, st_ino
7. **Cloud batch** — `pueue` with `parallel 2` + delays to avoid API rate limiting
8. **Failure** — roll back current batch, preserve prior completed batches, manifest status = `partial`
9. **Report** — operations completed, manifest path, undo command
10. **Notify** — desktop notification on completion if operation took >10s (`osascript` / `notify-send`)

## Scaling Strategy

| Scope | Strategy |
|-------|----------|
| <100 files | Direct operation, full preview |
| 100-1,000 files | Batched preview (summary + sample), pueue for parallelism |
| 1,000-10,000 files | Sampling preview (10%), batched execution, progress tracking |
| 10,000+ files | Sampling preview (1%), pueue queued batches, parallel subagents |

Cloud directories: halve the parallelism, double the batch delays.

## Reference Files

Load ONE reference at a time. Do not preload all references into context.

| File | Content | Read When |
|------|---------|-----------|
| `references/tool-integrations.md` | CLI interfaces for 20+ tools: fd, fclones, rmlint, f2, dust, erdtree, gomi, ouch, zstd, b3sum, detox, convmv, rclone, pueue, bat, watchexec, organize-tool, czkawka_cli. Install commands per platform. Output parsing. | Pre-flight tool detection |
| `references/cloud-drives.md` | Detection paths (macOS CloudStorage, iCloud Mobile Documents), brctl/fileproviderctl, evicted file handling, rclone backends, Google Drive dedupe, conflict copies, rate limiting | Pre-flight cloud detection |
| `references/organization-strategies.md` | organize-tool YAML templates, extension-to-category mapping, date grouping, project detection, collision handling | Organize mode, watch mode |
| `references/protected-paths.md` | Hard-blocked paths (macOS + Linux), escalated paths, validation algorithm, `.git/` exclusion | Pre-flight checks |
| `references/duplicate-detection.md` | fclones JSON parsing, rmlint lint types, rclone dedupe modes, hardlink detection, zero-byte exclusion, NFC/NFD gotchas | Clean mode |
| `references/rename-patterns.md` | f2 patterns (regex, EXIF `{xt.make}`, ID3 `{id3.artist}`, hash `{hash.blake3}`), CSV batch, conflicts, f2 undo | Rename mode |
| `references/safety-workflow.md` | Manifest schema, atomic writes, trash hierarchy, TOCTOU drift, cloud safety rules, permission restoration, corruption recovery | Undo mode, execution protocol |

| Script | When to Run |
|--------|-------------|
| `scripts/manifest-manager.py` | Create, list, search, validate, and close manifests — all destructive modes |
| `scripts/dashboard-renderer.py` | Inject JSON data into HTML template, open browser — dashboard mode |

| Template | When to Render |
|----------|----------------|
| `templates/dashboard.html` | After audit analysis — inject data JSON into `<script id="data">` tag |

## Critical Rules

1. Never delete without confirmation — tier determines friction level
2. Never use `rm` — local paths go to gomi / OS trash or `.files-buddy-trash/` fallback; cloud-tagged paths stage only to `.files-buddy-trash/`
3. Never operate outside scope-pinned directory
4. Never modify hard-blocked paths
5. Never follow symlinks outside operation boundary
6. Always create manifest (atomic write) before first operation
7. Always show blast radius before destructive operations
8. Respect `.gitignore` — never move tracked files without confirmation
9. Audit and find modes are strictly read-only; dashboard only writes a local report file
10. Prefer CLI tool delegation over reimplementation
11. Exclude dotfiles by default; `.git/` always excluded
12. Warn about restricted-permission files
13. Undo must verify BLAKE3 hashes for completed file ops — abort on mismatch or missing hash metadata
14. Load ONE reference at a time — do not preload all references
15. Operation whitelist: move, rename, copy, trash, mkdir
16. TOCTOU: re-validate filesystem state before each batch
17. Record st_mode and st_ino in manifest metadata
18. Validate manifest paths on undo — reject paths outside `~/.files-buddy/manifests/`
19. Check tool availability at mode start — fall back to Python, report install command
20. NEVER auto-delete cloud-synced files — deletion syncs to all devices
21. Materialize evicted files before size or hash analysis
22. Rate-limit cloud batch ops — use pueue with throttled parallelism

Download from GitHub

Resources

All Skills Browse the full skill catalog.

CLI Reference Install and manage skills.

agentskills.io The open ecosystem for cross-agent skills.

View source on GitHub