context-master

context-master is a skill for Claude Code, Codex from gitstq/awesome-ai-agent-skills. It costs 142 tokens per session (2,056 once invoked), scanned A, original, MIT.

A context-management system for coding agents that organizes task information into always-loaded, on-demand, and archived levels.

In plain words
What is it for?
Use it during extended coding sessions to prioritize active files, recent decisions, related summaries, architecture notes, and error history.
Why use it?
It reduces the chance that long conversations or large codebases cause important decisions and instructions to be forgotten.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Good fit Use it during extended coding sessions to prioritize active files, recent decisions, related summaries, architecture notes, and error history.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gitstq/awesome-ai-agent-skills/context-master
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.

Any agent
npx skills add gitstq/awesome-ai-agent-skills --skill context-master
Clone the repo
git clone --depth 1 https://github.com/gitstq/awesome-ai-agent-skills

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 context-master

README.md
[![agentmods](https://agentmods.dev/badge/skills/gitstq/awesome-ai-agent-skills/context-master.svg)](https://agentmods.dev/skills/gitstq/awesome-ai-agent-skills/context-master)
Your own site
<a href="https://agentmods.dev/skills/gitstq/awesome-ai-agent-skills/context-master"><img src="https://agentmods.dev/badge/skills/gitstq/awesome-ai-agent-skills/context-master.svg" alt="Measured on agentmods" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,056 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00142 $0.02056
Opus 5 $0.00071 $0.01028
Sonnet 5 $0.00028 $0.00411
Haiku 4.5 $0.00014 $0.00206

Measured 8d ago against content hash 81afe4fe70f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

context-master 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 8d 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.

skills/context-master/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Master - Intelligent Context Management System

Stop losing context in long coding sessions. Let Context Master manage your AI's memory intelligently.

The Problem

Every AI coding agent has a context window limit. When conversations get long or codebases are large:

  • The agent "forgets" earlier instructions
  • Important decisions get lost in the noise
  • Repetitive information wastes precious context
  • The agent starts giving contradictory answers

Context Master solves this with a smart, tiered context management system.

Core Architecture

Three-Tier Context Model

┌─────────────────────────────────────────────┐
│  TIER 1: HOT CONTEXT (Always Loaded)         │
│  - Current task description                  │
│  - Active file contents                      │
│  - Recent decisions (last 10)                │
│  - User preferences                          │
│  Budget: 30% of context window               │
├─────────────────────────────────────────────┤
│  TIER 2: WARM CONTEXT (Loaded on Demand)     │
│  - Related file summaries                    │
│  - Architecture decisions                    │
│  - Error history & fixes                     │
│  Budget: 40% of context window               │
├─────────────────────────────────────────────┤
│  TIER 3: COLD CONTEXT (Archived)             │
│  - Old conversation summaries                │
│  - Historical decisions                      │
│  - Resolved issues                           │
│  Accessed via semantic search                │
│  Budget: 30% of context window               │
└─────────────────────────────────────────────┘

Smart Features

1. Automatic Context Budget

The skill calculates optimal context allocation based on:

  • Model context window size (128K, 200K, 1M, etc.)
  • Current usage level (percentage consumed)
  • Task complexity (number of files involved)
  • Conversation length (number of turns)

When context reaches 70% capacity, it automatically:

  1. Summarizes the oldest conversation turns
  2. Archives resolved decisions
  3. Compresses redundant information
  4. Promotes critical info to Tier 1

Read the full file on GitHub · 246 lines

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. 8d ago First seen · 246 lines · 142 tokens per session scan A 81afe4fe70f4

Subscribe to this mod's changes

context-master is a skill published in the GitHub repository gitstq/awesome-ai-agent-skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 142 tokens to every session and 2,056 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

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

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

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens