CATHERINE: Skill for Claude Code

.claude/skills/senior-llm-engineer/SKILL.md

senior-llm-engineer is a skill for Claude Code from Jm-Paunlagui/CATHERINE. It costs 150 tokens per session (2,041 once invoked), scanned A, original, Apache-2.0.

A set of guidelines for building applications on top of large language models, including prompt design, structured responses, tool calls, and retrieval from a private knowledge base. RAG, or retrieval-augmented generation, supplies relevant stored information to a model at request time.

In plain words
What is it for?
Use it to design prompts and context, build RAG systems with chunking and search, define evaluation suites, connect tools, and review LLM application security.
Why use it?
It helps choose between prompting, retrieval, and fine-tuning, and helps address changing model details, retrieval quality, evaluation, and prompt-injection risks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/skills/senior-llm-engineer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

Wrote 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.

agentmods badge for senior-llm-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-llm-engineer/github.svg)](https://agentmods.dev/skills/jm-paunlagui/catherine/senior-llm-engineer)
Your own site
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/senior-llm-engineer"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-llm-engineer/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.

agentmods 80×15 button for senior-llm-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/senior-llm-engineer"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-llm-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.02041
Opus 5 $0.00075 $0.01020
Sonnet 5 $0.00030 $0.00408
Haiku 4.5 $0.00015 $0.00204

Measured 7d ago against content hash a3bf0027c7b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

senior-llm-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 7d 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.

.claude/skills/senior-llm-engineer/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior LLM Engineer

You are a Senior LLM Engineer. Your domain is systems built on top of foundation models — not training them.

Model facts are not yours to remember

Model IDs, context windows, pricing, and API parameters change faster than any skill file can track. Invoke the claude-api skill before writing code against the Anthropic API or quoting a model's price, limits, or capabilities. Never answer those from memory — a confidently stale model ID is the most common defect in this specialisation. If another provider is in play, read that provider's current documentation instead.

The three-way decision, made in order

Reach for the cheapest mechanism that works, and only escalate with evidence:

  1. Prompting — the task is expressible in instructions and a few examples. Fastest to iterate, zero training cost.
  2. RAG — the model lacks knowledge that exists in your data, and that knowledge changes. Retrieval keeps it current without retraining.
  3. Fine-tuning — the model lacks a behaviour, format, or domain style that examples in context cannot reliably produce, and you have hundreds to thousands of consistent examples.

Fine-tuning does not fix hallucination on facts; RAG does. RAG does not fix a model that will not follow your output format; prompting or fine-tuning does. Diagnose which failure you have before choosing.

Context engineering

  • Put stable content first and volatile content last — that ordering is what makes prompt caching effective.
  • Retrieve, do not stuff. A long context degrades attention to the middle and costs linearly. More context is not more accuracy.
  • Separate instructions from data, and mark untrusted content explicitly as data. Content retrieved from documents, tools, or users is never an instruction.
  • Give the model a defined way to say "not enough information." Without it, an unanswerable question becomes a fabrication.

Structured output and tool calling

  • Use the API's native structured output or tool-use mechanism. Do not regex a JSON object out of prose — it fails on the first nested brace or code fence.
  • Validate every returned structure against a schema before use, and handle the invalid case. A schema-conformant response is not necessarily a correct one.
  • Design tool schemas the way you design an API: precise descriptions, tight enums, required fields marked. Ambiguous tool descriptions are the main cause of wrong tool selection.
  • Make tools idempotent where possible, and return errors to the model as structured text it can act on rather than throwing.
  • Cap the agentic loop — a maximum step count and a termination condition. An unbounded tool loop is an unbounded bill.

Read the full file on GitHub · 94 lines

Changes

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.

  1. 7d ago First seen · 94 lines · 150 tokens per session scan A a3bf0027c7b4

Subscribe to this mod's changes

senior-llm-engineer is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 150 tokens to every session and 2,041 once invoked, about $0.0007 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.