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 arenagit 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/arena)<a href="https://agentmods.dev/skills/michael-denyer/pstack-claude/arena"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/arena/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/arena"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/arena.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- 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 | $0.00058 | $0.01386 |
| Opus 5.5 | $0.00023 | $0.00554 |
| Sonnet 5.5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
arena 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 2d ago.
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.
This is a copy
86% identical to arena — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arena
On Codex, read the platform mapping, including its per-skill notes, before following this skill.
On GitHub Copilot, read the platform mapping, including its per-skill notes, before following this skill.
On Muse, read the platform mapping, including its per-skill notes, before following this skill.
Open a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.
Phase A: Frame
Every candidate gets the same prompt, so the prompt is the contract.
- State the artifact each candidate is producing.
- Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on this task. It is the picker's tool in Phase D. Candidates only see the task.
- Pick the runners. Use the
arena runnersline inpstack-models.md. If the sheet or that line is missing, run one each on the defaults in Models. Anautoorinherit-parententry in this line or the cross-judge line means the parent model, so omitmodelfor it. If theAgenttool rejects a configured entry, run that seat on its family's default and say so. Families go by model name, such as Opus, Fable, or Sonnet. With no family match, use the single-role default in Models. If it rejects a default, use the closest valid slug of the same family from its error message. Spawn more runners when the arena covers multiple design directions. Use the same model N times when the work is generation-bound rather than judgment-sensitive. Pick each subagent's reasoning level for the job, per the Subagents section of the poteto-mode skill. - Give each candidate its own output location (a git worktree where possible, otherwise
/tmp/arena-<slug>/candidate-<n>/), per the separate-before-serializing-shared-state principle skill.
Phase B: Fan out
Spawn all N subagents in one message with run_in_background: true, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected.
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.
- 2d ago Changed · +2 lines 81327dd64a4e
- 7d ago Changed 7fea2b6eb1e6
- 10d ago Changed · -23 lines cd3773b64fd6
- 14d ago Changed 7807e00c4ad6
- 17d ago Changed · +2 lines 26e8365a64c3
- 27d ago Changed · +4 lines f59c0e268fef
- 29d ago Changed 5590eb0d3e52
- 1mo ago Changed 62592f511ccd
- 1mo ago Changed 707c2da187a1
- 1mo ago First seen · 80 lines · 58 tokens per session scan A a6db34a09d02
arena is a skill published in the GitHub repository michael-denyer/pstack-claude (3,302 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,386 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to arena, differing in 15 lines, and is treated as a copy.
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.
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.
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.
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.
cl-analyze
Analyze one ClosedLoop feature ticket from a URL or FEA slug before execution. Use when asked to assess ticket complexity, feasibility, readiness, applicable requirements PRDs and missing PRD links, UI design guidance, human UI plan approval needs, blockers, legacy split lineage, merge-batch compatibility, nonsensical…
software-ai-integration
Applies production AI integration patterns for chat, structured output, guardrails, provider routing, and AI UX. Use when adding LLM-powered features to an application.