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-mattermostWrote 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-mattermost)<a href="https://agentmods.dev/skills/nanocoai/nanoclaw/add-mattermost"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-mattermost/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-mattermost"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/add-mattermost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Privilege Escalation · line 114 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 227 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 233 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 240 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 336 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.04417 |
| Opus 5 | $0.00019 | $0.02209 |
| Sonnet 5 | $0.00008 | $0.00883 |
| Haiku 4.5 | $0.00004 | $0.00442 |
Grade B, and why
add-mattermost 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 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.
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 -sf -X POST "{{base_url}}/api/v4/channels/direct" -H "Authorization: Bearer {{bot_token}}" -H "Content-Type: application/json" -d '["{{owner_user_id}}","{{bot_user_id}}"]' | jq -er '"mattermost:" + .id' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for attempt in $(seq 1 30); do curl -fsS --connect-timeout 1 --max-time 1 http://localhost:8065/api/v4/system/ping >/dev/null && exit 0; sleep 1; done; docker compose -f .nanoclaw/mattermost/compose.yml logs --tail 100 m How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Mattermost Channel
Adds Mattermost DMs, channels, threads, files, reactions, and interactive approval cards. Messages arrive over Mattermost's WebSocket; card clicks return to NanoClaw over an authenticated HTTP callback. Every step is safe to re-run.
Discover the server first
Do this before installing the adapter or asking for a URL. The goal is to reuse a healthy Mattermost the user already has and establish one canonical base URL.
- Check an existing
MATTERMOST_BASE_URLin the current environment and NanoClaw env/config files. Do not print tokens or dump whole env files. - Probe likely local URLs, at least
http://localhost:8065andhttp://127.0.0.1:8065, usingGET /api/v4/system/ping. A listening port alone is not evidence that the service is Mattermost. - Inspect Docker/Compose for Mattermost containers. If a matching container exists but is stopped, offer to start it; do not start or recreate it without the user's approval.
- If you find a healthy server, show its URL. Ask the user to use this server, enter a different URL, or create the local evaluation server. Do not select a server automatically. Treat the localhost and 127.0.0.1 endpoints for the same container as one server.
- If nothing local is found, ask whether the user has a remote Mattermost. If not, offer the local evaluation installation in LOCAL_SERVER.md. Read that file only for local server discovery, repair, or installation.
Set MATTERMOST_BASE_URL to the chosen canonical URL (scheme included, no
trailing slash), then use that exact hostname in browser/Desktop setup. Do not
silently install Mattermost: it runs containers, binds a port, and persists
data, so show what will be created and get approval first.
Apply
1. Detect the server
Test the configured URL and the standard local URLs. A detected server is only a suggestion. The user must select the server.
node .claude/skills/add-mattermost/scripts/discover-server.mjs
What ships with it
7 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 · 383 lines · 38 tokens per session scan B 53a842a99d65
add-mattermost is a skill published in the GitHub repository nanocoai/nanoclaw (30,736 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 4,417 once invoked, about $0.0002 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 2026-08-30.
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.
slack-token-extractor
Refresh expired Slack browser tokens (xoxc/xoxd) using persistent browser sessions. Use when Slack MCP tools fail with authentication errors.
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.
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.