Config GcSAFE

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: config-gc
description: Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.
metadata:
  origin: ECC
---

# Config GC — Garbage Collection for Claude Code Setups

Borrowed from runtime garbage collection: periodically scan for objects that are no longer referenced, redundant, expired, or low-value, and reclaim the space. The critical difference: **here, collection requires a human in the loop. Never delete autonomously.**

## When to Activate

- The user asks to clean up, audit, or slim down their Claude Code configuration
- The user complains about too many skills, noisy hooks, or slow session startup
- A monthly/periodic config review is due
- After installing a large skill pack (e.g. this repo), to reconcile overlaps with existing setup

Do NOT activate for: cleaning project source code (that's refactoring), clearing chat history, or uninstalling Claude Code itself.

## Design Philosophy

1. **Append-only configs leak.** Skills, memory files, hooks, and permission entries only ever get added. Without periodic review they rot silently.
2. **Regular audits beat one-time purges.** Scan every ~30 days, propose a small batch of candidates each time.
3. **Per-channel strategies.** Each accumulation type (skills, hooks, permissions, ...) has its own staleness signals — don't apply one rule everywhere.
4. **Soft-delete first.** Rename to `.disabled` > move to `~/.claude/_gc_trash/` > real deletion. Always keep an undo path.
5. **Forced human-in-the-loop.** Every candidate gets its own `[y/n/skip]` confirmation. No "yes to all" shortcut.
6. **Keep a log.** Every GC run appends to `~/.claude/gc_log.md`: what was touched, why, and how to undo it.

## Scan Channels

| # | Channel | Path | Staleness / redundancy signals |
|---|---------|------|--------------------------------|
| 1 | Skills | `~/.claude/skills/*/` | Heavily overlapping names; never triggered in recent transcripts; domain mismatch with the user's actual work; broken or empty SKILL.md |
| 2 | Memory | `~/.claude/**/memory/*.md` + its index | Multiple index entries for one topic; contents contradicting newer entries; dates that have passed; orphan files missing from the index; sub-100-word fragments that should merge |
| 3 | Hooks | `~/.claude/hooks/` + settings | Scripts present on disk but referenced by no hook config; old versions superseded by rewrites |
| 4 | Permissions | `permissions.allow` in `settings.json` / `settings.local.json` | Duplicate entries; specific entries already covered by a wildcard (e.g. `Bash(git push)` when `Bash(*)` is allowed); one-off grants from past experiments |
| 5 | MCP servers | `~/.claude.json` or project `.mcp.json` | Servers that fail to connect; functional duplicates; long-unused |
| 6 | Scheduled reminders / jobs | wherever the user keeps them | Fired one-shots older than 30 days; jobs whose target scripts no longer exist |
| 7 | Project history | `~/.claude/projects/*/` | Stale handoff snapshots; session records superseded by newer state |
| 8 | Runtime caches | `cache/`, `file-history/`, `logs/`, `shell-snapshots/` | Sort by size and mtime; propose items >30 days old and large |

## Workflow

1. **Scan** all channels (or the subset the user names). Collect candidates with: path, channel, signal that flagged it, size, last-modified.
2. **Rank** by confidence (broken/orphaned = high; merely old = low) and present as a numbered table. Cap each run at ~20 candidates — GC is periodic, not exhaustive.
3. **Confirm one by one.** For each candidate show the evidence, then ask `[y/n/skip]`. The user can stop at any point.
4. **Soft-delete confirmed items**: prefer `.disabled` rename for skills/hooks and `_gc_trash/<date>/` move for files. Permission entries live in JSON (no comments possible): back up the settings file, record each removed entry verbatim in `gc_log.md`, then remove it from the `allow` array with `jq`. Only hard-delete when the user explicitly asks.
5. **Log** the run to `~/.claude/gc_log.md`: timestamp, items actioned, undo instructions.
6. **Report**: reclaimed size, channels still healthy, suggested next review date.

## Example Scan Commands

Orphaned hook scripts (channel 3) — scripts on disk that no hook config references:

```bash
for f in ~/.claude/hooks/*; do
  name=$(basename "$f")
  grep -rq "$name" ~/.claude/settings.json ~/.claude/settings.local.json 2>/dev/null \
    || echo "ORPHAN: $f"
done
```

Redundant permission entries (channel 4) — duplicates, and specific grants shadowed by a wildcard:

```bash
jq -r '.permissions.allow[]' ~/.claude/settings.local.json | sort | uniq -d
if jq -e '.permissions.allow | index("Bash(*)")' ~/.claude/settings.local.json >/dev/null; then
  jq -r '.permissions.allow[]' ~/.claude/settings.local.json \
    | grep '^Bash(' | grep -vF 'Bash(*)'
fi
```

Largest stale caches (channel 8) — `du -k` instead of GNU-only `find -printf`, so it works on macOS/BSD too:

```bash
find ~/.claude/file-history ~/.claude/shell-snapshots -type f -mtime +30 \
  -exec du -k {} + 2>/dev/null | sort -rn | head -20
```

Soft-delete with undo path (capture the date once so the log can't disagree with the directory):

```bash
gc_date=$(date +%Y-%m-%d)
mkdir -p ~/.claude/_gc_trash/$gc_date
mv ~/.claude/skills/dead-skill ~/.claude/_gc_trash/$gc_date/
echo "$(date -Iseconds) moved skills/dead-skill -> _gc_trash/$gc_date/ (undo: mv back)" >> ~/.claude/gc_log.md
```

Removing a confirmed-redundant permission entry (JSON has no comments — back up, log, then edit):

```bash
cp ~/.claude/settings.local.json ~/.claude/settings.local.json.bak
echo "$(date -Iseconds) removed permission entry: Bash(git push) (undo: 

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Config Gc](https://modelsatlas.com/skills/affaan-m/config-gc/badge.svg)](https://modelsatlas.com/skills/affaan-m/config-gc/)

Not your listing, or something out of date? Claim or update your listing.