cursor-context-architecture

cursor-context-architecture is a skill for Claude Code, Codex from navendubrajesh/context-management-for-agents. It costs 86 tokens per session (1,167 once invoked), scanned A, original, MIT.

A guide to how Cursor's AI coding agent finds, receives, and fits information into its context window, including indexed code, manually attached files, rules, tools, and subagents. The context window is the limited amount of information the agent can use in one interaction.

In plain words
What is it for?
Use it to troubleshoot Cursor search and context problems, tune ignore files, decide when to attach files, or assess large-context and Max modes.
Why use it?
It helps explain why the agent may miss code or run out of useful context even when the files exist. It also supports decisions about indexing exclusions, file attachments, and context budgets.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md; mentions Cursor.

Good fit Use it to troubleshoot Cursor search and context problems, tune ignore files, decide when to attach files, or assess large-context and Max modes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/navendubrajesh/context-management-for-agents/cursor-context-architecture
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 navendubrajesh/context-management-for-agents --skill cursor-context-architecture
Clone the repo
git clone --depth 1 https://github.com/navendubrajesh/context-management-for-agents

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 cursor-context-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture/github.svg)](https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture)
Your own site
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cursor-context-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/cursor-context-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,167 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 $0.00086 $0.01167
Opus 5 $0.00043 $0.00583
Sonnet 5 $0.00017 $0.00233
Haiku 4.5 $0.00009 $0.00117

Measured 11d ago against content hash 8eee5c8325ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cursor-context-architecture 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 11d 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/cursor-context-architecture/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Context Architecture

Cursor's context system combines automatic codebase indexing, user-selected @ attachments, project/user/team rules, and agent tool chains into a single fixed-size context window. Unlike inline-tab completion systems, Cursor Agent actively searches, reads, and compresses — but every component competes for the same token budget.

When to Activate

Activate this skill when:

  • Diagnosing why Cursor Agent cannot find relevant code despite it existing in the repo
  • Understanding what @-mentions, rules, MCP servers, and skills cost in the context ring
  • Tuning .cursorignore / .cursorindexingignore for indexing vs access control
  • Deciding when to use @ files vs letting Agent search autonomously
  • Evaluating Max mode or large-context models against effective usable capacity

Do not activate this skill for adjacent work owned by other skills:

  • Do not activate for platform-agnostic attention mechanics: context-fundamentals.
  • Do not activate for writing or restructuring .mdc rules: cursor-customization.
  • Do not activate for long-session compaction tactics: cursor-session-management.
  • Do not activate for building external RAG pipelines: memory-systems.

Core Concepts

Codebase semantic indexing

Cursor indexes open workspaces into vector embeddings using a custom embedding model. Code is chunked at meaningful boundaries (functions, classes, logical blocks), embedded, and stored in a vector database. Indexing starts on workspace open; semantic search becomes available at ~80% index completion and syncs changed files every ~5 minutes.

Practical lever: semantic search + grep together outperform grep alone on large codebases (Cursor reports ~12.5% accuracy improvement on 1000+ file repos). Agent chains semantic search → grep → file reads without the user choosing tools.

@-mention context channel

Typing @ attaches explicit context: files/folders, indexed docs, terminal output, past chats, git diffs, browser state. @ mentions are the highest-precision lever when the relevant files are known; skip them when scope is unclear and let Agent search.

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 81 lines · 86 tokens per session scan A 8eee5c8325ab

Subscribe to this mod's changes

cursor-context-architecture is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,167 once invoked, about $0.0004 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