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

certainlogic-context-tokenreducer特定逻辑上下文 tokenreducer

Agent Skill

certainlogic-context-tokenreducer 用于补充运维相关能力,适合在 OpenClaw 中需要让 Agent 承接运维相关任务时使用。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

2,446

周安装

104

GitHub Stars

公开资料未说明

下载量

857
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:certainlogic-context-tokenreducer(特定逻辑上下文 tokenreducer)
来源仓库:https://github.com/certainlogicai/certainlogic-context-tokenreducer
安装命令:
openclaw skills install certainlogic-context-tokenreducer
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 certainlogic-context-tokenreducer

简介

certainlogic-context-tokenreducer 监控会话代币消耗,防止成本失控。

  • 在阈值触发时发出警告并自动生成密集摘要压缩上下文。
  • 适用于长对话或多轮交互场景中优化 token 使用效率。
  • 安装命令:openclaw skills install certainlogic-context-tokenreducer;可配置告警级别与摘要频率。
  • 摘要质量依赖原始内容密度,关键结论仍需人工复核完整性。

SKILL.md

name
certainlogic-context-manager
license
MIT
description
Prevent AI session token bloat and runaway costs. Tracks query count per session, warns at a configurable threshold, auto-writes a dense handoff summary before reset, and reads it back on the next session start — so no work is lost and every session starts lean. Without session resets, a standard OpenClaw session can balloon from 18K to 400K+ input tokens, multiplying cost 22x. This skill prevents that automatically. Use when managing long AI sessions, reducing token burn, keeping context lean, or implementing session hygiene for any OpenClaw-based agent. Triggers on phrases like "context management", "session reset", "token bloat", "query counter", "handoff", "save context", or "/new". Built by CertainLogic.

Context Manager

Keeps sessions lean. Tracks query count, warns before context bloats, saves a handoff summary so work continues cleanly in the next session.

How It Works

  1. Counter — Increment session_query_count.txt every turn
  2. Warn — At threshold, write handoff.md and alert the user
  3. Reset — User runs /new; next session reads and deletes handoff.md

Files

FilePurpose
session_query_count.txtInteger. Increment each turn. Create if missing (default 0).
handoff.mdWorkspace root. Written at threshold. Read + deleted on next session start.

Every Turn (mandatory)

1. Read session_query_count.txt (default 0 if missing)
2. Increment by 1
3. Write back
4. If count == THRESHOLD: trigger handoff flow

Default threshold: 10. Configurable per deployment.

Handoff Flow (at threshold)

  1. Write handoff.md — see handoff-format.md for exact spec
  2. Tell the user:

> ⚠️ 10 queries in — context is getting heavy. Handoff saved. Run /new when ready to continue.

  1. Do NOT auto-reset. User controls the reset.

Session Start Flow

1. Check if handoff.md exists
2. If exists AND file is < 3 hours old:
   a. Read it
   b. Apply context to current session
   c. Delete handoff.md
3. Reset session_query_count.txt to 0

Topic Switch Detection

When the user says "BTW", "switching gears", "new topic", or starts a clearly unrelated task:

  1. Write/overwrite handoff.md immediately (don't wait for threshold)
  2. Tell the user: *"Handoff saved — /new when ready"*
  3. Resume or continue current task

Why This Matters

Session context is cumulative. Every prior message, tool call, and assistant response is re-sent on every new query. Without resets, a lean 18K-token session becomes 50K–400K+ within hours.

See token-math.md for cost impact data and reset savings estimates.

Commands

CommandBehavior
/new or /resetUser-triggered. New session starts; skill reads handoff.md if present.
/handoffExplicit handoff write. Same as threshold flow, on demand.
/counterReport current query count and threshold.

Configuration

Override defaults in AGENTS.md or equivalent workspace config:

- CONTEXT_THRESHOLD: 10        # Queries before warning (default: 10)
- HANDOFF_TTL_HOURS: 3         # Hours before handoff.md is considered stale (default: 3)

Reliability Rules

  • Never skip the counter increment — even for one-liner responses
  • Never auto-reset — the user owns the session lifecycle
  • Handoff must be written before warning — never warn without saving state first
  • Counter file is source of truth — do not track in memory

What This Saves You

Without this skillWith this skill
Sessions balloon to 400K+ tokensSessions stay under 25K
Cost multiplies 22x over a dayCost stays near baseline
Work lost on manual /new resetsHandoff auto-saved, resumed next session
No signal before context degradesWarning fires before quality drops

See token-math.md for the full cost breakdown.


*Built by CertainLogic — trusted fact infrastructure for AI agents.*

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

75.16%
按下载量换算644

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