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 personamanagmentlayer/pcl --skill llm-engineering-expertgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/personamanagmentlayer/pcl/llm-engineering-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/llm-engineering-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/llm-engineering-expert/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/personamanagmentlayer/pcl/llm-engineering-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/llm-engineering-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Anti-Refusal · line 182 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00092 | $0.02377 |
| Opus 5 | $0.00046 | $0.01189 |
| Sonnet 5 | $0.00018 | $0.00475 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
llm-engineering-expert 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 4d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Engineering Expert
Building on a language model is engineering against a component that is non-deterministic, occasionally confident and wrong, and priced per token. The discipline is in the surrounding structure, not in the wording of prompts.
Core Concepts
The Model Is a Component, Not the System
A production LLM feature is a pipeline: input validation, context assembly, the model call, output parsing and validation, then a decision about what to do when any of that fails. Treating the model call as the whole feature is the root of most reliability problems.
Determinism Is Not Available
Even at temperature zero, output can vary across model versions, infrastructure and batching. Design for a distribution of outputs, not a fixed one: validate what comes back, and make the failure path as considered as the success path.
Context Is a Budget
Everything competes for the same window: system instructions, examples, retrieved documents, conversation history, the user's input, and room for the answer. Attention is not uniform across a long context — material at the beginning and end is used more reliably than material buried in the middle. Spend the budget deliberately.
Evaluation Precedes Iteration
Without a scored test set, prompt changes are superstition. Ten to fifty representative cases with expected properties are enough to start and will catch most regressions.
Prompt Design
Structure that holds up
Order matters: instructions first, reference material next, the specific request last. Ending with the request keeps it close to generation.
SYSTEM = """You extract structured invoice data.
Rules:
- Return only fields present in the document. Never infer a missing value.
- Amounts are decimal strings with two places, e.g. "1234.50".
- If the document is not an invoice, set "is_invoice" to false and stop.
- Dates are ISO 8601 (YYYY-MM-DD).
"""
USER = """<document>
{document_text}
</document>
Extract the invoice fields defined by the schema."""
What ships with it
2 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.
- 4d ago First seen · 278 lines · 92 tokens per session scan A c51fc7191ee8
llm-engineering-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 2,377 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
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.
ai-engineering-toolkit
AI Engineering Toolkit workflow skill. Use this skill when the user needs 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 and the operator…
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.