context-window-management SKILL.md skillA

context-window-management from davila7/claude-code-templates is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add davila7/claude-code-templates/context-window-management@git:20261024.13da94c

Pins git:20261024.13da94c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
davila7/claude-code-templates
Path
cli-tool/components/skills/ai-research/context-window-management/SKILL.md
Versions recorded
2
Latest version
git:20261024.13da94c, committed Oct 24, 2026
First version recorded
Jan 25, 2026
Size
1,451 bytes
Repository stars
33,152
License
MIT

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Context Window Management

You're a context engineering specialist who has optimized LLM applications handling
millions of conversations. You've seen systems hit token limits, suffer context rot,
and lose critical information mid-dialogue.

You understand that context is a finite resource with diminishing returns. More tokens
doesn't mean better results—the art is in curating the right information. You know
the serial position effect, the lost-in-the-middle problem, and when to summarize
versus when to retrieve.

Your cor

## Capabilities

- context-engineering
- context-summarization
- context-trimming
- context-routing
- token-counting
- context-prioritization

## Patterns

### Tiered Context Strategy

Different strategies based on context size

### Serial Position Optimization

Place important content at start and end

### Intelligent Summarization

Summarize by importance, not just recency

## Anti-Patterns

### ❌ Naive Truncation

### ❌ Ignoring Token Costs

### ❌ One-Size-Fits-All

## Related Skills

Works well with: `rag-implementation`, `conversation-memory`, `prompt-caching`, `llm-npc-dialogue`

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add davila7/claude-code-templates/context-window-management@sha256:d0a41689a800683d

The line at the top of this page pins the label git:20261024.13da94c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_434wcok4k7pxgy2o.svg)](https://markdownregistry.com/a/art_434wcok4k7pxgy2o)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jan 25, 2026 and Oct 24, 2026, about one every 271 days.

versioncommittedcommitsizeaudit
git:20261024.13da94c latest2026-10-24 13da94c 1,451 BA view · diff
git:20260125.1deb97c2026-01-25 1deb97c 1,439 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1451 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

davila7/claude-code-templates · 33,152 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_434wcok4k7pxgy2o
GET https://markdownregistry.com/api/v1/resolve?ref=davila7/claude-code-templates/context-window-management
GET https://markdownregistry.com/api/v1/blob/d0a41689a800683dd383be3606439a91424506f3728f5f99d5002852709cf78c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from davila7/claude-code-templates

owasp-security SKILL.md skill
davila7/claude-code-templates · .claude-plugin/skills/owasp-security/SKILL.md · Comprehensive OWASP-aligned security guidance across six standards - Top 10 (2021) for web apps, ASVS 5.0, MASVS v2.1.0…
git:20260706.31fc2b5 · audit B · 33,152 stars
CLAUDE.md CLAUDE.md file
davila7/claude-code-templates · CLAUDE.md
git:20261105.cdccca6 · audit A · 33,152 stars
agent-management SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/agent-management/SKILL.md · Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list…
git:20260223.2f9c858 · audit A · 33,152 stars
agent-messaging SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/agent-messaging/SKILL.md · Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when…
git:20260223.2f9c858 · audit A · 33,152 stars
docs-search SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/docs-search/SKILL.md · Search auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments…
git:20260223.2f9c858 · audit A · 33,152 stars
graph-query SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/graph-query/SKILL.md · Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user…
git:20260223.2f9c858 · audit A · 33,152 stars
memory-search SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/memory-search/SKILL.md · Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the…
git:20260223.2f9c858 · audit A · 33,152 stars
planning SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-maestro/planning/SKILL.md · Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a…
git:20260223.2f9c858 · audit A · 33,152 stars
agent-evaluation SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-research/agent-evaluation/SKILL.md · Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and…
git:20261024.13da94c · audit A · 33,152 stars
agent-manager-skill SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-research/agent-manager-skill/SKILL.md · Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
git:20260125.1deb97c · audit A · 33,152 stars
agent-memory-mcp SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-research/agent-memory-mcp/SKILL.md · A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns…
git:20261024.13da94c · audit A · 33,152 stars
agent-memory-systems SKILL.md skill
davila7/claude-code-templates · cli-tool/components/skills/ai-research/agent-memory-systems/SKILL.md · Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the…
git:20261024.13da94c · audit A · 33,152 stars

Every file in davila7/claude-code-templates

Browse by kind, by grade A, or by owner.