pstack-claude is a set of opinionated coding-agent skills and workflows ported from Cursor to Claude Code, Codex, Pi, and other agent harnesses. It guides agents toward concise, simple, and verified code by routing goals to suitable workflows and supporting subagent tools. The catalogue entries are the project's skills, agents, hook, and plugin implementations for these agent environments.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add michael-denyer/pstack-claude --skill poteto-modegit clone --depth 1 https://github.com/michael-denyer/pstack-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/michael-denyer/pstack-claude/poteto-mode)<a href="https://agentmods.dev/skills/michael-denyer/pstack-claude/poteto-mode"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/poteto-mode/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/michael-denyer/pstack-claude/poteto-mode"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/poteto-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.06067 |
| Opus 5.5 | $0.00020 | $0.02427 |
| Sonnet 5.5 | $0.00010 | $0.01213 |
| Haiku 4.5 | $0.00005 | $0.00607 |
Grade A, and why
poteto-mode scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
5 near-identical copies found in the catalogue:
- poteto-mode — 91% identical, 68 lines differ
- poteto-mode — 89% identical, 41 lines differ
- poteto-mode — 89% identical, 170 lines differ
- poteto-mode — 84% identical, 119 lines differ
- Poteto Mode — 80% identical, 73 lines differ
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Poteto mode
Bundled skills live at ../<name>/SKILL.md from this file, so put this file's absolute path in every poteto-agent prompt.
Platform Adaptation
These skills use Claude Code tool names (the Skill tool, the Agent tool, AskUserQuestion) and the Claude model names the Agent tool accepts, as each Models section lists them. On Claude Code they work as written. On Codex, read references/codex-tools.md for the Codex equivalent of a Claude tool, model, or skill named by these workflows. On Pi, read references/pi-tools.md instead. On GitHub Copilot, CLI or app, read references/copilot-tools.md instead. On Muse, read references/muse-tools.md instead. Other runtimes can discover the same Agent Skills tree, but they must use their own tool, model, and configuration equivalents. No one of these mappings is a cross-runtime map.
Use the session's task-tracking tools for the todolist. On Claude Code these are TaskCreate and TaskUpdate, or TodoWrite when configured. Availability depends on the model; CLAUDE_CODE_ENABLE_TODO_TOOLS=1 enables them through the environment or a project's .claude/settings.local.json env block. See the task-tool documentation. If no task-tracking tool is available, keep an uncommitted todo.md Markdown checklist in the work dir, next to the decision trail, with the playbook steps verbatim and each skip: <reason> line. When several sessions share the checkout, name it .audit/<task-slug>.todo.md, beside that session's .audit/<task-slug>.tsv trail, so they never write one file.
Non-negotiables
The Principles section below grounds every trigger. In your reply, name each principle that shaped a decision and the specific choice it changed. Cite only principles whose leaf SKILL.md you read this session.
Remaining triggers:
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- playbooks/authoring-a-skill.md 852 B
- playbooks/autonomous-run.md 1.9 KB
- playbooks/autopilot-full.md 8.0 KB
- playbooks/autopilot-stack.md 2.7 KB
- playbooks/babysit.md 7.9 KB
- playbooks/bug-fix.md 2.3 KB
- playbooks/eval.md 2.5 KB
- playbooks/feature.md 3.4 KB
- playbooks/hillclimb.md 4.4 KB
- playbooks/investigation.md 928 B
- playbooks/multi-phase-plan.md 13 KB
- playbooks/opening-a-pr.md 5.8 KB
- playbooks/orchestrate.md 17 KB
- playbooks/pause-safely.md 1.9 KB
- playbooks/perf-issue.md 1.5 KB
- playbooks/prototype.md 2.1 KB
- playbooks/refactoring.md 3.3 KB
- playbooks/runtime-forensics.md 1.3 KB
- playbooks/session-pickup.md 2.3 KB
- playbooks/shipping.md 7.1 KB
- playbooks/trace-forensics.md 1.8 KB
- playbooks/visual-parity.md 1.2 KB
- playbooks/worktree-cleanup.md 4.3 KB
- references/agents/comment-sicko.md 2.2 KB
- references/bugbot-triage.md 9.4 KB
- references/codex-tools.md 11 KB
- references/copilot-tools.md 20 KB
- references/licenses/LICENSE 1.1 KB
- references/licenses/LICENSE-cursor-team-kit 1.0 KB
- references/licenses/LICENSE-thermos 1.0 KB
- references/licenses/NOTICE.md 1.9 KB
- references/merge-safety.md 5.1 KB
- references/muse-tools.md 12 KB
- references/pi-tools.md 20 KB
- references/resume-storage.md 3.6 KB
- scripts/.prettierignore 689 B
- scripts/.prettierrc.json 29 B
- scripts/bootstrap.ts 1.8 KB runs code
- scripts/bun.lock 6.5 KB
- scripts/check-plan.mjs 8.3 KB runs code
- scripts/check-plan.test.ts 3.4 KB runs code
- scripts/check-playbooks.mjs 3.0 KB runs code
- scripts/orch/orch.test.ts 48 KB runs code
- scripts/orch/orch.ts 15 KB runs code
- scripts/orch/store.ts 52 KB runs code
- scripts/package.json 344 B
- scripts/resume.mjs 7.1 KB runs code
- scripts/tsconfig.json 304 B
- scripts/watch-pr/cli.test.ts 11 KB runs code
- scripts/watch-pr/cli.ts 8.1 KB runs code
- scripts/watch-pr/deadline.ts 522 B runs code
- scripts/watch-pr/fakes.test-helper.ts 3.9 KB runs code
- scripts/watch-pr/github.test.ts 25 KB runs code
- scripts/watch-pr/github.ts 32 KB runs code
- scripts/watch-pr/integrity.test.ts 24 KB runs code
- scripts/watch-pr/landing.ts 2.9 KB runs code
- scripts/watch-pr/live-merge-safety.mjs 7.4 KB runs code
- scripts/watch-pr/policy.test.ts 33 KB runs code
- scripts/watch-pr/policy.ts 29 KB runs code
- scripts/watch-pr/render.ts 8.9 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed c0dc3827dd20
- 4d ago Changed 3bea074a0bc0
- 5d ago Changed · +2 lines 00dbecc912e0
- 8d ago Changed · +2 lines 40cd8f4485e1
- 9d ago Changed 945224f1a33c
- 13d ago Changed 9bcd30d1b65e
- 15d ago Changed · +2 lines f7278881da2a
- 17d ago Changed · +4 lines 93eb871abeef
- 18d ago Changed 611a6c396c06
- 19d ago First seen · 164 lines · 49 tokens per session scan A f20a03a61717
poteto-mode is a skill published in the GitHub repository michael-denyer/pstack-claude (3,186 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 6,067 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.