Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AndrewDongminYoo/cc-agents-kit --skill config-gcgit clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/config-gc)<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/config-gc"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/config-gc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/config-gc"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/config-gc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02763 |
| Opus 5 | $0.00041 | $0.01381 |
| Sonnet 5 | $0.00016 | $0.00553 |
| Haiku 4.5 | $0.00008 | $0.00276 |
Grade A, and why
config-gc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config GC — Garbage Collection for Claude Code Setups
Borrowed from runtime garbage collection: periodically scan for objects that are no longer referenced, redundant, expired, or low-value, and reclaim the space. The critical difference: here, collection requires a human in the loop. Never delete autonomously.
When to Activate
- The user asks to clean up, audit, or slim down their Claude Code configuration
- The user complains about too many skills, noisy hooks, or slow session startup
- A monthly/periodic config review is due
- After installing a large skill pack (e.g. this repo), to reconcile overlaps with existing setup
Do NOT activate for: cleaning project source code (that's refactoring), clearing chat history, or uninstalling Claude Code itself.
Active Config Root
Derive one root at the start of the run and use it for every scan, backup, soft-delete, and log operation:
ACTIVE_CONFIG_ROOT="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
Do not scan both the default and an override.
When CLAUDE_CONFIG_DIR is set, it is the active root; otherwise use $HOME/.claude.
Design Philosophy
- Append-only configs leak. Skills, memory files, hooks, and permission entries only ever get added. Without periodic review they rot silently.
- Regular audits beat one-time purges. Scan every ~30 days, propose a small batch of candidates each time.
- Per-channel strategies. Each accumulation type (skills, hooks, permissions, ...) has its own staleness signals — don't apply one rule everywhere.
- Soft-delete first. Rename to
.disabled> move to$ACTIVE_CONFIG_ROOT/_gc_trash/> real deletion. Always keep an undo path. - Forced human-in-the-loop. Every candidate gets its own
[y/n/skip]confirmation. No "yes to all" shortcut. - Keep a log. Every GC run appends to
$ACTIVE_CONFIG_ROOT/gc_log.md: what was touched, why, and how to undo it.
Scan Channels
| # | Channel | Path | Staleness / redundancy signals |
|---|---|---|---|
| 1 | Skills | $ACTIVE_CONFIG_ROOT/skills/*/ |
Heavily overlapping names; never triggered in recent transcripts; domain mismatch with the user's actual work; broken or empty SKILL.md |
| 2 | Memory | $ACTIVE_CONFIG_ROOT/**/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 | $ACTIVE_CONFIG_ROOT/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 | $ACTIVE_CONFIG_ROOT/.claude.json or .mcp.json records |
Servers that fail to connect; functional duplicates; long-unused |
| 6 | Scheduled reminders / jobs | job metadata referenced from $ACTIVE_CONFIG_ROOT |
Fired one-shots older than 30 days; jobs whose target scripts no longer exist |
| 7 | Project history | $ACTIVE_CONFIG_ROOT/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 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 170 lines · 81 tokens per session scan A 201422c0826c
config-gc is a skill published in the GitHub repository AndrewDongminYoo/cc-agents-kit (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 2,763 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bash-defensive-patterns
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
setup
One-command setup for usage-guard's real plan quota. Use this whenever the user runs /usage-guard:setup, asks to enable/activate/turn on the real 5-hour and weekly quota reading, asks to wire up the status line, or when /usage-guard:usage shows no "Real plan quota" block (only the weighted fallback). Detects the…
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.
sync-forks
Check how many of your GitHub forks are out of date and sync them.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.