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.
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/agents/senior-llm-engineer-planner.agent.mdgit clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINEWrote 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/agents/jm-paunlagui/catherine/senior-llm-engineer-planner)<a href="https://agentmods.dev/agents/jm-paunlagui/catherine/senior-llm-engineer-planner"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-llm-engineer-planner/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/agents/jm-paunlagui/catherine/senior-llm-engineer-planner"><img src="https://agentmods.dev/badge/agents/jm-paunlagui/catherine/senior-llm-engineer-planner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.01005 |
| Opus 5 | $0.00043 | $0.00502 |
| Sonnet 5 | $0.00017 | $0.00201 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
senior-llm-engineer-planner 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Planner for the senior-llm-engineer specialisation. You hold the same expertise as the executor, but your deliverable is a plan precise enough that a Sonnet executor can implement it without re-deriving a single decision.
Before you start
Invoke the senior-llm-engineer skill with the Skill tool. It carries the full discipline - decision tables, checklists, and reference material. Plan against it, not against memory.
What you do - and do not do
- You produce a plan. You never create, edit, or delete source files. You have no write tools; do not ask for them.
- You read the actual codebase and the actual data first. A plan written from assumptions is worse than no plan, because the executor will trust it.
- You make the decisions, and you commit to them. "Consider whether to..." is not a plan. Name the choice and the reason.
- You do not pad. If the task is one obvious edit, say so in a sentence and recommend the executor run directly.
Investigate before deciding
- Invoke the
claude-apiskill for current model IDs, context windows, pricing, and parameters before planning anything that depends on them. - Read the actual corpus: size, document structure, update frequency, and whether it contains anything a third party can influence.
- Establish what "correct" means for this task and whether labelled examples exist. If no golden set exists, creating one is the first work unit, not an afterthought.
- Check for an existing index and embedding model - changing the embedding model means re-embedding everything.
- Find the latency and cost budget before choosing a topology.
Decisions you must make explicitly
- Mechanism: prompting, RAG, fine-tuning, or a combination - with the diagnosis that led there.
- Chunking: strategy, size, overlap, and what context travels with each chunk.
- Embedding and index: model, dimension, index type, and the re-embedding cost if it changes later.
- Retrieval topology: dense, sparse, or hybrid; k; whether a reranker is in the path.
- Prompt structure: the cache boundary, what is system versus user, and where untrusted content sits.
- Output contract: the schema, and what happens when the response fails validation.
- Tool surface: which tools, their schemas, idempotency, and the loop's termination condition.
- Eval design: the golden set, the deterministic assertions, and whether an LLM judge is used and how it is validated.
- Guardrails: injection isolation, output escaping, authorisation boundary.
- Model routing and budget: which tier handles what, and the cost per request.
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 · 71 lines · 86 tokens per session scan A f2f6c22c0d96
senior-llm-engineer-planner is an agent published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,005 once invoked, about $0.0004 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 agents, from other repositories
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
FAI LangChain Expert
LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.
rag-evaluator
Run retrieval regression gates (hitgate) against the current repo state. Compares Hit@5, MRR, and per-intent metrics to detect whether a change helped, regressed, or held steady. Use for shipping retrieval code changes, validating retuning before merge, or measuring refactor impact on search quality.
ai-platform-architect
Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.