← 返回 Skills 市场
builtbyecho

Agent Work Receipts

作者 BuiltByEcho · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ 安全检测通过
11
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-work-receipts
功能描述
Provides a safe, auditable AI coding workflow with repo briefs, logged commands, trustable receipts, and CI dry-run planning for transparent handoffs and rev...
使用说明 (SKILL.md)

Agent Work Receipts Skill

Use this meta-workflow when a coding task needs reliable orientation, command evidence, and human-readable proof.

Recommended flow

1. Preflight the repo

npx repo-agent-brief . > AGENT_BRIEF.md
sed -n '1,220p' AGENT_BRIEF.md

For branch handoffs:

npx repo-agent-brief . --diff origin/main > AGENT_HANDOFF.md

2. Run important commands with logs

npx agent-runlog -- npm test
npx agent-runlog -- npm run lint
npx agent-runlog -- npm run build

Use runlogs for noisy debugging and CI reproduction.

3. Produce final receipts

npx @builtbyecho/trustlog run -- npm test
npx @builtbyecho/trustlog verify .trustlog/latest.json

Use Trust Log as concise final evidence for the user, PR, issue, or next agent.

4. If CI is missing, preview before modifying

npx @builtbyecho/add-ci . --tier 2 --dry-run

Only rerun without --dry-run after the user/project owner agrees with the plan.

Decision guide

  • Need orientation? repo-agent-brief.
  • Need full command logs? agent-runlog.
  • Need final proof/receipt? trustlog.
  • Need CI scaffold planning? add-ci --dry-run.

Safety rules

  • Check git identity before commits/pushes.
  • Do not run destructive commands without explicit approval.
  • Keep .agent-runs/, .trustlog/, AGENT_BRIEF.md, and AGENT_HANDOFF.md local unless the user wants them committed or shared.
  • Inspect generated artifacts before public posting; redaction helps but is not a guarantee.
安全使用建议
This skill appears safe and purpose-aligned for auditable coding work. Before using it, be comfortable running the referenced npm packages and your repo’s npm scripts, keep generated logs and receipts local unless intentionally shared, and review any generated artifacts before committing or posting them.
能力评估
Purpose & Capability
The stated purpose—auditable coding handoffs with repo briefs, command logs, trust receipts, and CI planning—matches the recommended commands and generated artifacts.
Instruction Scope
The skill includes clear safety limits, including dry-run CI planning first, explicit approval before destructive commands, and approval before rerunning CI scaffolding without --dry-run.
Install Mechanism
There is no install spec or bundled code, but the workflow relies on unpinned npx-invoked external npm CLIs.
Credentials
Reading the current repo and running npm test/lint/build are proportionate for a coding workflow, but they execute local project scripts and should be used in the intended repository.
Persistence & Privilege
The skill creates persistent local artifacts such as .agent-runs, .trustlog, AGENT_BRIEF.md, and AGENT_HANDOFF.md; it does not request credentials or elevated privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install agent-work-receipts
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agent-work-receipts 触发
  4. 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
v0.1.0
Initial ClawHub publish for the BuiltByEcho end-to-end auditable agent work workflow.
元数据
Slug agent-work-receipts
版本 0.1.0
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

Agent Work Receipts 是什么?

Provides a safe, auditable AI coding workflow with repo briefs, logged commands, trustable receipts, and CI dry-run planning for transparent handoffs and rev... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 11 次。

如何安装 Agent Work Receipts?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-work-receipts」即可一键安装,无需额外配置。

Agent Work Receipts 是免费的吗?

是的,Agent Work Receipts 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Agent Work Receipts 支持哪些平台?

Agent Work Receipts 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Agent Work Receipts?

由 BuiltByEcho(@builtbyecho)开发并维护,当前版本 v0.1.0。

💬 留言讨论