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/GEMINI.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/gemini-md)<a href="https://agentmods.dev/instructions/jasontang-ai/context-engineering/gemini-md"><img src="https://agentmods.dev/badge/instructions/jasontang-ai/context-engineering/gemini-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/gemini-md"><img src="https://agentmods.dev/badge/instructions/jasontang-ai/context-engineering/gemini-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 | $0.04417 | $0.04417 |
| Opus 5.5 | $0.01767 | $0.01767 |
| Sonnet 5.5 | $0.00883 | $0.00883 |
| Haiku 4.5 | $0.00442 | $0.00442 |
Grade A, and why
Context-Engineering GEMINI.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 — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - Cognitive Operating System
This document defines enhanced reasoning patterns, protocol shells, and cognitive frameworks to be used by Gemini CLI. These tools provide structured thinking, step-by-step reasoning, and recursive self-improvement capabilities.
Core Reasoning Frameworks
Systematic Problem Solving
/reasoning.systematic{
intent="Break down complex problems into manageable steps with clear logic",
input={
problem="<problem_statement>",
constraints="<any_constraints>",
context="<relevant_context>"
},
process=[
/understand{action="Restate the problem and identify the goal"},
/analyze{action="Break down the problem into components"},
/plan{action="Create a step-by-step approach"},
/execute{action="Work through each step methodically"},
/verify{action="Check the solution against the original problem"},
/refine{action="Improve the solution if needed"}
],
output={
understanding="Clear restatement of the problem",
approach="Structured step-by-step plan",
solution="Detailed implementation",
verification="Proof of correctness"
}
}
Code Analysis & Generation
/code.analyze{
intent="Deeply understand code structure, patterns, and potential improvements",
input={
code="<code_to_analyze>",
language="<programming_language>",
focus="<specific_aspect_to_focus_on>"
},
process=[
/parse{action="Identify key components and their relationships"},
/evaluate{
structure="Assess organization and architecture",
quality="Identify strengths and weaknesses",
patterns="Recognize design patterns in use"
},
/trace{action="Follow execution paths and data flow"},
/suggest{
improvements="Identify potential optimizations",
alternatives="Suggest alternative approaches"
}
],
output={
summary="High-level overview of the code",
components="Breakdown of key elements",
quality_assessment="Evaluation of code quality",
recommendations="Suggested improvements"
}
}
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 · 749 lines · 4,417 tokens per session scan A 6768e17364cb
Context-Engineering GEMINI.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 4,417 tokens to every session, about $0.0177 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 GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Context-Engineering GEMINI.mdjasontang-ai/Context-Engineering | Instructions file | 9.3k | 8mo ago | MIT | A | 4,417 | Gemini CLI |
| 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 |