core-context-management
Manage agent context files, enforce size limits, and optimize token budget allocation
Best use case
core-context-management is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Manage agent context files, enforce size limits, and optimize token budget allocation
Teams using core-context-management should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/context-management/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How core-context-management Compares
| Feature / Agent | core-context-management | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Manage agent context files, enforce size limits, and optimize token budget allocation
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Core Context Management ## Version History - **2.0.0** (2026-01-18): Add file management, continuous improvement, scheduled tasks - **1.1.0** (2026-01-17): Add recovery patterns, auto-archive triggers - **1.0.0** (2026-01-14): Initial context management skill ## Sub-Skills - [Quick Reference](quick-reference/SKILL.md) ## Sub-Skills - [Size Limits (MANDATORY) (+3)](size-limits-mandatory/SKILL.md) - [Response Format Rules (+3)](response-format-rules/SKILL.md) - [Learning from Past Work (+2)](learning-from-past-work/SKILL.md) - [validate_context.sh (+4)](validatecontextsh/SKILL.md) - [Windows Task Scheduler (+2)](windows-task-scheduler/SKILL.md)
Related Skills
context-compaction-handoff
Guardrails for resuming work after context compaction or transcript handoff blocks; prioritize the latest real user request over stale summarized tasks and verify before answering.
wiki-context
Auto-query llm-wiki domains for relevant context before executing domain tasks
cron-job-management
Patterns for creating, testing, debugging, and maintaining cron-driven automation in workspace-hub, including log strategy, failure analysis, and safe git-aware job design.
github-repo-management
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
data-context-extractor
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts
data-management
Comprehensive DataFrame loading, filtering, transformation, and data pipeline management from Excel, CSV, and multiple sources with YAML-driven configuration.
skill-chain-context-optimization
Refactor large or frequently-run skills into context-efficient chains using isolated execution, file-backed handoffs, minimal summaries, and runtime-aware command substitution.
task-management
Simple task management using a shared TASKS.md file for tracking commitments and action items.
memory-management
Two-tier memory system for decoding workplace shorthand, acronyms, nicknames, and internal language.
close-management
Manage the month-end close process with task sequencing, dependencies, and status tracking.
source-management
Configure and query MCP data sources for enterprise search. Use when checking which sources (chat, email, cloud storage, CRM, knowledge base) are connected, connecting new ones, or tuning query priority and rate limits.
knowledge-management
Create, organize, and maintain support knowledge base content to reduce ticket volume