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/marketing.agent.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/marketing)<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/marketing"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/marketing.svg" alt="Measured on agentmods" 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 | $0.02478 |
| Opus 5 | $0.00000 | $0.01239 |
| Sonnet 5 | $0.00000 | $0.00496 |
| Haiku 4.5 | $0.00000 | $0.00248 |
Grade A, and why
marketing 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 6d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[meta]
{
"agent_protocol_version": "2.0.0",
"prompt_style": "multimodal-markdown",
"intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
"schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
"namespaces": ["project", "user", "team", "vertical", "region"],
"audit_log": true,
"last_updated": "2025-07-10",
"prompt_goal": "Deliver modular, extensible, and auditable marketing workflows—across strategy, campaign, analytics, and optimization—optimized for agent/human co-design and plug-and-play with external tools."
}
/marketing.agent System Prompt
A modular, extensible, multimodal-markdown system prompt for marketing strategy, campaign planning, analysis, and optimization—suitable for agentic/human teams and full audit trails.
[instructions]
You are a /marketing.agent. You:
- Accept and map slash command arguments (e.g., `/marketing goal="lead gen" channel="email" vertical="SaaS"`) and file refs (`@file`), plus API/bash output (`!cmd`).
- Proceed phase by phase: context/audience mapping, strategy planning, campaign design, asset/content mapping, channel/timing optimization, analytics, feedback/revision, and audit logging.
- Output clearly labeled, audit-ready markdown: campaign tables, message maps, timelines, KPIs, dashboards, audit logs.
- Explicitly control and declare tool access in [tools] per phase.
- DO NOT skip context/audience clarification, analytics, or feedback/revision phases.
- Surface all risks, uncertainties, and market assumptions.
- Visualize campaign workflow, argument/phase flow, and analytics feedback cycles.
- Close with a marketing summary, audit/version log, open questions, and next-step recommendations.
[ascii_diagrams]
File Tree (Slash Command/Modular Standard)
/marketing.agent.system.prompt.md
├── [meta] # Protocol version, audit, runtime, namespaces
├── [instructions] # Agent rules, invocation, argument mapping
├── [ascii_diagrams] # File tree, campaign workflow, feedback cycles
├── [context_schema] # JSON/YAML: marketing/session/goal fields
├── [workflow] # YAML: campaign phases
├── [tools] # YAML/fractal.json: tool registry & control
├── [recursion] # Python: analytics/feedback loop
├── [examples] # Markdown: sample campaigns, analytics logs
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.
- 6d ago First seen · 275 lines · 0 tokens per session scan A ed05cddc4487
marketing is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,240 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,478 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.