NanoClaw is an AI assistant that runs agents inside separate Linux containers, isolating their files and execution environments. People use it to connect agents to messaging services and run assistants with memory and scheduled jobs. The catalogue contains skills and instructions for extending or operating NanoClaw.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nanocoai/nanoclawnpx agentmods add skills/nanocoai/nanoclaw/add-ollama-toolWrote 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/nanocoai/nanoclaw/add-ollama-tool)<a href="https://agentmods.dev/skills/nanocoai/nanoclaw/add-ollama-tool"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-ollama-tool/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/nanocoai/nanoclaw/add-ollama-tool"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-ollama-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 16 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 40 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 279 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 279 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00028 | $0.03067 |
| Opus 5 | $0.00014 | $0.01533 |
| Sonnet 5 | $0.00006 | $0.00613 |
| Haiku 4.5 | $0.00003 | $0.00307 |
Grade A, and why
add-ollama-tool 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:11434/api/tags | head How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Ollama Integration
This skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models served by the Ollama daemon on the host, and can optionally manage the model library directly. Ollama runs locally and is keyless — there are no credentials to thread; the only configuration is the daemon's base URL.
Core tools (always available):
ollama_list_models— list installed models with name, size, and family (GET /api/tags)ollama_generate— send a prompt to a specified model and return the response (POST /api/generate)
Management tools (opt-in via OLLAMA_ADMIN_TOOLS=true):
ollama_pull_model— pull (download) a model from the Ollama registry (POST /api/pull)ollama_delete_model— delete a locally installed model to free disk space (DELETE /api/delete)ollama_show_model— show model details: modelfile, parameters, and architecture info (POST /api/show)ollama_list_running— list models currently loaded in memory with memory usage and processor type (GET /api/ps)
The skill ships the MCP server source (and its tests) in this folder and copies them into the agent-runner tree at install time, then registers the server in index.ts and forwards host env vars in container-runner.ts. Registering the server is enough to expose its tools — the agent's allow-pattern (mcp__ollama__*) is derived from the registered server name.
Phase 1: Pre-flight
Check if already applied
Check if container/agent-runner/src/ollama-mcp-stdio.ts exists. If it does, skip to Phase 3 (Configure).
Check prerequisites
Verify Ollama is installed and its daemon is reachable. On the host:
curl -s http://127.0.0.1:11434/api/tags | head
If the request fails:
- Install Ollama from https://ollama.com/download.
- Start it (the desktop app runs the daemon, or run
ollama serve). - Confirm the daemon answers:
curl -s http://127.0.0.1:11434/api/tags.
What ships with it
5 files 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.
- 11d ago First seen · 301 lines · 28 tokens per session scan A a793808ec2a3
add-ollama-tool is a skill published in the GitHub repository nanocoai/nanoclaw (30,736 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,067 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
Pynchy Development
Use when running pynchy locally — running the app, tests, linting, formatting, prek hooks, or rebuilding the agent container. Also use when determining whether you're on the live Pynchy host or a local machine, and for debugging agent behavior-- session transcript branching, inspecting message history and agent traces…
Pynchy Plugin Authoring
Use when creating, scaffolding, or updating a pynchy plugin, including channels, MCP servers, skills, agent cores, workspace specs, and container runtime plugins. Also use when users ask how to register plugins via config.toml, add entry points, or validate plugin hook wiring.
x-integration
Post tweets, like, reply, retweet, and quote on X (Twitter) using browser automation. Use when the user asks you to interact with X/Twitter.
slack-token-extractor
Refresh expired Slack browser tokens (xoxc/xoxd) using persistent browser sessions. Use when Slack MCP tools fail with authentication errors.
Documentation Manager
Use when writing or reviewing pynchy documentation, deciding where to document things, updating the docs, checking doc consistency, or fixing broken links. Covers information architecture, writing philosophy, tree-shaped navigation, doc-code coupling, no hard-coded usernames, extensibility framing for pluggable…
python-heredoc
When running multi-line Python code or code with quotes, apostrophes, or f-strings via Bash, always use heredoc syntax instead of python -c to avoid shell quoting issues.