pstack-omp

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

pstack on OMP

在OMP上运行pstack

poteto-mode

is the sole router. It selects the playbook, canonical role, step order, and lifecycle protocol. This adapter translates those choices to OMP only. It never selects a playbook, repeats the playbook index, or changes a playbook gate.

While this skill is active, its role map is the specific pstack execution contract. Generic OMP instructions remain valid outside pstack work.

poteto-mode

是唯一的路由组件。它负责选择剧本、标准角色、步骤顺序和生命周期协议。本适配器仅将这些选择转换为OMP兼容的形式。它绝不会选择剧本、重复剧本索引或修改剧本关卡。

当本技能处于激活状态时，其角色映射即为特定的pstack执行协议。通用OMP指令在pstack工作场景外依然有效。

Canonical role map

标准角色映射

Use these exact OMP agent names.

Canonical role	OMP agent	Contract
`explorer`	`scout`	Read-only repository reconnaissance, trace reduction, narrow audits.
`watcher`	`scout`	Observe one exact generation or external-state transition, then terminate.
`planner`	`designer`	Technical planning, architecture, decomposition, sequencing, and non-visual design candidates.
`designer`	`designer`	Visual, interaction, and product-design candidates.
`reviewer`	`reviewer`	Independent code, protocol, behavioral, or security review.
`researcher`	`librarian`	Source-verified external library, framework, API, protocol, or version research.
`synthesizer`	`reviewer`	Cross-report synthesis, adjudication, and advisory judgment over frozen evidence.
`implementer`	`task`	Bounded implementation or test changes with explicit write ownership.
`owner`	`task`	One coupled multi-step implementation session retained through IRC follow-ups.
`mechanical`	`sonic`	Fully specified low-judgment edits. Ambiguity returns to the root.

The canonical OMP roster is closed:

text

scout
designer
reviewer
security-reviewer
librarian
task
sonic

A canonically routed task item's

agent

value must be one of those bundled names. Canonical role labels and model aliases are not agent names.

poteto-agent

and

comment-sicko

are custom compatibility agents for direct named seams in imported skills. A direct compatibility call may use that custom agent name; ordinary canonical routing never does.

请使用以下精确的OMP Agent名称。

标准角色	OMP Agent	协议内容
`explorer`	`scout`	只读仓库侦察、追踪缩减、范围限定审计。
`watcher`	`scout`	观察某一特定版本或外部状态转换，随后终止。
`planner`	`designer`	技术规划、架构设计、任务分解、步骤排序，以及非视觉设计方案。
`designer`	`designer`	视觉、交互及产品设计方案。
`reviewer`	`reviewer`	独立的代码、协议、行为或安全评审。
`researcher`	`librarian`	经过来源验证的外部库、框架、API、协议或版本调研。
`synthesizer`	`reviewer`	基于固定证据的跨报告整合、裁决及咨询判断。
`implementer`	`task`	有明确写入权限的限定性实现或测试变更。
`owner`	`task`	包含IRC跟进的关联多步骤实现会话。
`mechanical`	`sonic`	完全明确的低判断性编辑。存在歧义时返回至根节点。

标准OMP Agent列表是固定的：

text

scout
designer
reviewer
security-reviewer
librarian
task
sonic

通过标准路由的任务项其

agent

值必须是上述内置名称之一。标准角色标签和模型别名不属于Agent名称。

poteto-agent

和

comment-sicko

是用于导入技能中直接命名衔接点的自定义兼容Agent。直接兼容调用可使用该自定义Agent名称；常规标准路由绝不会使用。

Planning distinction

规划区分

The imported warning about a built-in planning subagent describes a source-host mechanism that bypassed the skill contract. This OMP version has no bundled

plan

agent. Canonical

planner

work uses

designer

with a technical-planning brief and does not pass source-host subagent fields.

关于内置规划子Agent的导入警告描述了一种绕过技能协议的源主机机制。本OMP版本没有内置的

plan

Agent。标准

planner

工作需使用带有技术规划简报的

designer

，且不会传递源主机子Agent字段。

Security review

安全评审

Use

security-reviewer

for an independent security lane. Keep it read-only and separate from ordinary code review when both are required. A later

reviewer

session may synthesize frozen reports; it does not replace the primary security review.

使用

security-reviewer

进行独立安全评审。当同时需要安全评审和常规代码评审时，保持其只读属性并与常规评审分离。后续的

reviewer

会话可整合固定报告，但不能替代主安全评审。

Task contract

任务协议

The root performs every

task

call. A child never calls

task

, starts another child, or asks the user directly. Put

Do not call task or start subagents

under

FORBIDDEN

in every child brief.

Children start without the parent conversation. Every prompt must stand alone. They receive the configured workspace, context files, skills, and approved plan resources supplied by OMP.

根节点执行所有

task

调用。子节点绝不能调用

task

、启动其他子节点或直接询问用户。在每个子节点简报的

FORBIDDEN

部分添加

Do not call task or start subagents

（禁止调用task或启动子Agent）。

子节点启动时不携带父会话内容。每个提示必须独立存在。它们会接收OMP提供的配置工作区、上下文文件、技能及已批准的规划资源。

One task

单个任务

When the flat schema is active:

json

{
  "name": "parser-overflow-worker",
  "agent": "task",
  "task": "GOAL\n...\n\nROLE\n...\n\nSCOPE\n...\n\nCONTEXT\n...\n\nACCEPTANCE\n...\n\nVERIFY\n...\n\nTIMEBOX\n...\n\nFORBIDDEN\n...\n\nREPORT\n...\n\nSTANDING\n...",
  "isolated": true
}

When batch mode is active, use a one-item

tasks[]

call instead of inventing a per-call batch switch.

Use

isolated: true

for a writer that needs a dedicated worktree. Read the returned isolation metadata and verify the patch, branch, or applied change OMP reports. Use a non-isolated session for a long-lived owner that must accept IRC follow-ups in the same workspace.

当扁平化架构激活时：

json

{
  "name": "parser-overflow-worker",
  "agent": "task",
  "task": "GOAL\n...\n\nROLE\n...\n\nSCOPE\n...\n\nCONTEXT\n...\n\nACCEPTANCE\n...\n\nVERIFY\n...\n\nTIMEBOX\n...\n\nFORBIDDEN\n...\n\nREPORT\n...\n\nSTANDING\n...",
  "isolated": true
}

当批处理模式激活时，使用单元素

tasks[]

调用，而非为每个调用单独设置批处理开关。

对于需要专用工作树的写入者，使用

isolated: true

。读取返回的隔离元数据并验证OMP报告的补丁、分支或已应用变更。对于需要在同一工作区接收IRC跟进的长期所有者，使用非隔离会话。

Batched panel

批处理评审组

Use one batch call for independent participants:

json

{
  "context": "Shared immutable repository, base SHA, artifacts, constraints, and verification context.",
  "tasks": [
    {
      "name": "candidate-a",
      "agent": "designer",
      "task": "Standalone brief for architecture candidate A.",
      "isolated": false
    },
    {
      "name": "candidate-b",
      "agent": "designer",
      "task": "Standalone brief for architecture candidate B.",
      "isolated": false
    }
  ]
}

Each

name

is unique.

context

contains common immutable material. Each item still names its exact role, slice, acceptance criteria, verification, forbidden work, and report contract.

Start every participant in one batch before consuming any verdict. Separate writers with isolated workspaces or disjoint output paths. Freeze candidate artifacts before starting reviewers. Freeze reviewer reports before starting a separate synthesizer session.

对独立参与者使用单次批处理调用：

json

{
  "context": "Shared immutable repository, base SHA, artifacts, constraints, and verification context.",
  "tasks": [
    {
      "name": "candidate-a",
      "agent": "designer",
      "task": "Standalone brief for architecture candidate A.",
      "isolated": false
    },
    {
      "name": "candidate-b",
      "agent": "designer",
      "task": "Standalone brief for architecture candidate B.",
      "isolated": false
    }
  ]
}

每个

name

都是唯一的。

context

包含通用不可变材料。每个条目仍需明确指定其角色、任务切片、验收标准、验证要求、禁止操作及报告协议。

在接收任何结论前启动所有参与者。为写入者分配隔离工作区或不相交的输出路径。在启动评审者前固定候选工件。在启动单独的整合者会话前固定评审报告。

Background completion and follow-ups

后台完成与跟进

Background task results arrive through OMP's async result delivery. Record the returned job and agent identifiers. The preview may be truncated.

Read the full result from
```
agent://<id>
```
.
Read the session transcript from
```
history://<id>
```
when the report is incomplete, ambiguous, or suspicious.
Use
```
hub
```
with
```
op: "jobs"
```
to inspect jobs and
```
op: "wait"
```
with
```
ids
```
to wait for specific job IDs.
Use
```
hub
```
with
```
op: "list"
```
to inspect peers and
```
op: "send"
```
with
```
to
```
for one in-scope correction, answer, authorization, or next coupled phase.
Use
```
hub
```
with
```
op: "cancel"
```
and exact job
```
ids
```
for stale, superseded, or scope-breaching work.
A follow-up to a parked session revives the same session when the host reports that capability.
Never steer a reviewer toward a preferred conclusion.
Use only operations exposed by the live
```
hub
```
schema. Do not invent lifecycle operations.
Ignore duplicate terminal deliveries and reject stale artifact generations.

A task result is evidence, not completion. The root inspects the artifact and runs verification.

后台任务结果通过OMP的异步结果交付机制送达。记录返回的作业和Agent标识符。预览内容可能被截断。

从
```
agent://<id>
```
读取完整结果。
当报告不完整、存在歧义或可疑时，从
```
history://<id>
```
读取会话记录。
使用带有
```
op: "jobs"
```
的
```
hub
```
检查作业，使用带有
```
ids
```
的
```
op: "wait"
```
等待特定作业ID。
使用带有
```
op: "list"
```
的
```
hub
```
检查对等节点，使用带有
```
to
```
的
```
op: "send"
```
发送范围内的修正、答案、授权或下一关联阶段指令。
使用带有
```
op: "cancel"
```
和精确作业
```
ids
```
的
```
hub
```
取消过期、已被取代或超出范围的工作。
当主机支持该功能时，对暂停会话的跟进会恢复同一会话。
绝不能引导评审者得出偏好结论。
仅使用实时
```
hub
```
架构暴露的操作。不得自行发明生命周期操作。
忽略重复的终端交付，拒绝过期工件版本。

任务结果是证据，而非完成标志。根节点需检查工件并执行验证。

Brief shape

简报格式

A dispatch is forbidden until its brief contains:

GOAL
One-sentence outcome executable by a stranger.

ROLE
The canonical role, mapped OMP agent, authority, and expected stance.

SCOPE
Writable and non-writable paths, exact slice or race arm, worktree and branch where applicable, and every output path. State the one-writer assignment.

CONTEXT
Repository root, relevant source paths, base SHA, frozen artifacts, active skill and playbook paths, settled assumptions, and known gotchas.

ACCEPTANCE
Checkable observable outcomes, one per line.

VERIFY
Exact commands, fixtures, runtime probes, comparison baselines, environment requirements, and known false-positive or false-negative risks.

TIMEBOX
A rough cap. At the cap, return partial evidence and stop instead of broadening scope.

FORBIDDEN
At minimum: no child task calls; no subagent spawning; no out-of-scope fixes; no unrequested migrations; no shared-path edits outside ownership; no merge; no direct user questions; no completion claim without executed verification.

REPORT
Require

PASS | ISSUES | BLOCKED

, semantic session name, branch and exact SHAs where applicable, verdict and evidence, changed files or artifacts, actual verification commands and results, deviations, unresolved risks, and parent actions.

STANDING
Copy the active playbook's standing policy text verbatim when it supplies one.

简报包含以下内容前禁止分发：

GOAL（目标）
一句可由陌生人执行的结果描述。

ROLE（角色）
标准角色、映射的OMP Agent、权限及预期立场。

SCOPE（范围）
可写入和不可写入路径、精确任务切片或分支、适用的工作树和分支，以及所有输出路径。指定单一写入者分配。

CONTEXT（上下文）
仓库根目录、相关源路径、基准SHA、固定工件、激活技能和剧本路径、已确定的假设及已知陷阱。

ACCEPTANCE（验收标准）
可检查的可观测结果，每行一个。

VERIFY（验证方式）
精确命令、测试用例、运行时探测、对比基准、环境要求，以及已知的假阳性或假阴性风险。

TIMEBOX（时间盒）
大致时间上限。到达上限时，返回部分证据并停止，而非扩大范围。

FORBIDDEN（禁止操作）
至少包含：禁止调用子任务；禁止启动子Agent；禁止超出范围的修复；禁止未请求的迁移；禁止在所有权外编辑共享路径；禁止合并；禁止直接询问用户；禁止未执行验证就声明完成。

REPORT（报告要求）
要求包含

PASS | ISSUES | BLOCKED

（通过|问题|阻塞）、语义会话名称、适用的分支和精确SHA、结论及证据、变更文件或工件、实际验证命令及结果、偏差、未解决风险，以及父节点需执行的操作。

STANDING（常规策略）
当提供相关内容时，逐字复制激活剧本的常规策略文本。

Canonical protocols

标准协议

Bounded session

限定会话

Author one standalone brief.
Start one task with the mapped agent.
Record its semantic name, agent ID, job ID, role, scope, isolation mode, base SHA, and expected artifact.
Consume the async result when delivered.
Read
```
agent://<id>
```
; inspect
```
history://<id>
```
when needed.
Send one IRC correction only within the same unit.
Inspect the artifact and independently run the promised verification.
Accept the unit only after the parent verifies the reported output.

A role or unit change requires a fresh task.

编写一份独立简报。
使用映射的Agent启动一个任务。
记录其语义名称、Agent ID、作业ID、角色、范围、隔离模式、基准SHA及预期工件。
接收异步结果。
读取
```
agent://<id>
```
；必要时检查
```
history://<id>
```
。
仅在同一单元内发送一次IRC修正。
检查工件并独立执行承诺的验证。
仅在父节点验证报告输出后接受该单元。

角色或单元变更需要启动新任务。

Panel

评审组

Partition independent slices or race arms with one task per participant.
Start every participant in one batch before consuming any result.
Track participants by semantic name and identifiers, never arrival order.
Wait for every required result through
```
hub
```
```
op: "wait"
```
, or cancel it explicitly through
```
hub
```
```
op: "cancel"
```
.
Ignore duplicate terminal delivery.
Freeze implementation artifacts, branches, head SHAs, reports, and hashes.
Start every independent reviewer in a new batch only after the candidates are frozen.
Freeze verdicts before starting a separate
```
reviewer
```
when synthesis is needed.
Treat synthesis as advice. The root selects and verifies.

Do not mix implementers, reviewers, or synthesizers in one session. Do not let reviewers race a moving head.

将独立切片或分支划分为多个任务，每个参与者对应一个任务。
在接收任何结果前启动所有参与者。
通过语义名称和标识符跟踪参与者，而非到达顺序。
通过
```
hub
```
的
```
op: "wait"
```
等待所有必要结果，或通过
```
op: "cancel"
```
明确取消。
忽略重复的终端交付。
固定实现工件、分支、头部SHA、报告及哈希值。
仅在候选工件固定后，在新批处理中启动所有独立评审者。
当需要整合时，在启动单独的
```
reviewer
```
前固定结论。
将整合结果视为建议。根节点负责选择和验证。

不得在同一会话中混合实现者、评审者或整合者。不得让评审者追踪变动的头部节点。

Long-lived owner

长期所有者

Start one non-isolated
```
task
```
session with the complete owner brief.
Record its agent ID and reuse it. Do not start a sibling owner for the same unit.
The owner works only in its assigned branch and paths and never starts children.
Send a
```
hub
```
```
op: "send"
```
follow-up only for the next coupled phase, an in-scope correction, an answer resolved from evidence, or explicit authorization.
Require a terminal report at each verification boundary.
Independently verify the boundary before authorizing the next phase.
Stand down on ownership violation, stale generation, or terminal scope breach.

使用完整的所有者简报启动一个非隔离
```
task
```
会话。
记录其Agent ID并复用。不得为同一单元启动同级所有者。
所有者仅在指定分支和路径中工作，绝不启动子节点。
仅为下一关联阶段、范围内修正、基于证据的答案或明确授权发送
```
hub
```
的
```
op: "send"
```
跟进。
要求在每个验证边界提交终端报告。
在授权下一阶段前独立验证边界。
当出现所有权违规、版本过期或终端范围 breach时终止。

One-shot watcher

一次性观察者

Start one background
```
scout
```
task.
Put the exact branch, head SHA, generation, watched predicate, stop predicate, and timebox in the brief.
Require one meaningful event and a terminal report.
Discard a report whose generation no longer matches.
Start a fresh watcher for each new generation.
Stand down when the stop predicate is met or the work is superseded.

A watcher observes. It does not fix, merge, authorize, or silently follow a changed head.

启动一个后台
```
scout
```
任务。
在简报中明确指定分支、头部SHA、版本、观察谓词、停止谓词及时间盒。
要求返回一个有意义的事件和终端报告。
丢弃版本不匹配的报告。
为每个新版本启动新的观察者。
当满足停止谓词或工作被取代时终止。

观察者仅负责观察。不得进行修复、合并、授权或静默追踪变动的头部节点。

Interactions and decisions

交互与决策

Children resolve uncertainty from source, standing policy, frozen evidence, or the brief. Otherwise they use the safest reversible interpretation and report the assumption, or return

BLOCKED

with the exact missing decision and evidence gathered.

The root resolves a child question and sends the answer through

hub

op: "send"

to the existing agent. Ask the user only for genuine product preference, unavailable authority, or an irreversible action not covered by standing orders.

子节点从源、常规策略、固定证据或简报中解决不确定性。否则采用最安全的可逆解释并报告假设，或返回

BLOCKED

及确切的缺失决策和已收集证据。

根节点解决子节点的问题，并通过

hub

的

op: "send"

将答案发送给现有Agent。仅在需要真实产品偏好、无法获取的权限或常规指令未覆盖的不可逆操作时询问用户。

Ownership and verification

所有权与验证

One writer per branch, worktree, mutable state, and output path.
Separate sessions own implementation, review, judgment, and synthesis.
A task stays inside its assigned unit and role.
Isolate concurrent writers unless their outputs are structurally disjoint.
A worker's report never verifies its own work.
Record branch, base SHA, and exact head SHA or artifact generation.
Prefer behavioral proof over type-check-only evidence.
A new commit, restack, conflict resolution, or applied patch creates a new generation that voids the prior verdict.
Judges and synthesizers advise. The root owns selection, user interaction, external writes, merges, deletion, and final truth.
Claim model independence only from returned resolved-model and fallback metadata.

每个分支、工作树、可变状态及输出路径仅分配一个写入者。
实现、评审、判断及整合由独立会话负责。
任务需保持在指定单元和角色范围内。
隔离并发写入者，除非其输出在结构上不相交。
工作者的报告不得验证自身工作。
记录分支、基准SHA及精确的头部SHA或工件版本。
优先选择行为验证而非仅类型检查的证据。
新提交、重排、冲突解决或应用补丁会生成新版本，使之前的结论失效。
判断者和整合者仅提供建议。根节点负责选择、用户交互、外部写入、合并、删除及最终结论。
仅在返回已解析模型和回退元数据时声明模型独立性。

Model routing

模型路由

OMP resolves a task agent through its current settings, including

modelRoles

task.agentModelOverrides

, the agent definition, and normal fallback. Agent selection and model selection are separate decisions.

Do not put a

model

field in a task item. Do not use a model alias as the

agent

value. Configure routing through the installed OMP settings and report the actual resolved model when independence matters.

Recommended role aliases:

OMP agent	Recommendation
`scout`	`@smol`
`designer`	`@designer`
`reviewer`	`@advisor`
`security-reviewer`	`@advisor`
`librarian`	`@smol`
`task`	`@task` or a stronger implementation role
`sonic`	`@tiny` or `@smol`

These are recommendations, not task payload fields.

OMP通过当前设置解析任务Agent，包括

modelRoles

、

task.agentModelOverrides

、Agent定义及常规回退。Agent选择和模型选择是独立的决策。

不得在任务项中添加

model

字段。不得将模型别名用作

agent

值。通过已安装的OMP配置进行路由，并在独立性重要时报告实际解析的模型。

推荐角色别名：

OMP Agent	推荐别名
`scout`	`@smol`
`designer`	`@designer`
`reviewer`	`@advisor`
`security-reviewer`	`@advisor`
`librarian`	`@smol`
`task`	`@task` 或更强的实现角色
`sonic`	`@tiny` 或 `@smol`

以上为推荐内容，不属于任务负载字段。

Writing

写作规范

Apply

unslop

to every reply, brief, report, review, task dispatch, commit message, and agent-facing edit.

对所有回复、简报、报告、评审、任务分发、提交信息及面向Agent的编辑应用

unslop

规范。