ollama

ollama is a skill for Claude Code, Codex from ssube/conclave. It costs 58 tokens per session (1,287 once invoked), scanned A, original, MIT.

A local text and image-captioning tool built around Ollama, which runs language models on your own computer. It can create captions, prompts, enhanced text, and model descriptions without cloud API keys.

In plain words
What is it for?
Captioning single images or image folders for training datasets, creating prompts, improving existing prompts, and writing model cards, gallery descriptions, or social alt text.
Why use it?
It keeps supported generation work on local hardware and can produce faithful captions or richer descriptive text from images.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ssube/conclave/ollama
Any agent
npx skills add ssube/conclave --skill ollama
Clone the repo
git clone --depth 1 https://github.com/ssube/conclave

Made for: Claude Code, Codex.

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 ollama

README.md
[![agentmods](https://agentmods.dev/badge/skills/ssube/conclave/ollama.svg)](https://agentmods.dev/skills/ssube/conclave/ollama)
Your own site
<a href="https://agentmods.dev/skills/ssube/conclave/ollama"><img src="https://agentmods.dev/badge/skills/ssube/conclave/ollama.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00058 $0.01287
Opus 5 $0.00029 $0.00643
Sonnet 5 $0.00012 $0.00257
Haiku 4.5 $0.00006 $0.00129

Measured 4d ago against content hash e3e53cf4d80d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ollama scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (ollama_generate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Verify with `curl $OLLAMA_HOST/api/tags` that the vision model is pulled.
pi/skills/ollama/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ollama — Local LLM Generation

Generate text and caption images using a local Ollama instance. No cloud API keys required — everything runs on your own hardware.

Actions

caption — Caption images for training datasets

Uses a two-stage pipeline: a vision model sees the image, then a text model writes a polished caption in the requested style.

Single image:

python3 {baseDir}/ollama_generate.py caption /path/to/image.png [--style training|tags|detailed]

Batch directory (writes .txt files alongside each image):

python3 {baseDir}/ollama_generate.py caption /path/to/dataset/ [--style training] [--overwrite]

Creative mode — embellishes with atmosphere, mood, and descriptive richness:

python3 {baseDir}/ollama_generate.py caption /path/to/image.png --style detailed --creative

Without --creative: faithful, accurate captions — only what the vision model sees. With --creative: adds atmosphere, mood, and sensory detail. Use for model cards, gallery descriptions, social alt text — anywhere prose matters more than raw data.

Caption styles:

Style Format Use for
training Natural language paragraph (50-150 words) Flux/T5 LoRA training datasets
tags Booru-style comma-separated tags (20-40 tags) SDXL/Pony/Illustrious training
detailed Rich prose description (2-4 sentences) Model cards, galleries, catalogs

Options:

  • --creative / -c — Embellish with atmosphere and mood (default: accurate)
  • --trigger <word> — Include a trigger word in every caption (for LoRA training)
  • --prefix <text> — Prepend text to every caption
  • --overwrite — Overwrite existing .txt files (default: skip existing)

Batch output pattern:

dataset/
├── image_001.png
├── image_001.txt   ← generated caption
├── image_002.jpg
├── image_002.txt   ← generated caption
└── ...

prompt — Generate an image prompt from a concept

python3 {baseDir}/ollama_generate.py prompt "<concept>" [--encoder clip|t5]

Read the full file on GitHub · 153 lines

Files

What ships with it

1 file 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.

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. 4d ago First seen · 153 lines · 58 tokens per session scan A e3e53cf4d80d

Subscribe to this mod's changes

ollama is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 1,287 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

strategy

Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

EliasOulkadi/shokunin · 42 tokens

autoresearch

Self-improving optimization via Karpathy autoresearch pattern. Generates → evaluates → scores → mutates prompts/descriptions in a loop. Targets — tool-selection, system-prompt, skill, decision-parser. Use when "optimize tools", "autoresearch", "improve skill X", "self-improve prompts", "optimize tool descriptions".

fortunto2/rust-code · 73 tokens

prompt

Use ONLY when the user explicitly asks to improve a prompt aimed at an AI: "improve my prompt", "fix this prompt", "how should I ask for this", "make this prompt better". A prompt pasted to be answered or executed is a task, not a rewrite request: do that task instead. About prompts for an AI, not about optimizing…

mehrad-dm/mastermind · 76 tokens

prompt-architect

Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.

repowise-dev/claude-code-prompts · 31 tokens

sc:image-gen-prompting

Craft effective text-to-image prompts for AI generators (Higgsfield, Midjourney, DALL·E/GPT-Image, Stable Diffusion, Flux). Subject + style + composition + lighting structure, negative prompts, aspect ratios, model-specific tips, and Hebrew→English prompt translation. Activate for: generate image, AI art, product…

squadcodercom/squadcoder · 95 tokens

prompt-engineering-expert

Expert prompt engineering: prompt structure, few-shot, chain-of-thought, structured output, and iteration. Trigger keywords: prompt, prompt engineering, system prompt, few-shot, chain-of-thought, output format, JSON schema, structured output, instructions, role, examples, eval. Use for writing, debugging, or…

Miaoge-Ge/coding-agent-skills · 77 tokens