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/commands/README.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/commands/jasontang-ai/context-engineering/readme)<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/readme"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/readme/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/commands/jasontang-ai/context-engineering/readme"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/readme.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 | $0.00000 | $0.03152 |
| Opus 5.5 | $0.00000 | $0.01261 |
| Sonnet 5.5 | $0.00000 | $0.00630 |
| Haiku 4.5 | $0.00000 | $0.00315 |
Grade A, and why
README 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering AgenticOS
“We shape our tools and thereafter our tools shape us.” — Marshall McLuhan
Anthropic Slash Commands | Subagents
Overview
This directory contains a growing library of modular, customizable, and extendable agents and harnesses embedded as slash commands, forming an Agentic Operating System (AgenticOS) designed for enhancing the capabilities of Claude Code and other frontier systems, such as OpenCode, Amp, Kiro, Codex, Gemini CLI, and more. Each agent implements a standardized workflow with consistent structure, enabling sophisticated context engineering across various domains.
The operating system provides a selection of agents that serve as scaffolds for context-driven AI workflows, leveraging the latest research in cognitive tools, neural field theory, symbolic mechanisms, and quantum semantics to create more capable, interpretable, and predictable AI interactions.
/command Q="query" param="value" [email protected] ...
│
▼
[context]→[specialized_phase_1]→[specialized_phase_2]→...→[synthesis]→[audit/log]
↑___________________feedback/CI___________________|
AgenticOS Library (Under Construction)
| Command | Purpose | Usage Example |
|---|---|---|
alignment.agent.md |
AI safety/alignment evaluation | /alignment Q="prompt injection" model="claude-3" |
cli.agent.md |
Terminal workflow automation | /cli "find all .log files" alias=logscan |
comms.agent.md |
Stakeholder communications | /comms Q="major outage" audience="internal" type="crisis" |
data.agent.md |
Data transformation and validation | /data input="data.csv" op="validate" [email protected] |
deploy.agent.md |
Deployment automation | /deploy target="app" env="staging" version="1.2.0" |
diligence.agent.md |
Due diligence workflows | /diligence target="acquisition" scope="tech" depth="full" |
doc.agent.md |
Documentation generation | /doc target="api" format="markdown" scope="public" |
legal.agent.md |
Legal research and analysis | /legal Q="contract review" jurisdiction="US" type="SaaS" |
lit.agent.md |
Literature review and writing | /literature Q="PEMF effect" type="review" years=3 |
marketing.agent.md |
Marketing strategy and campaigns | /marketing goal="lead gen" channel="email" vertical="SaaS" |
meta.agent.md |
Meta-level agent coordination | /meta agents="research,data" task="market analysis" |
monitor.agent.md |
System/service monitoring | /monitor service="api" period="24h" alert=true |
optimize.agent.md |
Code and process optimization | /optimize target="foo.py" area="speed" mode="aggressive" |
research.agent.md |
Research workflows | /research topic="quantum computing" depth="technical" |
security.agent.md |
Security analysis | /security target="app" scope="full" report="detailed" |
test.agent.md |
Test generation and execution | /test suite="integration" mutate=true report=summary" |
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 · 338 lines · 0 tokens per session scan A e2bf151fff6c
README is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,274 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,152 tokens. 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.
README compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| READMEjasontang-ai/Context-Engineering | Command | 9.3k | 8mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |
| speckit.bug.fixgithub/spec-kit | Command | 148k | yesterday | MIT | A | 12 | Claude Code |