claude-agent-workflow-validation SKILL.md skillA
claude-agent-workflow-validation from esonhugh/claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add esonhugh/claude-code/claude-agent-workflow-validation@v0.3.0Pins v0.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- esonhugh/claude-code
- Path
.claude/skills/claude-agent-workflow-validation/SKILL.md- Versions recorded
- 1
- Latest version
- v0.3.0, committed Jul 18, 2026
- Size
- 14,713 bytes
- Repository stars
- 43
- License
- none declared
This skill should be used automatically when the user asks for strict binary-side validation of Agent, Workflow, /deep-research, /code-review, task lifecycle, foreground/background continuation, completion notifications, scheduling, slash-command dispatch, or official/local terminal parity using the latest built-claude and stable scripted tmux pane evidence. It also triggers for Chinese requests mentioning Agent/Workflow 验收、调度、任务生命周期、前后台续跑、通知、并发隔离 or 官方对照. Never substitute parent-assistant…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# tmux CLI Agent/Workflow 验收 通过可审计脚本驱动 tmux 中的最新 `built-claude`，验收只存在于 Claude CLI 进程内的 slash command、Agent、Workflow、任务调度和 TUI 行为。涉及这些行为的实现、修复、回归或验收时自动使用，无须用户再次明确要求 tmux。 ## 不可违反的证据边界 - 被测对象是 tmux 中运行的当前工作区 `built-claude`。 - assistant-side `Agent`、`Workflow`、`Skill`、Task/Run 查询或其他同名工具不能作为 binary-side 证据。 - parent-side Task ID、Run ID、Agent 数、token 和报告不得写入 binary-side 结果表。 - parent-side 成功不能作为 tmux 验收失败后的替代证据。 - assistant-side 工具只用于构建、驱动 tmux、捕获 pane、读取 debug log、检查文件和保存证据。 - slash command 必须输入 `built-claude` stdin，不能作为 shell 命令执行。 - 每份 pane、debug log、输入、Task ID 和 Run ID 必须来自同一次 tmux 运行，禁止拼接不同重试的成功片段。 - 如误启动 parent-side 同名工具，立即停止该调用，从正式结果中排除，并在限制中披露；不得中止仍有效的 binary-side session。 ## 验收入口矩阵 | 目标 | 必须使用的 binary-side 入口 | 禁止替代 | |---|---|---| | slash command | tmux 向 CLI stdin 输入 `/...` | shell 执行、parent Skill | | Agent | 让 tmux 中的 `built-claude` 实际调用 Agent tool | parent Agent tool | | Workflow | 让 tmux 中的 `built-claude` 实际调用 Workflow/WorkflowTool | parent Workflow tool | | deep-research | CLI stdin 输入 `/deep-research ...` | parent 同名 skill/tool | | code-review | CLI stdin 输入 `/code-review ...` | parent 同名 skill/tool | 无法在 binary 中触发的入口必须报告 `not covered`，不能用 parent-side 工具补足。 …
Read the whole file at its exact version.
How to install
mdr add esonhugh/claude-code/claude-agent-workflow-validation@sha256:eb1718c0d4e334daThe line at the top of this page pins the label v0.3.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_d4mt6ah5ab2ccro7)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 18, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (14713 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
esonhugh/claude-code · 43 stars · license none declared · pushed 2026-10-20 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_d4mt6ah5ab2ccro7 GET https://markdownregistry.com/api/v1/resolve?ref=esonhugh/claude-code/claude-agent-workflow-validation GET https://markdownregistry.com/api/v1/blob/eb1718c0d4e334da4dc125deb47d593feb0773bd42feae8c92734b9b5fae4227
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.