Michael DenyerBioinformatician at Wisdom Panel; pstack, 3.4k+ stars349 installs on skills.sh

Principle Guard the Context Window

Apply when context is filling up: large outputs.

Works in any agentClaude CodeCodexCursorClaude appChatGPT+ any other agent
michael-denyer/pstack-claude
Security state: reviewed

3 static scans, 0 counted findings.

Edge checks it again each time your agent loads it.

SKILL.md1 file · 930 bytes

From the michael-denyer public repository. Edge did not write or edit this skill.

What it does

  • Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
  • Route bulk to subagents; keep summaries in the main thread, not raw payloads.
MD

Why Michael Denyer

Software engineer and bioinformatician at Wisdom Panel. Each fact links its public source.

  • Role at Wisdom Panel

    His GitHub profile lists Wisdom Panel as employer and "Software Engineer and Bioinformatician" as his bio.

    GitHub profile
  • Popular agent workflow repo

    pstack-claude has 3.4k+ GitHub stars.

    GitHub repo

Public sources, checked Oct 26, 2026.

How it works

  1. 1
    Copy

    Try for free gives you one prompt.

  2. 2
    Paste

    Paste it into Claude Code, Codex or Cursor.

  3. 3
    Ask

    Ask for the outcome. Your agent loads Principle Guard the Context Window.

What you can inspect

3 static scans, 0 counted findings.

Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.

State definitions
SKILL.md930 bytes · Open on GitHub

Skill details

Security scansReviewed

3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.

Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .

Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.

Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .

Edge static checks
Pass · 0 counted findings · 2026-09-27
Cisco skill-scanner
Pass · 0 counted findings · 2026-09-27
Semgrep Edge rules
Pass · 0 counted findings · 2026-09-27
Creator, source & licencemichael-denyer

From the michael-denyer public repository. Edge did not write or edit this skill.

Revision
c02fd4922b25ee005f42042463d741d236c2c35e
Package hash
sha256:b20e3ae13e86719577fdd3d4984b28dd971ec9957f879dbd39b1f00b3cd0af29
Licence
MIT
Description
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Quoted from the skill’s own description
Read skill files1 file

1 file, 930 bytes at revision c02fd4922b25.

Questions about Principle Guard the Context Window

What does Principle Guard the Context Window do?

Apply when context is filling up: large outputs. Published by Michael Denyer (michael-denyer/pstack-claude).

Is Principle Guard the Context Window safe to use?

Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.

How do I use Principle Guard the Context Window in Claude Code, Codex or Cursor?

Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.