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 getcrew44/crew44 --skill context-engineering-advisorgit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/context-engineering-advisor)<a href="https://agentmods.dev/skills/getcrew44/crew44/context-engineering-advisor"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/context-engineering-advisor/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/skills/getcrew44/crew44/context-engineering-advisor"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/context-engineering-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Memory Poisoning · line 548 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- high Memory Poisoning · line 582 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00032 | $0.06963 |
| Opus 5.5 | $0.00013 | $0.02785 |
| Sonnet 5.5 | $0.00006 | $0.01393 |
| Haiku 4.5 | $0.00003 | $0.00696 |
Grade A, and why
context-engineering-advisor 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 1mo 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 — 764 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Guide product managers through diagnosing whether they're doing context stuffing (jamming volume without intent) or context engineering (shaping structure for attention). Use this to identify context boundaries, fix "Context Hoarding Disorder," and implement tactical practices like bounded domains, episodic retrieval, and the Research→Plan→Reset→Implement cycle.
Key Distinction: Context stuffing assumes volume = quality ("paste the entire PRD"). Context engineering treats AI attention as a scarce resource and allocates it deliberately.
This is not about prompt writing—it's about designing the information architecture that grounds AI in reality without overwhelming it with noise.
Key Concepts
The Paradigm Shift: Parametric → Contextual Intelligence
The Fundamental Problem:
- LLMs have parametric knowledge (encoded during training) = static, outdated, non-attributable
- When asked about proprietary data, real-time info, or user preferences → forced to hallucinate or admit ignorance
- Context engineering bridges the gap between static training and dynamic reality
PM's Role Shift: From feature builder → architect of informational ecosystems that ground AI in reality
Context Stuffing vs. Context Engineering
| Dimension | Context Stuffing | Context Engineering |
|---|---|---|
| Mindset | Volume = quality | Structure = quality |
| Approach | "Add everything just in case" | "What decision am I making?" |
| Persistence | Persist all context | Retrieve with intent |
| Agent Chains | Share everything between agents | Bounded context per agent |
| Failure Response | Retry until it works | Fix the structure |
| Economic Model | Context as storage | Context as attention (scarce resource) |
Critical Metaphor: Context stuffing is like bringing your entire file cabinet to a meeting. Context engineering is bringing only the 3 documents relevant to today's decision.
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.
- 1mo ago First seen · 764 lines · 32 tokens per session scan A b7839a64fa25
context-engineering-advisor is a skill published in the GitHub repository getcrew44/crew44 (356 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 6,963 once invoked, about $0.0001 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.
Other skills, from other repositories
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
ai-evaluation-engineering
An AI evaluation engineering specialist for testing models and prompts. The description does not provide enough detail to state which concrete operations it performs.
prompt-polisher
Use when the user explicitly wants rough notes, voice transcription, or stream-of-consciousness instructions rewritten into a clean reusable prompt for another model or for later execution. Do not use this just because the input is messy; use input-triage when the job is to separate goals, claims, and options.
pi-prompting
Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks.