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.
npx skills add pnp/copilot-prompts --skill prompt-context-engineergit clone --depth 1 https://github.com/pnp/copilot-promptsWrote 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/skills/pnp/copilot-prompts/prompt-context-engineer)<a href="https://agentmods.dev/skills/pnp/copilot-prompts/prompt-context-engineer"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/prompt-context-engineer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 94 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00180 | $0.01817 |
| Opus 5 | $0.00090 | $0.00908 |
| Sonnet 5 | $0.00036 | $0.00363 |
| Haiku 4.5 | $0.00018 | $0.00182 |
Grade A, and why
prompt-context-engineer 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Context Engineer
Convert a raw prompt or request into a structured prompt built on context engineering principles.
The guiding idea, from Andrej Karpathy: context engineering is "the delicate art and science of filling the context window with just the right information for the next step." A prompt is not one clever sentence — it is everything the model sees. The job is to supply each piece of context the task genuinely needs (task framing, background, examples, constraints, output format) and ruthlessly exclude everything it doesn't. Too little or wrongly-formed context and the model can't perform; too much or irrelevant context and quality degrades and cost rises.
Workflow
Follow these four steps in order.
Step 1 — Diagnose the raw prompt
Read the user's original prompt or request and determine:
- Target type — Is this a one-off prompt for a chat assistant, or a reusable system prompt / API instruction? Cues: "system prompt", "for my app", "API", "agent" → system prompt. Otherwise default to a chat prompt. If building a system prompt, also identify what the user turns will contain.
- Task type — generation (writing, code), transformation (summarize, translate, rewrite), extraction/analysis, classification, conversation/roleplay, or agentic/multi-step.
- Component audit — Check the raw prompt against the context component checklist below. Mark each component as PRESENT, INFERABLE (you can supply a sensible default), or UNCLEAR (genuinely ambiguous and materially affects the output).
Context component checklist:
| Component | What it answers |
|---|---|
| Task definition | What exactly should the model do? What does "done" look like? |
| Role / perspective | What expertise or persona should the model adopt, if any? |
| Background / data | What facts, documents, or domain knowledge does the task depend on? |
| Audience | Who consumes the output, and at what expertise level? |
| Examples (few-shot) | Would 1–3 input→output examples disambiguate the task? |
| Constraints | Length, tone, scope, things to avoid, edge-case handling |
| Output format | Structure: prose, list, JSON, table, markdown, specific template |
| State / history | For multi-turn or agentic prompts: what prior state must be carried? |
| Success criteria | How will the user judge whether the output is good? |
What ships with it
6 files 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.
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.
- 8d ago First seen · 100 lines · 180 tokens per session scan A 1258ad569b64
prompt-context-engineer is a skill published in the GitHub repository pnp/copilot-prompts (871 stars, last pushed 4d ago), licensed MIT. It adds 180 tokens to every session and 1,817 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
image-prompt-builder-nl
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt"…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
813-regulations-iso-42001
Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…