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 crypdick/pynchy --skill slack-token-extractorgit clone --depth 1 https://github.com/crypdick/pynchyWrote 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/crypdick/pynchy/slack-token-extractor)<a href="https://agentmods.dev/skills/crypdick/pynchy/slack-token-extractor"><img src="https://agentmods.dev/badge/skills/crypdick/pynchy/slack-token-extractor/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/crypdick/pynchy/slack-token-extractor"><img src="https://agentmods.dev/badge/skills/crypdick/pynchy/slack-token-extractor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.00616 |
| Opus 5.5 | $0.00014 | $0.00246 |
| Sonnet 5.5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
slack-token-extractor 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Token Extractor
Refresh expired Slack browser session tokens (xoxc/xoxd) used by Slack MCP server.
System requirements
Need system Chrome/Chromium binary — CHROME_PATH must set in .env (e.g. CHROME_PATH=/usr/bin/google-chrome-stable). Playwright bundled Chromium never used — services fingerprint as bot traffic.
On headless servers, setup_slack_session also need VNC stack for interactive login:
apt install xvfb x11vnc novnc
Plugin check missing deps at startup, log warnings.
How it works
Use Playwright persistent browser contexts — after one manual login (human handle CAPTCHA/magic-link), later token extractions run headless using saved session.
First-time setup (requires human)
Before tokens auto-refresh, human must log in once:
setup_slack_session(workspace_name="acme")
Open visible Chromium window. Human complete Slack login flow (CAPTCHA, magic link, SSO — whatever Slack require). Session saved for future headless use.
On headless server (no X display), tool auto-start virtual display with noVNC web access on port 6080. Before calling setup_slack_session, tell human open http://<server>:6080/vnc.html?autoconnect=true in browser so can interact with login page.
Hardware security keys (YubiKey, FIDO2): noVNC cannot forward WebAuthn challenges — key must physically connect to machine running browser. If Slack login need hardware key, run setup_slack_session on local machine with key attached, then rsync profile to server:
rsync -az data/playwright-profiles/acme/ server:/path/to/pynchy/data/playwright-profiles/acme/
Refreshing tokens
Once session set up, tokens refresh headless:
refresh_slack_tokens(
workspace_name="acme",
xoxc_var="SLACK_XOXC_ACME",
xoxd_var="SLACK_XOXD_ACME",
)
Tool navigate to Slack using saved session, extract fresh tokens, write to .env. pynchy service auto-restart on .env changes.
Error handling
- "Not logged in — persistent session expired" — Saved browser session expired. Human need run
setup_slack_sessionagain. - "Failed to extract xoxc/xoxd" — Browser reached Slack client but tokens not found. Slack may have changed storage format.
- "Login not completed within Xs" — Human not finish manual login in time. Try again with longer
timeout_seconds.
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.
- 1mo ago First seen · 64 lines · 34 tokens per session scan A c206715f81d7
slack-token-extractor is a skill published in the GitHub repository crypdick/pynchy (10 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 616 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
add-opencode
Use OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the Anthropic Agent SDK. Per group via ncl groups config update --provider opencode; host passes OPENCODE and XDG mount when spawning containers.
migrate-from-openclaw
Migrate from OpenClaw to NanoClaw v2. Detects an existing OpenClaw installation, extracts identity, channel credentials, scheduled tasks, and other config, then guides interactive migration. Triggers on "migrate from openclaw", "openclaw migration", "import from openclaw".
add-iron-proxy
Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.