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 principle-guard-the-context-windowgit 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/principle-guard-the-context-window)<a href="https://agentmods.dev/skills/michael-denyer/pstack-claude/principle-guard-the-context-window"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/principle-guard-the-context-window/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/principle-guard-the-context-window"><img src="https://agentmods.dev/badge/skills/michael-denyer/pstack-claude/principle-guard-the-context-window.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 | $0.00046 | $0.00111 |
| Opus 5.5 | $0.00018 | $0.00044 |
| Sonnet 5.5 | $0.00009 | $0.00022 |
| Haiku 4.5 | $0.00005 | $0.00011 |
Grade A, and why
principle-guard-the-context-window 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 13d 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.
Copies of this mod
6 near-identical copies found in the catalogue:
- principle-guard-the-context-window — 100% identical, 0 lines differ
- principle-guard-the-context-window — 95% identical, 2 lines differ
- principle-guard-the-context-window — 95% identical, 9 lines differ
- principle-guard-the-context-window — 95% identical, 8 lines differ
- principle-guard-the-context-window — 94% identical, 11 lines differ
- principle-guard-the-context-window — 92% identical, 11 lines differ
What it actually says
Guard the Context Window
Why: Context overflow degrades reasoning quality, creates compression artifacts, and halts progress.
Pattern:
- Size phases and cap scope. Limit files per phase, set turn budgets, account for mechanism costs.
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.
- 13d ago Changed · -4 lines 6db84b7d5e67
- 1mo ago Changed · -1 lines fa71b4501392
- 1mo ago Changed faa03c333c18
- 1mo ago First seen · 18 lines · 46 tokens per session scan A 5f9f0416730d
principle-guard-the-context-window is a skill published in the GitHub repository michael-denyer/pstack-claude (3,430 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 111 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
context-engine
Loads and manages company context for all C-suite advisor skills. Reads /.claude/company-context.md, detects stale context (older than 90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks…
agents-skills-feedback-loop
Adds per-skill learnings loops for dated patterns, mistakes, and domain facts. Use when wiring skill memory, consolidation, or drift audits.
dev-context-multi-repo
Builds multi-repo context hubs and compiled markdown knowledge maps. Use when profiling repo portfolios or assembling LLM-ready cross-repo knowledge bases.
docs-notes-retrieval
Builds local-first note vault retrieval for Obsidian, markdown notebooks, and NotebookLM-adjacent exports. Use when packaging notes into LLM-ready context.
handoff
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…