agentmods.dev

rag-vs-finetune-decision

rag-vs-finetune-decision is a skill for Claude Code from VandanaAjayDubey111/great-pm. It costs 109 tokens per session (4,222 once invoked), scanned A, original, MIT.

A decision guide for choosing between prompt changes, RAG, and fine-tuning for an AI system. RAG retrieves relevant outside information at answer time, while fine-tuning changes how a model behaves through additional training.

In plain words
What is it for?
Use it to decide how to address missing knowledge, missing behavior or format, cost, and response-time problems in an AI feature.
Why use it?
It helps avoid using fine-tuning when clearer instructions or retrieved information would solve the problem, while weighing cost, speed, and maintenance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the great-pm plugin — 114 skills, 34 commands, 48 agents, 5 hooks shipped together

not rated 3repo 1mo ago A scan 109 tokens original MIT

Good fit Use it to decide how to address missing knowledge, missing behavior or format, cost, and response-time problems in an AI feature.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision
View source ↗ VandanaAjayDubey111/great-pm
Install

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.

Any agent
npx skills add VandanaAjayDubey111/great-pm --skill rag-vs-finetune-decision
Clone the repo
git clone --depth 1 https://github.com/VandanaAjayDubey111/great-pm

Made for: Claude Code.

Or install great-pm, the plugin that ships this one along with the rest of its 114 skills, 34 commands, 48 agents, 5 hooks.

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 rag-vs-finetune-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision/github.svg)](https://agentmods.dev/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision)
Your own site
<a href="https://agentmods.dev/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision/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 rag-vs-finetune-decision

Your own site · 80×15
<a href="https://agentmods.dev/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision"><img src="https://agentmods.dev/badge/skills/vandanaajaydubey111/great-pm/rag-vs-finetune-decision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,222 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 $0.00109 $0.04222
Opus 5.5 $0.00044 $0.01689
Sonnet 5.5 $0.00022 $0.00844
Haiku 4.5 $0.00011 $0.00422

Measured 1mo ago against content hash 9d844d7b7fd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rag-vs-finetune-decision 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.

plugins/great-pm/skills/rag-vs-finetune-decision/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex host binding

  • Treat references to Claude slash workflows as the equivalently named Codex skill.
  • Before delegating to any specialist, read the great-pm-runtime skill and the selected packaged role file.
  • Treat "invoke", "assign", "delegate", "spawn", and source Agent-tool instructions as a required Codex spawn_agent call with that role and a bounded assignment.
  • For the spawn tool's task_name or agent_name identifier, replace canonical role-name hyphens with underscores (query-refiner-pm → query_refiner_pm). Keep canonical names unchanged in prompts, filenames, verdict logs, and user-facing output; this is an internal identifier mapping, not a role rename.
  • Store every returned agent identifier. Never call a wait tool until a spawn has returned an identifier, and wait only on identifiers returned by successful spawns.
  • If spawn_agent is unavailable or a spawn fails, report BLOCKED; do not impersonate the specialist or wait on an empty agent set.
  • Resolve bundled paths from the installed GreatPM plugin root.
  • Ignore Claude-only model aliases, colors, turn limits, and tool allowlists.
  • Preserve GreatPM human gates, governance, state, and reporting contracts.

RAG vs Fine-tune Decision — the model-capability ladder

When an AI feature isn't good enough, teams reach for the most expensive, least reversible fix — fine-tuning — far too early. The discipline this skill enforces: climb the capability ladder prompt → RAG → fine-tune only as far as the problem actually requires. Roughly 99% of products never need fine-tuning. The decision is not "which is most powerful" — it is where the missing capability actually lives, and the cheapest rung that closes that specific gap.

The diagnosing question for every gap: does the model lack instructions, knowledge, or behavior?

  • Missing instructions (it can do it, but you asked badly) → prompt engineering.
  • Missing knowledge (it doesn't know your facts, or they go stale) → RAG.
  • Missing behavior / format at scale, or a latency/cost problem from huge repeated prompts → fine-tuning (only after prompt + RAG fail).

Read the full file on GitHub · 284 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. 1mo ago First seen · 284 lines · 109 tokens per session scan A 9d844d7b7fd5

Subscribe to this mod's changes

rag-vs-finetune-decision is a skill published in the GitHub repository VandanaAjayDubey111/great-pm (3 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 4,222 once invoked, about $0.0004 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 2026-09-21.

Data and AILLMMulti-AgentPlanningPromptingRAG and vectorsagenticai-agentsclaude-code-plugin
Related

Other skills, from other repositories

oracle

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

simota/agent-skills · 45 tokens

dspy

DSPy: declarative LM programs, auto-optimize prompts, RAG.

StarryCod/cogitum · 19 tokens

dspy

DSPy: declarative LM programs, auto-optimize prompts, RAG.

NousResearch/hermes-agent · 19 tokens

ai-engineering-toolkit

Overview of six 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.

sickn33/agentic-awesome-skills · 47 tokens

llm-ops

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

davila7/claude-code-templates · 44 tokens

awesome-chatgpt

Search this repository's awesome-ChatGPT-repositories list for open-source ChatGPT and LLM projects such as RAG frameworks, agents, chatbots, CLIs, prompts, and browser extensions. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, or AI development; not for editing or adding list…

taishi-i/awesome-ChatGPT-repositories · 79 tokens