gc

A command that finds session state files not updated for a chosen number of days and lists or deletes them. It previews the files by default; deletion requires an explicit apply option.

In plain words
What is it for?
Use it to inspect or remove stale session state files, choose an age threshold, and see how many files and bytes are affected.
Why use it?
Long-running use can leave many old JSON files behind. It helps clean up unused session data while keeping the default operation non-destructive.

Command

Part of the cc-enforcer plugin — 2 skills, 6 commands, 1 agent, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/skymanbp/cc-enforcer/gc
Clone the repo
git clone --depth 1 https://github.com/skymanbp/cc-enforcer

Or install cc-enforcer, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 1 agent, 4 hooks.

Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.01096
Opus 5 $0.00030 $0.00548
Sonnet 5 $0.00012 $0.00219
Haiku 4.5 $0.00006 $0.00110

Measured 3d ago against content hash 43ab5a503570, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/gc.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cc-enforcer:gc

长期使用插件后,${CLAUDE_PLUGIN_DATA}/sessions/ 下会累积每会话一个 JSON 状态文件。每个文件几 KB,但数量积起来值得清理。本命令调用 hooks/scripts/gc_state.py 按 mtime 阈值 列出 / 删除老旧 state。

安全默认

本命令默认替你补 --dry-run(只打印不删除),要真正删除必须显式改成 --apply。注意"默认"只存在于本命令这一层:gc_state.py 自己要求 --dry-run / --apply 恰好传一个,一个都不传(或两个都传)它会打印 gc_state: pass exactly one of --dry-run or --apply 并 exit 1,而不是退回 dry-run —— 无标志时永不删除,是靠"拒绝执行"实现的。 mtime 是该会话状态最近一次被写入的时间戳 —— 不只是 Read:记录编辑、 Stop 拦截、滚动补丁计数、mtime 基线、同步 ack 等九个以上的 mutator 都会 刷新它。所以一个只改文件、不读新文件的会话同样是"活跃"的。30 天没有任何 写入的,几乎肯定是已死会话。

你(receiving agent)要做的

按用户传入的参数构造 Bash 调用:

python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/gc_state.py" --dry-run --older-than 30

或:

python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/gc_state.py" --apply --older-than 30

参数解释:

  • --dry-run / --apply:互斥,且必须恰好传一个;都不传 → exit 1(不是 隐式 dry-run)。用户没说要删时,本命令替他传 --dry-run
  • --older-than DAYS:阈值(天数)。默认 30。

输出契约

脚本始终打印:

state_dir: <path>
scanned:   <N>
threshold: <M> days
eligible:  <K>
  [dry-run] would delete: <name>  (<age>d old, <size>B)   |   deleted: <name>
  ...
deleted: <K>     |   would delete: <K>
bytes_freed: <B> |   would free: <B>B

用户场景

用户:"/gc 看看"          → dry-run, 默认 30 天
用户:"/gc 看看 90 天的"   → dry-run, --older-than 90
用户:"/gc 真的删 30 天的" → --apply --older-than 30

如果 eligible 为 0 → 报告 "nothing to do" 即可。

禁止

  • ❌ 不传任何参数就直接 --apply —— 始终先 dry-run 让用户看清楚再问。
  • ❌ 删除 ${CLAUDE_PLUGIN_DATA}/sessions/ 之外的任何文件 —— 脚本本身有 这道防线(只 glob <state_dir>/*.json),不要绕过它。

自动 GC(v0.18 · opt-in)

设置环境变量 CC_ENFORCER_AUTO_GC_DAYS=N(正整数)即可让 SessionStart 钩子在每次开会话时自动删除 ≥ N 天未触碰的 state 文件。受 24h 速率限制 (marker 文件 <state_dir>/_auto_gc.json),不会每次开会话都重扫。

# Bash / Linux / macOS
export CC_ENFORCER_AUTO_GC_DAYS=30

# PowerShell
$env:CC_ENFORCER_AUTO_GC_DAYS = "30"
[Environment]::SetEnvironmentVariable("CC_ENFORCER_AUTO_GC_DAYS", "30", "User")  # 持久化

未设置 / 设为 0 / 设为非数字 → 自动 GC 完全禁用(默认)。失败 → silent stderr,永不阻塞 SessionStart 注入。/cc-enforcer:gc 手动命令 仍然完全可用,两个入口共用同一份 prune_old_sessions()

Read the full file on GitHub · 93 lines

Changes

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.

  1. 3d ago First seen · 93 lines · 60 tokens per session scan A 43ab5a503570

Subscribe to this mod's changes

gc is a command published in the GitHub repository skymanbp/cc-enforcer (5 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 1,096 once invoked, about $0.0003 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.