nanobot is a small, self-hosted personal AI agent framework written in Python, providing an agent runtime that can operate through a WebUI, terminal, or chat applications. Users use it to connect language models with tools, memory, MCP integrations, scheduled automation, and multi-agent workflows. The catalogue add-ons provide skills and instructions for working with nanobot.
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 HKUDS/nanobot --skill mygit clone --depth 1 https://github.com/HKUDS/nanobotWrote 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/hkuds/nanobot/my)<a href="https://agentmods.dev/skills/hkuds/nanobot/my"><img src="https://agentmods.dev/badge/skills/hkuds/nanobot/my.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00624 |
| Opus 5 | $0.00034 | $0.00312 |
| Sonnet 5 | $0.00014 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
my 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Awareness
How to use
- Identify the situation from the categories below
- Call the my tool with the appropriate action
- If set, warn the user before changing impactful settings such as the model or runtime limits
- For detailed examples, read references/examples.md
When to check
When to set
| Situation | Command |
|---|---|
| Check capacity for a large task | my(action="check", key="context_window_tokens") |
| Switch model or context capacity | my(action="set", key="model_preset", value="<preset-name>") |
| Long multi-step task | my(action="set", key="max_iterations", value=80) |
Tradeoff: Bias toward stability. Only set when defaults are genuinely insufficient.
Anti-patterns
Constraints
model_presetis saved for the current session; other modifications are in-memory only- Direct
modelandcontext_window_tokenswrites are rejected during active sessions because they would change the shared instance default. Use a configuredmodel_presetinstead. - Protected params have type/range validation:
max_iterations(1–100),context_window_tokens(4096–1M),model(non-empty str) - If
tools.my.allow_setis false, check only
Related tools
| Need | Use | Persists? |
|---|---|---|
| Per-session temp state | my(action="set", key="...", value=...) |
No |
| Long-term facts | Memory skill (MEMORY.md, USER.md) |
Yes |
| Permanent config change | Edit config file | Yes |
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.
- 8d ago First seen · 73 lines · 68 tokens per session scan A 9352352e37f8
my is a skill published in the GitHub repository HKUDS/nanobot (47,869 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 624 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
predictor-hand-skill
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking.
researcher-hand-skill
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats.
twitter-hand-skill
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking.
collector-hand-skill
Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis.
lead-hand-skill
Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation.