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 CarbeneAI/Forge --skill ollamaresearchergit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/ollamaresearcher)<a href="https://agentmods.dev/skills/carbeneai/forge/ollamaresearcher"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/ollamaresearcher/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/carbeneai/forge/ollamaresearcher"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/ollamaresearcher.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 | $0.00067 | $0.01131 |
| Opus 5 | $0.00034 | $0.00566 |
| Sonnet 5 | $0.00013 | $0.00226 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade B, and why
OllamaResearcher scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl http://localhost:11434/api/show -d '{"name":"dolphin3:8b-llama3.1-fp16"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:11434/api/tags How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OllamaResearcher - Private Local AI Research
Local, private AI research using your self-hosted Ollama server for sensitive information and offline tasks.
Why Use Ollama?
Use Ollama for:
- Sensitive Information: Financial records, medical data, personal information
- Offline Work: No internet required, works on local network
- Privacy: Data never leaves your local network
- No API Costs: Free to use, no quota limits
- Older Knowledge: Tasks that don't require up-to-date information
Don't use Ollama for:
- Current events or recent information (use Perplexity/Claude instead)
- Web research requiring internet access
- Tasks requiring latest model capabilities
Configuration
Ollama Server Details:
- URL: http://localhost:11434/ (your local machine)
- Model: gemma4:31b (default), dolphin3:8b-llama3.1-fp16 (fast)
- Location: localhost (your local machine running Ollama)
No API keys required - runs on your local network.
Workflow Routing
| Workflow | Trigger | Behavior |
|---|---|---|
| Ollama Query | "use ollama to...", "ollama research", "ask ollama", "private AI" | Use Ollama for question/research |
| Sensitive Data Analysis | Working with financial/medical data | Automatically suggest Ollama |
| Offline Work | When internet access limited | Fall back to Ollama |
Examples
Example 1: Financial Analysis
User: "Analyze my investment portfolio using ollama"
→ Routes to Ollama server (keeps financial data local)
→ Uses dolphin3:8b-llama3.1-fp16 model
→ Returns analysis without sending data to cloud
Example 2: Medical Information
User: "Help me understand my medical test results using local AI"
→ Automatically uses Ollama for privacy
→ Processes sensitive health data locally
→ Returns explanation without cloud services
Example 3: General Query with Privacy
User: "Use ollama to explain quantum computing"
→ Sends query to local Ollama server
→ Gets response from dolphin3 model
→ Works offline, no external API calls
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.
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.
- 7d ago First seen · 172 lines · 67 tokens per session scan B 37022b92e25c
OllamaResearcher is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,131 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-ethics-governance
../../../platform-ai/ai-ethics-governance/SKILL.md.
ai-red-teaming
../../../red-team/ai-red-teaming/SKILL.md.
update-llm-models
Autonomously research and update the default lightweight LLM models in src/core/llm.ts using web search to ensure the most current versions are used.
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
aatmf-t06-training-poisoning
AATMF T6 — Training & Feedback Poisoning. Data poisoning, RLHF reward hacks, fine-tune-time exfil, embedding poisoning.