AGENT SKILL

pstack-omp

Maps the Cursor names in pstack skills to OMP tools, agents, models, and paths. pstack skills read it once per session; poteto-mode embeds it.

License 许可
MIT
最近更新
2026-10-28
Stars
★ 0
Forks
0

01 前言 Front Matter

name
pstack-omp
description
Maps the Cursor names in pstack skills to OMP tools, agents, models, and paths. pstack skills read it once per session; poteto-mode embeds it.
disable-model-invocation
true

03 SKILL.md 正文

pstack in OMP

pstack skills use Cursor names. In OMP, read this once per session, then map each Cursor name in a pstack skill with the tables below. When this text arrives embedded in poteto-mode or autoloaded into a subagent, it is already read. Do not read it again. <pstack> means the plugin folder that holds skills/, agents/, and docs/, two levels up from this file. If a Cursor field has no row, drop it and say so. Never pass a field or value the live tool schema rejects. The live schema wins over this file.

Tools

Cursor OMP
Task task. In batch mode the call is {context, tasks: [{agent, name, task, solutionSpace}]}, with agent on each item. solutionSpace says how open the problem is, not how big it is. With async.enabled on, spawns run as background jobs and their results arrive on their own. Do not poll.
AskQuestion ask. When the session has no ask tool, as in omp -p, ask in plain text.
Open a todolist todo. Copy the playbook's steps in verbatim as its first items.
Run another pstack skill (/name or "the name skill") Read skill://<name> and follow it, unless its body is already in context from /skill:<name> or an earlier read. When you tell the user to type it, write /skill:<name>.
Read, Write, StrReplace, Shell, Grep, Glob read, write, edit, bash, grep, glob.
WebFetch, WebSearch read on the URL, web_search.

Subagent fields

An OMP task item has no model, subagent_type, readonly, environment, run_in_background, resume, or file_attachments field. The agent name picks the model.

Cursor OMP
subagent_type: generalPurpose agent: "pstack-code" for code, exploration, verification, and swarm seats. agent: "pstack-judge" for prose, review, synthesis, and judgment seats. When the skill names a model, pick the agent from that model's row in Models.
poteto-agent agent: "poteto-agent" for code delegates. agent: "poteto-agent-judge" for the hardest changes and for judgment. Both autoload poteto-mode. Still name skill://poteto-mode in the brief.
comment-sicko agent: "comment-sicko".
readonly: true The same agent, and the brief says "do not edit files". This is an instruction, not a sandbox, so check git status afterward. readonly: false needs nothing.
environment: "cloud" isolated: true when the task schema offers it (task.isolation.enabled). Otherwise create a worktree with git worktree add, name its path and base commit in the brief, and never run two writers in one checkout. A worktree is not a VM and shares your credentials.
environment: "local" Omit.
cloud_base_branch: <b> Base the worktree on <b>, or tell the worker to check out <b> first.
run_in_background: true Omit. Spawns are background jobs while async.enabled is on.
resume Spawn a fresh agent and paste the earlier result into its brief. When the strict reuse case applies (the agent holds a checkout, uncommitted work, or a live process), message it with write agent://<id> instead.
file_attachments List absolute paths in the brief.

Models

Two OMP model roles carry pstack's two model families. modelRoles.pstack-code backs pstack-code and poteto-agent. modelRoles.pstack-judge backs pstack-judge, poteto-agent-judge, and comment-sicko. pstack-parent has no model of its own, so it runs on the session model unless task.agentModelOverrides.pstack-parent sets one. Before the first spawn, run omp config get modelRoles. An agent whose role is unset fails to start with No model selected. Give each such seat to pstack-parent instead, name skill://poteto-mode in the brief when it replaces a poteto delegate, and tell the user once that /skill:setup-pstack sets the roles. Same-model seats are not model diversity, so never claim it.

Cursor OMP
A grok-*, gpt-*, composer-*, or other non-Claude slug, and every code role The code agent. pstack-code, or poteto-agent when the skill spawns a poteto delegate.
claude-<family>-<version>-<effort>[-fast], such as claude-opus-5-5-xhigh, and every judgment, prose, or hardest-task role The judge agent. pstack-judge, or poteto-agent-judge when the skill spawns a poteto delegate.
auto or inherit-parent pstack-parent.
An effort suffix (-xhigh, -high) or -fast Drop it. Effort comes from the role's thinking suffix, such as anthropic/claude-opus-5-5:xhigh. Pass per-spawn effort (lo, med, hi) only when the task schema shows it.
A two-family panel (arena, architect, interrogate) One pstack-code seat and one pstack-judge seat per pair. If both roles resolve to the same family, say so. Same-family seats are not multi-model evidence.
The pstack-models.mdc rule, ~/.cursor/rules/pstack-models.mdc ~/.omp/agent/pstack-models.md. Read it when it exists. Each role line names the OMP agent (pstack-code, pstack-judge, pstack-parent, or a panel list of them) for that role. Without the file or the line, use the rows above.

setup-pstack

In OMP the choice has two layers. The two modelRoles selectors pick the models. The role lines in ~/.omp/agent/pstack-models.md pick which agent runs each role. Follow the skill's steps with these changes.

  • Detect. omp models --json lists each model's selector (provider/id) and the efforts in its thinking list.
  • Load current state. The current models are omp config get modelRoles. The current role lines and # budget line come from ~/.omp/agent/pstack-models.md. Its role values are agent names, not slugs.
  • Defaults. The upstream grok-* defaults are the code role. The claude-opus-* defaults are the judgment role. Map each to a detected selector, or mark it as needing a choice.
  • Budget. Set the budget's effort as the :<effort> suffix of both modelRoles selectors, such as anthropic/claude-opus-5-5:xhigh. When the model's thinking list lacks that effort, use the highest one it has below it. Role lines carry no effort.
  • Confirm. Show both selectors and every role line. A selector can be any detected model. A role line can be pstack-code, pstack-judge, pstack-parent, or, for a panel role, a list of them.
  • Validate. Each selector without its suffix equals a detected selector, and its suffix is in that model's thinking list. Role-line values are agent names, so they always pass. Never write a slug into a role line.
  • Write. Run omp config set modelRoles.pstack-code <selector> and omp config set modelRoles.pstack-judge <selector>. Then write ~/.omp/agent/pstack-models.md with no frontmatter: the comment lines, the # budget line, and one line per role from step 5 with its agent name. Overwrite the whole file. Never put role lines in AGENTS.md.

Paths

Cursor OMP
.cursor/skills/, ~/.cursor/skills/ .omp/skills/, ~/.omp/agent/skills/.
~/.cursor/plugins/, .cursor-plugin/plugin.json <pstack>. Read bundled skills through skill://<name>. <pstack>/package.json holds the version.
.cursor/rules/*.mdc, always-applied rules AGENTS.md at the project root, or .omp/AGENTS.md. User-wide rules live in ~/.omp/agent/AGENTS.md. OMP never reads .mdc files. The model rule is the exception. See Models.
https://github.com/cursor/plugins/blob/main/pstack/<path> <pstack>/<path> when that file exists. The plugin ships the skills and docs/guide/. Read the local copy and never fetch it. Give the user the URL when they need a link.
Transcripts in ~/.cursor/projects/<slug>/agent-transcripts/ OMP sessions in ~/.omp/agent/sessions/<folder>/<timestamp>_<id>.jsonl. The first or second line is a {"type":"session"} header whose cwd is the workspace. A {"type":"title"} line can come before it. Messages are {"type":"message"} lines whose message.content holds the text. Pick the folder whose headers match the workspace. The newest file is the current session. The folder beside it with the same name holds subagent transcripts, and history://<agent> renders one. Read only this workspace's sessions.

Cursor-only features

OMP has no Cursor Automations, Bugbot, Cursor cloud agents, persistent /loop wakes, custom mode, or built-in PR tool. When a step needs one, put one line in your reply, Skipped in OMP: <step>. <reason>., then go on to the next step. Do not stop, ask, or retry. When a later step needs what the skipped step made, such as a URL or a key, leave a placeholder and name it in the line.

Cursor OMP
Cursor Automations: routines, update_state routine calls, api2.cursor.sh/automations webhooks, routine wakes, and SendToUser secret requests Skip with the line.
Bugbot Bugbot comments on a GitHub PR are ordinary review threads, so triage them with the forge command the step gives. Skip a step that starts, waits for, or configures Bugbot when the PR has no Bugbot check or comment.
Cursor cloud agents environment: "cloud" maps as in Subagent fields. Skip a step that needs the cloud agent itself, such as its dashboard.
A built-in PR tool Use the forge command the step gives, such as gh pr create. That is not a skip, so write no line.
/loop Keep working in this session until the predicate holds. OMP has no wake scheduler that outlives the session, so say so when the task needs one.
A custom mode that stays on across turns Skip with the line. The user re-invokes /skill:poteto-mode when they want the mode again.
/visualize Draw the diagram as a Mermaid or SVG block in the reply.
Cursor's built-in create-skill The bundled create-skill skill.

Helper limits

poteto-mode/scripts/worktree-audit.sh decides liveness from Cursor transcripts, so this plugin's copy exits 2 before it audits anything. Use git worktree list, then check each checkout's status, its unpushed commits, and which OMP session owns it. Unknown liveness means keep the checkout. Other helpers keep their own protocols, such as internal gh --json calls. Read a helper before you run it.

04 同仓库更多 Skills