Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计通过

clankerhiveclankerhive 分析

Agent Skill

clankerhive 用于处理数据库查询、表结构、迁移和数据维护任务,适合在 OpenClaw 中需要分析 schema、编写 SQL 或排查数据问题时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,326

周安装

140

GitHub Stars

公开资料未说明

下载量

1,165
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:clankerhive(clankerhive 分析)
来源仓库:https://github.com/pfrederiksen/clankerhive
安装命令:
openclaw skills install clankerhive
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install clankerhive

简介

clankerhive 基于共享 SQLite 数据库实现多会话代理间的上下文协调与状态同步。

  • 适用于多 Agent 协作任务中的记忆共享与进度跟踪场景。
  • 通过 clawhub 安装后可在 OpenClaw 中读写公共上下文表。
  • 需统一管理数据库锁机制以防止并发写入冲突。
  • 生产环境建议使用加密存储保护敏感会话信息。

SKILL.md

name
clankerhive
description
Shared SQLite-backed context store for multi-session agent coordination. Use when: (1) checking if work was already done recently (email checked, briefing sent), (2) preventing duplicate cron/heartbeat runs via task claiming, (3) passing alerts between sessions (cron queues alert → main session pops it), (4) storing short-lived facts with TTL, or (5) any cross-session state sharing. Replaces ad-hoc JSON state files with a proper coordination bus. Triggers on: deduplication, cross-session state, shared facts, alert queue, task coordination, heartbeat state.
homepage
https://github.com/pfrederiksen/clankerhive
metadata

🐝 ClankerHive

Shared context store for OpenClaw multi-session coordination. Three primitives:

  1. Facts — key/value pairs with optional TTL (auto-expire)
  2. Alerts — cross-session notification queue (producer/consumer)
  3. Tasks — claim-based deduplication for in-flight work

All backed by a single SQLite database in WAL mode (safe for concurrent access).

Setup

No dependencies beyond Python 3 stdlib. The DB is created automatically on first use.

# Default DB location: ~/.openclaw/hive.db
# Override with environment variable:
export CLANKERHIVE_DB=/path/to/custom/hive.db

Resolve the script path relative to this skill directory:

HIVE="python3 $(dirname "$0")/../scripts/clankerhive.py"
# Or use absolute path from skill install location

Facts — Key/Value with TTL

Store short-lived coordination state. Expired facts are auto-pruned on every read.

# Set a fact (lives forever unless --ttl is given)
python3 scripts/clankerhive.py set email.last_check "$(date +%s)" --ttl 900

# Read it back (empty output if missing/expired)
python3 scripts/clankerhive.py get email.last_check

# List all facts matching a prefix
python3 scripts/clankerhive.py list --prefix email

# Delete a fact
python3 scripts/clankerhive.py delete email.last_check

# Tag who set it (useful for debugging)
python3 scripts/clankerhive.py set weather.checked "1" --ttl 3600 --source heartbeat

Pattern: Skip-if-recent

Before doing expensive work, check if it was done recently:

LAST=$(python3 scripts/clankerhive.py get email.last_check)
if [ -z "$LAST" ]; then
    # Do the work, then record it
    python3 scripts/clankerhive.py set email.last_check "$(date +%s)" --ttl 900
fi

Alerts — Cross-Session Queue

Cron jobs or sub-agents produce alerts; the main session consumes them.

# Queue an alert (from cron job)
python3 scripts/clankerhive.py queue-alert email "urgent: server down — production alert from monitoring"

# List unclaimed alerts
python3 scripts/clankerhive.py list-alerts

# Claim and return all pending alerts (marks them claimed)
python3 scripts/clankerhive.py pop-alerts

# Claim only alerts for a specific topic
python3 scripts/clankerhive.py pop-alerts --topic email

# Clean up old claimed alerts (default: older than 24h)
python3 scripts/clankerhive.py purge-alerts --age 86400

Pattern: Cron → Main Session Handoff

Cron job detects something important:

python3 scripts/clankerhive.py queue-alert calendar "Standup with the platform team in 30 minutes"

Main session heartbeat checks for alerts:

ALERTS=$(python3 scripts/clankerhive.py pop-alerts)
# Process and notify user if non-empty

Tasks — Deduplication

Prevent multiple sessions from doing the same work simultaneously.

# Try to claim a task (exit 0 = got it, exit 1 = someone else has it)
python3 scripts/clankerhive.py claim-task daily-briefing-2026-04-01
# stdout: "ok" or "already-claimed by <owner>"

# Release when done
python3 scripts/clankerhive.py release-task daily-briefing-2026-04-01 --result "sent to telegram"

# Check status
python3 scripts/clankerhive.py task-status daily-briefing-2026-04-01

Pattern: Idempotent Cron

if python3 scripts/clankerhive.py claim-task "morning-briefing-$(date +%Y-%m-%d)"; then
    # Do the work...
    python3 scripts/clankerhive.py release-task "morning-briefing-$(date +%Y-%m-%d)" --result "done"
else
    echo "Already running or completed"
fi

Stats

Quick summary of the hive state:

python3 scripts/clankerhive.py stats

Returns JSON with counts for facts, pending/claimed alerts, and claimed/done tasks.

Replacing heartbeat-state.json

Instead of maintaining a separate memory/heartbeat-state.json file, use ClankerHive facts:

# Old way: read/write JSON file
# New way:
python3 scripts/clankerhive.py set heartbeat.email "$(date +%s)" --ttl 1800
python3 scripts/clankerhive.py set heartbeat.calendar "$(date +%s)" --ttl 3600
python3 scripts/clankerhive.py set heartbeat.weather "$(date +%s)" --ttl 7200

# Check when something was last done:
python3 scripts/clankerhive.py get heartbeat.email
# Empty = time to check again

Notes

  • DB path configurable via CLANKERHIVE_DB env var (default: ~/.openclaw/hive.db)
  • WAL mode ensures safe concurrent reads/writes from multiple processes
  • All list/query commands output JSON; scalar commands output plain text
  • Exit code 0 = success, 1 = error (already-claimed, not-found, etc.)
  • No external dependencies — pure Python stdlib

System Access

Reads: Nothing — no files, env vars, or network beyond the SQLite DB.

Writes: Only to the SQLite database file at $CLANKERHIVE_DB (default ~/.openclaw/hive.db). Creates parent directories if they don't exist. The default path (~/.openclaw/) is typically mode 700 on OpenClaw installs, meaning only the owning user can read the DB. If you change CLANKERHIVE_DB to a shared or world-readable location, restrict permissions manually: chmod 600 hive.db.

Network: None. No outbound connections of any kind.

Imports: argparse, json, os, sqlite3, sys, time, typing — all Python stdlib. No third-party packages, no subprocess calls, no eval/exec.

Source: <https://github.com/pfrederiksen/clankerhive>

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

70.4%
按下载量换算820

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills