prune-workflows

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Prune Workflows Skill

VCS Provider

This skill's safeguards use VCS operations internally (open PR detection). The orchestrate handler manages VCS provider dispatch automatically. No

gh

glab

az

commands needed — the MCP server handles provider dispatch.

此Skill的防护机制内部使用VCS操作（检测未合并PR）。编排处理程序会自动管理VCS提供商的调度。无需使用

gh

glab

az

命令——MCP服务器会处理提供商调度。

Overview

概述

Bulk-cancel stale non-terminal workflows that have accumulated in the pipeline. Wraps the

prune_stale_workflows

orchestrate action with an interactive dry-run-then-confirm UX so the user always sees the candidate set before any state mutates.

Pruning is a maintenance operation -- not a workflow phase. It produces

workflow.pruned

events alongside the standard

workflow.cancelled

events emitted by the underlying cancel path, so downstream views can distinguish user-intent cancellations from batch cleanup.

批量取消流水线中累积的过时非终端工作流。该Skill为

prune_stale_workflows

编排操作封装了“试运行+确认”的交互式体验，确保用户在任何状态变更前都能查看待清理的候选集。

清理是一项维护操作——而非工作流阶段。除了底层取消流程生成的标准

workflow.cancelled

事件外，它还会生成

workflow.pruned

事件，以便下游视图区分用户主动发起的取消与批量清理操作。

Triggers

触发条件

Activate this skill when:

User runs
```
/prune
```
command
User says "prune workflows", "clean stale workflows", "pipeline cleanup"
```
mcp__exarchos__exarchos_view({ action: "pipeline" })
```
shows many inactive workflows the user wants to clear in bulk

满足以下任一条件时激活此Skill：

用户运行
```
/prune
```
命令
用户说出“prune workflows”“clean stale workflows”“pipeline cleanup”
```
mcp__exarchos__exarchos_view({ action: "pipeline" })
```
显示大量用户想要批量清理的非活跃工作流

Prerequisites

前置条件

An exarchos state directory with one or more non-terminal workflows
For safeguard checks against live PRs:
```
gh
```
available in PATH (the orchestrate handler shells out)
For safeguard checks against branch activity:
```
git
```
available in PATH

存在包含一个或多个非终端工作流的exarchos状态目录
若要针对实时PR执行防护检查：PATH中需存在
```
gh
```
（编排处理程序会调用shell命令）
若要针对分支活动执行防护检查：PATH中需存在
```
git
```

Process

流程

Step 1: Dry-Run Preview

步骤1：试运行预览

Always start with

dryRun: true

. This call performs candidate selection and safeguard evaluation but does not mutate any workflow state.

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: true
  }
})

The response shape is:

{
  candidates: [
    { featureId: string, phase: string, workflowType: string, stalenessMinutes: number }
  ],
  skipped: [
    { featureId: string, reason: "open-pr" | "active-branch" }
  ]
}

Optional args:

```
thresholdMinutes
```
-- staleness cutoff. Default is 10080 (7 days).
```
includeOneShot
```
-- whether to include
```
oneshot
```
workflows in the candidate set. Default
```
true
```
.
```
force
```
-- not relevant in dry-run; only honored in apply mode (Step 4).

始终以

dryRun: true

启动。此调用会执行候选工作流筛选和防护机制评估，但不会修改任何工作流状态。

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: true
  }
})

响应格式如下：

{
  candidates: [
    { featureId: string, phase: string, workflowType: string, stalenessMinutes: number }
  ],
  skipped: [
    { featureId: string, reason: "open-pr" | "active-branch" }
  ]
}

可选参数：

```
thresholdMinutes
```
-- 过时时长阈值，默认值为10080（7天）
```
includeOneShot
```
-- 是否将
```
oneshot
```
工作流纳入候选集，默认值为
```
true
```
```
force
```
-- 在试运行阶段无效；仅在执行阶段（步骤4）生效

Step 2: Display Candidate Table

步骤2：展示候选工作流表格

Render a table to the user so they can review what would be pruned. Use this format:

markdown

undefined

向用户渲染表格，以便其查看待清理内容，使用以下格式：

markdown

undefined

Prune Candidates (3)

待清理候选工作流（3个）

Feature ID	Type	Phase	Stale (min)
feat-old-experiment	feature	implementing	14430
oneshot-typo-fix	oneshot	plan	9120
debug-flaky-test	debug	investigate	8650

Feature ID	类型	阶段	过时时长（分钟）
feat-old-experiment	feature	implementing	14430
oneshot-typo-fix	oneshot	plan	9120
debug-flaky-test	debug	investigate	8650

Skipped by Safeguards (2)

被防护机制跳过的工作流（2个）

Feature ID	Reason
feat-active-pr	open-pr
feat-recent-work	active-branch


If `candidates.length === 0` AND `skipped.length === 0`, output:

> No stale workflows to prune. Pipeline is clean.

Then exit -- no further action.

Feature ID	原因
feat-active-pr	open-pr
feat-recent-work	active-branch


若`candidates.length === 0`且`skipped.length === 0`，则输出：

> 无过时工作流需要清理，流水线已处于整洁状态。

随后退出，无需执行后续操作。

Step 3: Prompt for Confirmation

步骤3：确认提示

Ask the user one of three choices:

proceed -- prune the listed candidates (skipped workflows stay) abort -- exit without changes force -- bypass safeguards and prune skipped workflows too

Wait for explicit user input. Do not auto-proceed.

向用户提供三个选项：

proceed -- 清理列出的候选工作流（被跳过的工作流保留） abort -- 退出且不做任何变更 force -- 绕过防护机制，同时清理被跳过的工作流

等待用户明确输入，请勿自动执行。

Step 4a: Apply (proceed)

步骤4a：执行（proceed）

proceed

, invoke the same action with

dryRun: false

. Pass through

thresholdMinutes

and

includeOneShot

if the user set them in Step 1.

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: false
  }
})

The response now includes a

pruned

array:

{
  candidates: [...],
  skipped: [...],
  pruned: [
    { featureId: string, previousPhase: string }
  ]
}

Each entry in

pruned

corresponds to a workflow that transitioned to

cancelled

and emitted a

workflow.pruned

event.

用户选择

proceed

时，调用相同操作并设置

dryRun: false

。若用户在步骤1中设置了

thresholdMinutes

和

includeOneShot

，则需一并传入。

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: false
  }
})

此时响应会包含

pruned

数组：

{
  candidates: [...],
  skipped: [...],
  pruned: [
    { featureId: string, previousPhase: string }
  ]
}

pruned

中的每个条目对应一个已转为

cancelled

状态并生成

workflow.pruned

事件的工作流。

Step 4b: Apply (force)

步骤4b：执行（force）

force

, set

force: true

. Safeguards are bypassed but the bypass is recorded in the

workflow.pruned

event payload as

skippedSafeguards: [...]

so the audit trail is intact.

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: false,
    force: true
  }
})

In force mode, workflows that were in the

skipped

list during dry-run are now eligible for pruning.

用户选择

force

时，设置

force: true

。防护机制会被绕过，但绕过操作会被记录在

workflow.pruned

事件的

skippedSafeguards: [...]

字段中，确保审计轨迹完整。

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "prune_stale_workflows",
  args: {
    dryRun: false,
    force: true
  }
})

在强制模式下，试运行阶段处于

skipped

列表中的工作流现在也可被清理。

Step 4c: Apply (abort)

步骤4c：执行（abort）

abort

, exit without invoking the action a second time. The dry-run has not mutated any state.

用户选择

abort

时，退出且不再调用操作。试运行阶段未修改任何状态。

Step 5: Report Results

步骤5：结果报告

After the apply call returns, summarize the outcome:

markdown

undefined

执行调用返回后，总结结果：

markdown

undefined

Prune Complete

清理完成

Pruned: 3 workflows transitioned to cancelled Skipped: 2 workflows preserved by safeguards Force bypass: no

已清理： 3个工作流转为已取消状态 已跳过： 2个工作流被防护机制保留 强制绕过： 否

Pruned Workflows

已清理工作流

feat-old-experiment (was: implementing)
oneshot-typo-fix (was: plan)
debug-flaky-test (was: investigate)


If `force` was used, also list any safeguards that were bypassed:

```markdown

feat-old-experiment（原阶段：implementing）
oneshot-typo-fix（原阶段：plan）
debug-flaky-test（原阶段：investigate）


若使用了`force`模式，还需列出被绕过的防护机制：

```markdown

Safeguards Bypassed

被绕过的防护机制

feat-active-pr: open-pr
feat-recent-work: active-branch

undefined

feat-active-pr: open-pr
feat-recent-work: active-branch

undefined

Safeguards Explained

防护机制说明

Two safeguards run automatically in the orchestrate handler before each cancel:

Safeguard	Behavior	Reason key
Open PR	Skip if `gh pr list --head <branch> --state open` returns any results	`open-pr`
Recent commits	Skip if `git log --since "24 hours ago" origin/<branch>` shows commits	`active-branch`

A workflow without a

branchName

in state (e.g., abandoned at ideate/plan before delegation) cannot have a PR or branch activity, so safeguards short-circuit and the workflow is eligible for pruning.

force: true

bypasses both checks but does not bypass the audit -- the bypassed safeguard names are recorded in the

workflow.pruned

event payload.

编排处理程序在每次取消操作前会自动运行两项防护检查：

防护机制	行为	原因标识
未合并PR检查	若 `gh pr list --head <branch> --state open` 返回结果则跳过	`open-pr`
近期提交检查	若 `git log --since "24 hours ago" origin/<branch>` 显示有提交则跳过	`active-branch`

状态中无

branchName

的工作流（例如在委派前已停滞在ideate/plan阶段的工作流）无法进行PR或分支活动检查，因此防护机制会直接放行，该工作流可被清理。

force: true

会绕过两项检查，但不会绕过审计——被绕过的防护机制名称会记录在

workflow.pruned

事件的负载中。

Anti-Patterns

反模式

Don't	Do Instead
Skip the dry-run step	Always start with `dryRun: true` so the user sees candidates first
Auto-confirm without showing the table	Render the candidate table and wait for explicit user input
Use `force: true` by default	Reserve `force` for cases where the user has explicitly opted in
Manually call `cancel` for each stale workflow	Use this skill -- it batches the cancel loop and emits the `workflow.pruned` audit event
Run on every session	Pruning is a maintenance operation; run when pipeline accumulation is observable

请勿	建议做法
跳过试运行步骤	始终以 `dryRun: true` 启动，确保用户先查看候选工作流
不展示表格直接自动确认	渲染候选工作流表格并等待用户明确输入
默认启用 `force: true`	仅在用户明确选择时使用 `force` 模式
手动为每个过时工作流调用 `cancel`	使用此Skill——它会批量处理取消循环并生成 `workflow.pruned` 审计事件
每次会话都运行清理	清理是维护操作；仅当流水线中累积大量非活跃工作流时运行

Examples

示例

Example 1: Clean dry-run, user proceeds

示例1：试运行无跳过，用户选择继续

> /prune

> /prune

Prune Candidates (2)

待清理候选工作流（2个）

Feature ID	Type	Phase	Stale (min)
feat-old-spike	feature	plan	12880
oneshot-readme-tweak	oneshot	implementing	9700

Feature ID	类型	阶段	过时时长（分钟）
feat-old-spike	feature	plan	12880
oneshot-readme-tweak	oneshot	implementing	9700

Skipped by Safeguards (0)

被防护机制跳过的工作流（0个）

(none)

Proceed? (proceed/abort/force)

proceed

(无)

是否继续？(proceed/abort/force)

proceed

Prune Complete

清理完成

Pruned: 2 workflows transitioned to cancelled Skipped: 0 Force bypass: no

已清理： 2个工作流转为已取消状态 已跳过： 0个 强制绕过： 否

Pruned Workflows

已清理工作流

feat-old-spike (was: plan)
oneshot-readme-tweak (was: implementing)

undefined

feat-old-spike（原阶段：plan）
oneshot-readme-tweak（原阶段：implementing）

undefined

Example 2: Safeguard skip, user forces

示例2：存在防护跳过，用户选择强制清理

> /prune

> /prune

Prune Candidates (1)

待清理候选工作流（1个）

Feature ID	Type	Phase	Stale (min)
feat-stale-no-pr	feature	implementing	11200

Feature ID	类型	阶段	过时时长（分钟）
feat-stale-no-pr	feature	implementing	11200

Skipped by Safeguards (1)

被防护机制跳过的工作流（1个）

Feature ID	Reason
feat-stale-with-pr	open-pr

Proceed? (proceed/abort/force)

force

Feature ID	原因
feat-stale-with-pr	open-pr

是否继续？(proceed/abort/force)

force

Prune Complete

清理完成

Pruned: 2 workflows transitioned to cancelled Skipped: 0 Force bypass: yes

已清理： 2个工作流转为已取消状态 已跳过： 0个 强制绕过： 是

Pruned Workflows

已清理工作流

feat-stale-no-pr (was: implementing)
feat-stale-with-pr (was: implementing)

feat-stale-no-pr（原阶段：implementing）
feat-stale-with-pr（原阶段：implementing）

Safeguards Bypassed

被绕过的防护机制

feat-stale-with-pr: open-pr

undefined

feat-stale-with-pr: open-pr

undefined

Example 3: Empty pipeline

示例3：流水线无过时工作流

> /prune

No stale workflows to prune. Pipeline is clean.

> /prune

无过时工作流需要清理，流水线已处于整洁状态。

Schema Discovery

Schema 发现

For the canonical argument schema and any future fields, use:

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "describe",
  actions: ["prune_stale_workflows"]
})

如需获取标准参数Schema及未来新增字段，请使用：

typescript

mcp__exarchos__exarchos_orchestrate({
  action: "describe",
  actions: ["prune_stale_workflows"]
})

Exarchos Integration

Exarchos 集成

The

prune_stale_workflows

action emits two events per pruned workflow:

```
workflow.cancelled
```
(auto-emitted by the underlying
```
handleCancel
```
path)

workflow.pruned

(emitted by this handler with

triggeredBy: 'manual'

and optional

skippedSafeguards

)

Both are projected into the workflow state's

_events

array by the standard projection. Downstream views can filter on

workflow.pruned

to identify batch cleanups versus user-initiated cancels.

prune_stale_workflows

操作会为每个被清理的工作流生成两个事件：

```
workflow.cancelled
```
（由底层
```
handleCancel
```
流程自动生成）
```
workflow.pruned
```
（由此处理程序生成，包含
```
triggeredBy: 'manual'
```
及可选的
```
skippedSafeguards
```
字段）

两个事件都会被标准投影写入工作流状态的

_events

数组中。下游视图可通过筛选

workflow.pruned

事件区分批量清理与用户主动发起的取消操作。