← 返回 Skills 市场

Edvisage Agent Ops

Name: Edvisage Agent Ops
Author: edvisage

作者 Edvisage Global · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

100

总下载

当前安装

版本数

在 OpenClaw 中安装

/install edvisage-agent-ops

功能描述

Operational visibility for AI agents — cost tracking, action logging, and performance monitoring.

使用说明 (SKILL.md)

agent-ops — Operational Visibility for AI Agents

By Edvisage Global — the agent safety company

Stop flying blind. agent-ops gives you complete visibility into what your agent is doing, what it's costing, and whether it's working.

What This Skill Does

When installed, your agent gains structured operational awareness — tracking its own costs, logging its actions, and generating reports for you, the owner.

Core Capabilities

1. Cost Tracking Protocol

Before every API call, assess and log:

Model used: Which model is being called (Opus, Sonnet, Haiku, GPT, etc.)
Estimated tokens: Input and output token estimate
Estimated cost: Based on current model pricing
Task classification: Is this a heartbeat, user request, automated task, or sub-agent spawn?

Maintain a running daily cost log in your memory files:

## Daily Cost Log — [DATE]
| Time | Model | Tokens (in/out) | Est. Cost | Task Type | Description |
|------|-------|-----------------|-----------|-----------|-------------|

2. Action Logging

Every significant action gets logged with:

Timestamp: When it happened
Action type: Post, reply, API call, file read, file write, skill use, tool use
Target: Where/what was affected
Outcome: Success, failure, or partial
Cost: If applicable

Log format:

## Action Log — [DATE]
| Time | Action | Target | Outcome | Cost | Notes |
|------|--------|--------|---------|------|-------|

3. Daily Summary Report

At the end of each operating day (or on request), generate a summary:

## Daily Operations Summary — [DATE]

### Cost Breakdown
- Total estimated spend: $X.XX
- By model: [breakdown]
- By task type: [breakdown]
- Highest cost action: [description]

### Activity Summary
- Total actions: X
- Successful: X | Failed: X
- Posts created: X
- Replies sent: X
- API calls made: X

### Alerts
- [Any unusual patterns or cost spikes]

4. Cost Alerts

Flag when:

Daily spend exceeds a threshold (default: $1.00)
A single action costs more than $0.10
Heartbeat/maintenance costs exceed 30% of total spend
Costs are trending higher than the previous 7-day average

5. Model Routing Awareness

When a task could be handled by a cheaper model, note it:

Simple lookups → suggest Haiku/Flash tier
Heartbeats → suggest cheapest available model
Complex reasoning → confirm current model is appropriate
Summarization → suggest mid-tier model

How to Use

Tell your agent: "You have the agent-ops skill installed. Start tracking your costs and actions today."

Ask for reports: "Give me your daily operations summary" or "How much have you spent today?"

Limitations (Free Version)

Manual report requests only (no scheduled delivery)
Basic cost tracking (no historical trend analysis)
Simple action log (no categorized performance metrics)
No spending limit enforcement
No multi-agent cost aggregation

Want automated reports, trend analysis, spending limits, and more? → Upgrade to agent-ops-pro: https://edvisage.gumroad.com/l/[TBD]

About Edvisage Global

We build practical safety and operations tools for AI agents. Our skills are designed for the OpenClaw ecosystem and install in minutes.

Website: https://edvisageglobal.com/ai-tools

安全使用建议

This skill appears to do what it says (tracking costs and actions) and doesn't request credentials or install code, but its instructions are vague about where logs are stored and what exactly gets recorded. Before installing or enabling it: 1) Confirm where 'memory files' and logs will be written and who/what can read them; set a secure storage location and retention policy if possible. 2) Limit or redact sensitive fields from logs (user messages, API responses, credentials). 3) Test the skill in an isolated environment to inspect sample logs and verify no secrets are captured. 4) Verify the publisher (homepage/repo) and prefer a published source you trust. 5) If you enable autonomous use, consider restricting the skill's permissions or turning on manual approval for any actions that could expose data.

功能分析

Type: OpenClaw Skill Name: edvisage-agent-ops Version: 1.0.0 The skill bundle consists of markdown instructions (SKILL.md) directing the AI agent to perform self-monitoring, cost tracking, and action logging. It instructs the agent to maintain local logs of its API usage and task outcomes to provide operational visibility. There is no evidence of data exfiltration, malicious command execution, or harmful prompt injection; all activities are confined to the agent's local environment and align with the stated purpose of the tool.

能力评估

✓ Purpose & Capability

Name, description, and SKILL.md all align: the skill is an instruction-only operations/monitoring helper for agents (cost estimates, action logs, summaries). It requests no binaries, no env vars, and no installs — which is proportionate for a purely protocol/format guidance skill. The only implicit capability assumed is that the agent can observe its own API calls and estimate tokens/costs, which is a plausible requirement for an ops tool.

⚠ Instruction Scope

The SKILL.md tells the agent to log detailed action and cost information 'in your memory files' and to 'assess and log before every API call' including file-read/write events and targets. It does not specify storage locations, retention, or access controls. That vagueness can lead the agent to record sensitive user data, API payloads, or credentials in persistent memory/logs. The instructions do not explicitly tell the agent to transmit logs off-system, but they also do not constrain what to log or who can read the logs.

✓ Install Mechanism

This is instruction-only (no install spec, no code files to execute). No downloads or package installs are requested, which minimizes the risk of arbitrary code being written to disk.

✓ Credentials

No environment variables, credentials, or config paths are requested. That is proportionate to the stated monitoring purpose. However, the skill's logging could cause the agent to capture unrelated sensitive environment data if the agent logs entire inputs or outputs without filtering.

⚠ Persistence & Privilege

always is false and autonomous invocation is allowed by default (normal), but the skill explicitly asks agents to maintain 'running daily cost log in your memory files' and daily action logs. Whether these are ephemeral or persistent depends on the agent's memory implementation; if persistent, the skill can cause accumulation of potentially sensitive transcripts across days. The skill does not request or modify other skills' configs.

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 edvisage-agent-ops
安装完成后，直接呼叫该 Skill 的名称或使用 /edvisage-agent-ops 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 agent-ops 1.0.0: - Adds cost tracking and logging for AI agent operations, including model usage, token estimates, and task classification. - Introduces structured action logging for all major events and API calls. - Provides daily summary reports covering costs, activities, and alerts for unusual patterns. - Implements cost alerts for high spending and inefficiencies. - Suggests model routing to optimize for cheaper or more efficient model usage. - Free version includes manual reports and basic tracking; advanced features available in agent-ops-pro.

元数据

Slug edvisage-agent-ops

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