Context Engineering is a handbook and research-oriented course about designing the information supplied to language models at inference time, including context selection, organization, orchestration, and optimization. It is for people building or studying AI agents and other systems that need to provide models with the right information for each task. The catalogue entries contain commands and instructions for using these ideas with coding-agent tools.
Borrowing it
Nothing to install: this file belongs to jasontang-ai/Context-Engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jasontang-ai/Context-Engineering/main/CLAUDE.mdgit clone --depth 1 https://github.com/jasontang-ai/Context-EngineeringWrote 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.
[](https://agentmods.dev/instructions/jasontang-ai/context-engineering/claude-md)<a href="https://agentmods.dev/instructions/jasontang-ai/context-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/jasontang-ai/context-engineering/claude-md/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.
<a href="https://agentmods.dev/instructions/jasontang-ai/context-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/jasontang-ai/context-engineering/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05062 | $0.05062 |
| Opus 5.5 | $0.02025 | $0.02025 |
| Sonnet 5.5 | $0.01012 | $0.01012 |
| Haiku 4.5 | $0.00506 | $0.00506 |
Grade A, and why
Context-Engineering CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 928 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Cognitive Operating System
This document provides a comprehensive framework of cognitive tools, protocol shells, reasoning templates, and workflows for Claude Code. Load this file in your project root to enhance Claude's capabilities across all contexts.
1. Core Meta-Cognitive Framework
Context Schemas
Code Understanding Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Code Understanding Schema",
"description": "Standardized format for analyzing and understanding code",
"type": "object",
"properties": {
"codebase": {
"type": "object",
"properties": {
"structure": {
"type": "array",
"description": "Key files and directories with their purposes"
},
"architecture": {
"type": "string",
"description": "Overall architectural pattern"
},
"technologies": {
"type": "array",
"description": "Key technologies, frameworks, and libraries"
}
}
},
"functionality": {
"type": "object",
"properties": {
"entry_points": {
"type": "array",
"description": "Main entry points to the application"
},
"core_workflows": {
"type": "array",
"description": "Primary functional flows"
},
"data_flow": {
"type": "string",
"description": "How data moves through the system"
}
}
},
"quality": {
"type": "object",
"properties": {
"strengths": {
"type": "array",
"description": "Well-designed aspects"
},
"concerns": {
"type": "array",
"description": "Potential issues or areas for improvement"
},
"patterns": {
"type": "array",
"description": "Recurring design patterns"
}
}
}
}
}
Troubleshooting Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Troubleshooting Schema",
"description": "Framework for systematic problem diagnosis and resolution",
"type": "object",
"properties": {
"problem": {
"type": "object",
"properties": {
"symptoms": {
"type": "array",
"description": "Observable issues"
},
"context": {
"type": "string",
"description": "When and how the problem occurs"
},
"impact": {
"type": "string",
"description": "Severity and scope of the issue"
}
}
},
"diagnosis": {
"type": "object",
"properties": {
"potential_causes": {
"type": "array",
"description": "Possible root causes"
},
"evidence": {
"type": "array",
"description": "Supporting information for each cause"
},
"verification_steps": {
"type": "array",
"description": "How to confirm each potential cause"
}
}
},
"solution": {
"type": "object",
"properties": {
"approach": {
"type": "string",
"description": "Overall strategy"
},
"steps": {
"type": "array",
"description": "Specific actions to take"
},
"verification": {
"type": "string",
"description": "How to confirm the solution worked"
},
"prevention": {
"type": "string",
"description": "How to prevent future occurrences"
}
}
}
}
}
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.
- 2mo ago First seen · 928 lines · 5,062 tokens per session scan A 772aa478077d
Context-Engineering CLAUDE.md is an instructions file published in the GitHub repository jasontang-ai/Context-Engineering (9,274 stars, last pushed 8mo ago), licensed MIT. It adds 5,062 tokens to every session, about $0.0202 per session on Opus 5.5. 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 2026-08-30.
Context-Engineering CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Context-Engineering CLAUDE.mdjasontang-ai/Context-Engineering | Instructions file | 9.3k | 8mo ago | MIT | A | 5,062 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |