principle-guard-the-context-window

principle-guard-the-context-window is a skill for Claude Code, Codex from backnotprop/pstack. It costs 46 tokens per session (243 once invoked), scanned A, original, MIT.

A workflow for managing an AI agent's limited context window, the amount of information it can work with in one session. It routes large material to separate workers and keeps concise summaries in the main conversation.

In plain words
What is it for?
Use it when a task involves many files, large outputs, repeated reads, or parallel work, so only relevant summaries and bounded amounts of information stay in the main context.
Why use it?
It reduces overload from long files, large command outputs, screenshots, and repeated reading, which can make reasoning less reliable.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/backnotprop/pstack/principle-guard-the-context-window
Any agent
npx skills add backnotprop/pstack --skill principle-guard-the-context-window
Clone the repo
git clone --depth 1 https://github.com/backnotprop/pstack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for principle-guard-the-context-window

README.md
[![agentmods](https://agentmods.dev/badge/skills/backnotprop/pstack/principle-guard-the-context-window.svg)](https://agentmods.dev/skills/backnotprop/pstack/principle-guard-the-context-window)
Your own site
<a href="https://agentmods.dev/skills/backnotprop/pstack/principle-guard-the-context-window"><img src="https://agentmods.dev/badge/skills/backnotprop/pstack/principle-guard-the-context-window.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00243
Opus 5 $0.00023 $0.00121
Sonnet 5 $0.00009 $0.00049
Haiku 4.5 $0.00005 $0.00024

Measured 4d ago against content hash 291d0125125e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

skills/principle-guard-the-context-window/SKILL.md · 18 lines

What it actually says

Guard the Context Window

The context window is finite and non-renewable within a session. Every token that enters should earn its place.

Why: Context overflow degrades reasoning quality, creates compression artifacts, and halts progress. Unlike compute or time, context spent inside a session cannot be reclaimed.

Pattern:

  • Isolate large payloads. Route verbose outputs, screenshots, and large documents to subagents. The main context gets summaries, not raw data.
  • Don't read what you won't use. Read selectively based on relevance. If a file isn't needed for the current task, skip it.
  • Keep frequently used content inline. Templates and references used on every invocation belong in the skill file, not in separate files that cost a read each time.
  • Size phases and cap scope. Limit files per phase, set turn budgets, account for mechanism costs.
Changes

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.

  1. 4d ago First seen · 18 lines · 46 tokens per session scan A 291d0125125e

Subscribe to this mod's changes

principle-guard-the-context-window is a skill published in the GitHub repository backnotprop/pstack (193 stars, last pushed 15d ago), licensed MIT. It adds 46 tokens to every session and 243 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens