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
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 nanocoai/nanoclaw --skill add-onecligit clone --depth 1 https://github.com/nanocoai/nanoclawWrote 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-onecli)<a href="https://agentmods.dev/skills/nanocoai/nanoclaw/add-onecli"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-onecli/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-onecli"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-onecli.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 | $0.00058 | $0.00990 |
| Opus 5.5 | $0.00023 | $0.00396 |
| Sonnet 5.5 | $0.00012 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
add-onecli 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 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add OneCLI gateway
This skill owns the full OneCLI integration. NanoClaw core supplies the generic gateway seam and existing skill engine.
Install the provider payload
Copy the package's native adapter, tests, and agent guidance into their normal NanoClaw paths. NanoClaw core owns the approval workflow.
payload/src/gateway-providers/onecli-files.ts -> src/gateway-providers/onecli-files.ts
payload/src/gateway-providers/onecli-files.test.ts -> src/gateway-providers/onecli-files.test.ts
payload/src/gateway-providers/onecli.ts -> src/gateway-providers/onecli.ts
payload/src/gateway-providers/onecli.test.ts -> src/gateway-providers/onecli.test.ts
payload/src/gateway-providers/onecli-install.test.ts -> src/gateway-providers/onecli-install.test.ts
payload/container/skills/onecli-gateway/SKILL.md -> container/skills/onecli-gateway/SKILL.md
payload/container/skills/onecli-gateway/instructions.md -> container/skills/onecli-gateway/instructions.md
payload/docs/onecli-upgrades.md -> docs/onecli-upgrades.md
Register once
The provider file makes the only product registration call. It translates OneCLI sessions and native approval events into the generic contract.
import './onecli.js';
Install the pinned SDK
@onecli-sh/[email protected]
Configure the gateway
The setup script safely reuses a healthy existing installation, installs the pinned local gateway when absent, or uses NANOCLAW_ONECLI_API_HOST and NANOCLAW_ONECLI_API_TOKEN for a remote gateway.
This integration supports exactly the gateway version pinned in .claude/skills/add-onecli/versions.json (onecli-gateway, today 1.42.0; not the versions.json at the project root). OneCLI 1.43 and later remove the agent secret-assignment API used below, so 1.43+ is not supported for now. Setup reuses an existing gateway without checking its version: follow Upgrading the OneCLI gateway to check it and to move it to the pin. The CLI (onecli-cli) and SDK (onecli-sdk) have their own pins.
What ships with it
23 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.
- gateway.json 123 B
- payload/container/skills/onecli-gateway/instructions.md 760 B
- payload/container/skills/onecli-gateway/SKILL.md 3.3 KB
- payload/docs/onecli-upgrades.md 13 KB
- payload/src/gateway-providers/onecli-files.test.ts 4.4 KB runs code
- payload/src/gateway-providers/onecli-files.ts 4.2 KB runs code
- payload/src/gateway-providers/onecli-install.test.ts 1.1 KB runs code
- payload/src/gateway-providers/onecli.test.ts 13 KB runs code
- payload/src/gateway-providers/onecli.ts 9.6 KB runs code
- references/chatgpt-oauth-refresh.md 1.1 KB
- REMOVE.md 576 B
- scripts/auth.ts 5.6 KB runs code
- scripts/credential-store.test.ts 1.7 KB runs code
- scripts/credential-store.ts 2.5 KB runs code
- scripts/detect.ts 764 B runs code
- scripts/install-claude.sh 1.6 KB runs code
- scripts/no-proxy.test.ts 1.6 KB runs code
- scripts/provider-credentials.test.ts 19 KB runs code
- scripts/provider-credentials.ts 12 KB runs code
- scripts/readiness.test.ts 1.1 KB runs code
- scripts/register-claude-token.sh 4.5 KB runs code
- scripts/setup.ts 21 KB runs code
- versions.json 83 B
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 Changed · +2 lines 073eb699eedd
- 12d ago Changed e6ad44652f19
- 17d ago Changed · +17 lines 451c11a25fe1
- 23d ago First seen · 60 lines · 58 tokens per session scan A 9a051c4a1ebd
add-onecli is a skill published in the GitHub repository nanocoai/nanoclaw (30,960 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 990 once invoked, about $0.0002 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 2026-09-24.
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.