# MyAgent

**Repository Path**: knifecms/my-agent

## Basic Information

- **Project Name**: MyAgent
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-09-17
- **Last Updated**: 2026-09-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Reader Kit — My Agent: From Chat to a Reviewable AI Workbench

This folder is the downloadable companion to **My Agent: From Chat to a Reviewable AI Workbench**
(author: Zeal). It collects every template referenced in the book in one place, so you can copy
them straight into Markdown, Notion, Feishu/Lark docs, or the `templates/` folder of your own
workbench.

## How to use

1. Read the chapter that introduces a template.
2. Copy the matching `.md` file below into your workbench folder.
3. Fill it in as you run a real task. The form *is* the process material — task, evidence, change,
   and the human confirmation points.

## Templates

| File | Used in | Purpose |
|------|---------|---------|
| task-map.md | Ch.3 | Plan a task so a human can see and inspect it |
| evidence-ledger.md | Ch.4 | Record each claim with strength + verification status |
| change-ledger.md | Ch.5 | Log what the agent changed, and how to undo it |
| code-review-flow.md | Ch.7 / Ch.8 | Human-in-the-loop review flow for AI-written code |
| data-analysis-ledger.md | Ch.9 | Keep a data task's plan and checks reviewable |
| notebook-checklist.md | Ch.10 | A checklist for recomputing a key number in a Notebook |
| research-evidence-matrix.md | Ch.11 | Bind every conclusion to a source and a challenger |
| handoff-protocol.md | Ch.12 | Hand work to a reviewing agent with a clear spec |
| personal-workbench-structure.md | Ch.13 | Folder structure for your personal agent workbench |
| team-agent-delivery-spec.md | Ch.14 | Delivery spec for a team agent workbench |
| adversarial-review-prompt.md | Ch.6 | A prompt that probes an agent's expansion and takeover signals |
| agent-extension-log.md | App. E | Log every skill, plugin, or Codex self-optimization under the four objects |

## License

Free to use and adapt for your own work. Attribution appreciated.