principle-guard-the-context-window

principle-guard-the-context-window is a skill for Claude Code, Codex from painhardcore/pstack. It costs 46 tokens per session (235 once invoked), scanned A, a copy of principle-guard-the-context-window, MIT.

A set of rules for managing an AI agent's limited context window, the amount of information it can actively use in one session. It recommends summarizing large inputs and routing bulky work to separate agents.

In plain words
What is it for?
Handling large outputs, long files, repeated reads, and multi-part tasks by limiting scope and keeping concise summaries.
Why use it?
It helps keep long coding sessions focused when files, command output, screenshots, or repeated research begin to consume too much context.

Skill for Claude CodeCodex

Part of the pstack plugin — 41 skills, 2 agents shipped together

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

Made for: Claude Code, Codex.

Or install pstack, the plugin that ships this one along with the rest of its 41 skills, 2 agents.

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/painhardcore/pstack/principle-guard-the-context-window.svg)](https://agentmods.dev/skills/painhardcore/pstack/principle-guard-the-context-window)
Your own site
<a href="https://agentmods.dev/skills/painhardcore/pstack/principle-guard-the-context-window"><img src="https://agentmods.dev/badge/skills/painhardcore/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 235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00235
Opus 5 $0.00023 $0.00118
Sonnet 5 $0.00009 $0.00047
Haiku 4.5 $0.00005 $0.00023

Measured 5d ago against content hash 17301d7bd38c, 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 5d 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

This is a copy

91% identical to principle-guard-the-context-window — 5 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.

.opencode/skills/principle-guard-the-context-window/SKILL.md · 17 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. 5d ago First seen · 17 lines · 46 tokens per session scan A 17301d7bd38c

Subscribe to this mod's changes

principle-guard-the-context-window is a skill published in the GitHub repository painhardcore/pstack (1 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 235 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to principle-guard-the-context-window, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

self-evolving-memory-graph

Grants the AI long-term episodic memory. The agent autonomously documents the user's coding preferences, past mistakes to avoid, and architectural decisions into a persistent learning graph.

roedyrustam/vibes-plug · 41 tokens

token-saver

Skill to implement token saving scheme, concise, and focused on essential changes / Skill untuk menerapkan skema penghematan token, ringkas, dan fokus pada perubahan esensial tanpa basa-basi.

roedyrustam/vibes-plug · 45 tokens

pm-engine

Interface with the PM-ENGINE-MEMORY file — the operator's accumulated PM tacit knowledge database. Enables agents to reference, search, and apply TK (Tacit Knowledge) entries, and supports TK extraction from experience (--mode extract), TK querying and referencing (--mode query), and TK-to-instruction conversion…

kimsanguine/hplan · 134 tokens

lore

Use when answering any domain or knowledge question in a project linked to a lore (its CLAUDE.md has a "## Knowledge Base" section naming the lore path), and as the shared contract for all lore- skills. Defines the lore folder layout, page schema, retrieval ladder, index regeneration, and citation rules.

barakgut/lore · 67 tokens

memory-arch

Design an agent memory system — working memory, episodic memory, semantic memory, and procedural memory. Use when building agents that need to remember context across sessions, learn from interactions, or maintain persistent knowledge. Covers storage strategy, retrieval patterns, and context management.

kimsanguine/hplan · 56 tokens

lore-init

Use when the user runs /lore:lore-init [path] [--no-git] — create the lore folder, scaffold its layout with its CLAUDE.md schema, and git-init it unless --no-git. Writes nothing outside the lore folder.

barakgut/lore · 58 tokens