← 返回 Skills 市场

openclaw context usage

Name: openclaw context usage
Author: goog

作者 Jay · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

178

总下载

当前安装

版本数

在 OpenClaw 中安装

/install context-usage

功能描述

Check current session's context window usage. Shows model name, estimated token usage, and context window utilization percentage. Use when user asks about co...

使用说明 (SKILL.md)

Context Window Usage

How to Check

Call session_status to get current session info
Extract the 📚 Context: line for usage data
Present a clean summary to the user

Output Format

📊 Context Window
Model: \x3Cmodel_name>
Used: \x3Cused> / \x3Ctotal> (\x3Cpercent>%)
Cache: \x3Ccache_hit>% hit · \x3Ccached_tokens> cached
Status: 🟢 Comfortable | 🟡 Getting Full | 🔴 Near Limit

Thresholds

Usage	Status	Action
\x3C50%	🟢 Comfortable	No action needed
50-70%	🟡 Getting Full	Monitor
70-85%	🟠 Consider compact	Suggest `/compact`
>85%	🔴 Near limit	Recommend `/compact`

Notes

session_status provides exact context data via the 📚 Context: field
Token counts and cache hit rates are also available
If usage is high, suggest running op-helper skill for /compact

安全使用建议

This skill is narrowly focused and appears safe: it only asks the agent to call session_status (platform session metadata) and display token/context usage. It requires no installs or credentials. Before installing, confirm you are comfortable with the agent having access to session metadata (token counts/cache rates). Also note the skill may recommend running an 'op-helper' skill to compact context — review/trust that helper before following its recommendation.

功能分析

Type: OpenClaw Skill Name: context-usage Version: 1.0.0 The skill bundle is a utility designed to monitor and report on the AI agent's context window usage. It provides instructions for the agent to call a 'session_status' tool and format the resulting token usage data for the user, with no evidence of malicious intent, data exfiltration, or unauthorized execution.

能力评估

✓ Purpose & Capability

Skill name/description (context usage) match the runtime instructions: call session_status, parse the '📚 Context:' line, and present a summary. No unrelated binaries, env vars, or paths are requested.

✓ Instruction Scope

SKILL.md only instructs obtaining session metadata via session_status and formatting a summary. It does not ask to read files, secrets, or unrelated system state. It does reference recommending the 'op-helper' skill for /compact, which is an expected follow-up action and not an immediate scope expansion.

✓ Install Mechanism

No install spec or code files are included; this is instruction-only and therefore does not write or execute new code on disk.

✓ Credentials

No environment variables, credentials, or config paths are required. Requested access (session_status) is proportional to the stated goal of reporting context usage.

✓ Persistence & Privilege

always is false and the skill does not request persistent presence or modification of other skills/config. Model invocation is allowed (the platform default) but that is expected for a user-invocable utility skill.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install context-usage
安装完成后，直接呼叫该 Skill 的名称或使用 /context-usage 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the "Context Window Usage" skill. - Lets users check the current session's context window usage, model name, token usage, and utilization percentage. - Displays a clear summary with usage status: Comfortable, Getting Full, Consider Compact, or Near Limit. - Advises users to compact context when nearing the limit and offers guidance on next steps. - Responds to queries about context window, token usage, or how much of the model’s context is in use.

元数据

Slug context-usage

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题