pstack-claude

Ochiq manbalardan

Poteto pstack’ning Claude Code, Codex, Copilot, Pi, OpenCode, Gemini va Prime Agent uchun versiyalari. Boshqa muhitlarga moslashtirilgan Cursor primitivlari bilan qat’iy agent ish jarayonlari.

Mashina tarjimasi · Asl matnni koʻrsatish

Claude Code, Codex, Copilot, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

AI skillKategoriya: AI koʻnikmalari · Koʻnikmalar toʻplamlari · Dasturiy muhandislikOpen sourcemaʼlumot tekshirilgan: 15-okt, 2026

Sharh

  • agent-plugin
  • agent-skills
  • agentic-ai
  • anthropic
  • chatgpt
  • claude
  • claude-code
  • claude-code-skills
  • claude-plugin
  • claude-skills

Oʻrnatish

Buyruqlar faqat koʻrsatiladi, marketpleys ularni bajarmaydi. Rasmiy hujjatlar bilan solishtiring.

Moslik

«Nomaʼlum» dalil topilmaganini bildiradi, mahsulot mos emasligini emas.
PlatformaHolatArxitekturaDalilIshonchlilik
Claude CodeNomaʼlum———
Claude (web & desktop)Nomaʼlum———
OpenAI CodexNomaʼlum———
ChatGPTNomaʼlum———
CursorNomaʼlum———
GitHub CopilotNomaʼlum———
Gemini CLINomaʼlum———

Relizlar

tekshirilgan: 29-okt, 2026
v0.9.112Oxirgi29-okt, 2026Rasmiy manba ↗

0.9.112 versiyasi fayllari

Relizga fayllar biriktirilmagan.

Relizlar tarixi

Sifat profili

algoritm quality-v1.0 · baholangan 15-okt, 2026
Sifat bahosi83
Xavf bahosi0
Ishonchlilik 1.00
Sifat bahosi va xavf bahosi — turli koʻrsatkichlar. Yuqori sifat xavfsizlikni kafolatlamaydi.

Baho tarkibi

Qoʻllab-quvvatlash · 2020
last activity 0 days ago
Hujjatlar · 1515
README 5544 chars, description present
Foydalanishga tayyorlik · 156
install instructions: no; releases: yes
Metamaʼlumotlar · 108
3/4 of description, homepage, license, topics
Relizlar · 1010
10 release(s), latest 0 days ago
Kategoriya aniqligi · 107
classifier confidence 0.65
Ommaboplik · 108
2256 stars (log-dampened, 10k = max)
Litsenziya aniqligi · 55
SPDX MIT
Hamjamiyat · 55
issues enabled, 223 forks

Litsenziya

MIT
Litsenziya maʼlumrepozitoriy xostingi maʼlumotlariga koʻra

Bu katalog siyosati holati, yuridik xulosa emas.

Manbalar

github.com/michael-denyer/pstack-claudeAsosiy★ 2 256 yulduzfaollik: 15-okt, 2026Asosiy repozitoriy · Ishonchlilik 1.00

Sharhlar

Sharh yozish uchun kiring

Hali sharhlar yoʻq.

Muqobillar

ChisleOʻxshash
AI kodlash agentingizning token xarajatlarini uch yoʻnalishda kamaytiring: ixcham matn, YAGNI tamoyili asosidagi kod va asbob chiqishlarini siqish. Claude Code, Pi, Cursor, Codex, Gemini va yana 4 ta. Bogʻliqliklarsiz, yutqazgan sinovlarni ham oʻz ichiga olgan ochiq benchmarklar.AI koʻnikmalari
agentsOʻxshash
Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity va Pi uchun koʻp platformali agentli plagin marketpleysiMIT · AI koʻnikmalari
one-skill-to-rule-them-allOʻxshash
Oʻzini ham qoʻshgan holda barcha koʻnikmalaringizni yaratadi va takomillashtiradi. Ish sessiyalaringizni (avtonom yoki inson rahbarligidagi) kuzatadi, namunalar, tuzatishlar va mulohaza bilan qabul qilingan qarorlarni qayd etadi hamda ularni koʻnikmalarni takomillashtirish va yangi koʻnikma nomzodlariga aylantirib, koʻrib chiqishingiz uchun taqdim etadi. Augmented ning amaliy qoʻllanilishiCC-BY-4.0 · AI koʻnikmalari
planning-with-filesOʻxshash
AI kodlash agentlari va uzoq davom etadigan vazifalar uchun doimiy fayl asosidagi rejalashtirish. Nosozliklarga chidamli markdown rejalar, /clear va kontekstni siqishdan keyin sessiyani tiklash, kontekst buzilishiga qarshi har bir bosqichda qayta kiritish, deterministik yakunlash nazorati. Manus uslubida. npm, Claude Code plagin marketpleysi yoki npx sk orqali oʻrnatingMIT · AI koʻnikmalari
claude-skillsOʻxshash
Claude Code uchun 380 ta koʻnikma va agent koʻnikmalari hamda plagin (30+ agent, 70+ maxsus buyruq, 380+ koʻnikma, moslashtiriladigan maʻlumotnomalar, skriptlar) — Claude Code, Codex, Gemini CLI, Cursor va yana 8 ta kod agenti uchun: injiniring, marketing, mahsulot, muvofiqlik, C-darajadagi maslahat, tadqiqot, biznes-jarayonlar, kommersMIT · AI koʻnikmalari
claude-skillsOʻxshash
Texnologik stekka bogʻliq boʻlmagan Claude Skills koʻnikmalari veb-sayt hayot siklining toʻliq qamrovini taʼminlaydi: brend, dizayn, kontent, SEO, dasturlash, ekspluatatsiya, oʻsish va tadqiqot. Yarating, ishga tushiring, tekshiring va optimallashtiring.MIT · AI koʻnikmalari

README

michael-denyer/pstack-claude dan · litsenziya MIT · yuklangan 29-okt, 2026

pstack

[Buy Me A Coffee]

Lauren Tan's pstack is an opinionated Cursor skill stack that improves agent outcomes. This is a port for Claude Code, Codex, Pi, GitHub Copilot, Muse, and other agent harnesses. It tracks upstream and also carries named policy forks, each declared in tools/forks.json.

Tell poteto-mode your goal and it will invoke the correct workflow for the task. It keeps your code concise, simple and verified.

For concurrency bugs and invariants that tests cannot reach, /create-formal-verification-skill picks the riskiest property in your code, verifies it with a tool that fits, and leaves a project skill the next agent reruns. The separate agent-formal-verify plugin goes deeper on the method, with guided TLA+ model checking, Lean proofs, and Kani for Rust.

Built for Claude Code

This port translates upstream's Cursor skills for Claude Code before installation. Upstream's Claude Code install asks agents to translate Cursor names at runtime, using extra tokens and relying on them to apply the mapping correctly. This port also adds a SessionStart hook that routes tasks to poteto-mode.

Install

Run in Claude Code 2.1.292 or later:

/plugin marketplace add michael-denyer/pstack-claude
/plugin install pstack@pstack-claude

Claude Code leaves auto-update off for third-party marketplaces, so pstack stays on the version you installed. To turn it on, run /plugin, open the Marketplaces tab, select pstack-claude, and choose Enable auto-update. To update once by hand, run claude plugin update pstack@pstack-claude.

Run in your terminal:

codex plugin marketplace add michael-denyer/pstack-claude
codex plugin add pstack@pstack-claude

Run in your terminal:

pi install git:github.com/michael-denyer/pstack-claude

The package loads the skills and the pstack Pi extension, which adds the subagent, question, and wake-up tools the skills use, plus /loop and the routing instruction. Invoke a skill with /skill:<name>.

Run in your terminal:

copilot plugin marketplace add michael-denyer/pstack-claude
copilot plugin install pstack@pstack-claude

This installs pstack for the Copilot CLI and the GitHub Copilot app, which share ~/.copilot. Start a new session afterwards. Copilot ships no default pstack models, so the first skill that needs one runs setup-pstack to pick from the models your account lists, and later sessions reuse that choice.

The Copilot build is tested on Copilot CLI 1.0.87 through 1.0.92. On those versions the routing hook's context reaches the session alongside other plugins' session-start context. If a later version keeps only one plugin's context, setup-pstack offers a standing instruction for ~/.copilot/copilot-instructions.md instead. On 1.0.92, once the CLI caches its computer-use experiment assignment, copilot -p sessions list no plugin skills and a skill call returns "Skill not found". Interactive sessions, the hooks, and the agents are unaffected.

Run in your terminal:

git clone https://github.com/michael-denyer/pstack-claude
cd pstack-claude
muse plugins install ./plugins/pstack
muse plugins approve pstack

The first command installs the native Muse plugin bundle. The second approves its SessionStart hook and agent definitions, which Muse runs only after approval. Start a new session afterwards. Invoke a skill with /<name> (for example /poteto-mode), which Muse lists for each user-invocable skill.

OpenCode (the CLI and the desktop app), Gemini CLI, Prime Agent, and skills-only Codex installs read skills from ~/.agents/skills/. Run in your terminal:

git clone https://github.com/michael-denyer/pstack-claude
cd pstack-claude
mkdir -p ~/.agents/skills
for s in plugins/pstack/skills/*/; do
  target=~/.agents/skills/"$(basename "$s")"
  test -e "$target" || test -L "$target" || ln -s "$(pwd)/$s" "$target"
done

To update, run git pull in the clone, then run the for loop again to link skills added since the last run. These installs have no routing hook, so ask for poteto-mode by name or add a standing instruction to the harness's instruction file. See shared installation for per-harness notes and uninstalling.

Configure

pstack routes tasks to poteto-mode automatically. At session start, a hook injects an instruction that points the agent at it: the plugin's hook on Claude Code, Codex, GitHub Copilot, and Muse, and the pstack extension on Pi. Codex runs the hook only after you trust it through /hooks, and Muse only after muse plugins approve pstack. Other harnesses have no hook.

Run setup-pstack to turn automatic routing on or off, change model defaults, or set a reasoning effort per role (arena runners: opus @xhigh, fable @max).

Getting started

Use poteto-mode to fix the search filter resetting when I change pages.

For a bug, it reproduces the failure, uses how and why to investigate, delegates the fix, then reruns the failing case. If the fix crosses a function boundary, it brings in architect before implementation. You receive the fix and the failing and passing evidence.

Other playbooks cover planning, features, refactoring, performance issues, investigations, prototypes, PR maintenance, shipping, and longer projects.

[poteto-mode on Claude Code, Codex, and Pi turns a request into verified work. Choose a playbook, plan and delegate with architect, arena, or swarm, then review and verify with interrogate, tests, and measurements. Project playbooks customize the workflow, and setup-pstack configures the model and reasoning effort per role. Supporting skills include how, why, and unslop.]

Details

Data handling

pstack has no server or telemetry. Anything its skills ask your agent to read, including session transcripts, goes to your model provider. Scripts run locally, and PR tools use your GitHub CLI login.

Contributing

Thanks for helping make this port better. Bug reports, documentation fixes, and runtime improvements are welcome. See CONTRIBUTING.md for the checks and where your change belongs. Report vulnerabilities privately as described in SECURITY.md.

To support maintenance of this port, buy the maintainer a coffee.

License

This port, including its modifications and additions, is also MIT-licensed, © 2026 Michael Denyer. Original pstack © 2026 Lauren Tan; imported cursor-team-kit and thermos skills © 2026 Cursor. See LICENSE-cursor-team-kit, LICENSE-thermos, and NOTICE.md.

Repozitoriyni ochish ↗