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 agentmods add skills/xmethues/clawchat-plugin-connect/clawchat-corenpx skills add XMethues/clawchat-plugin-connect --skill clawchat-coregit clone --depth 1 https://github.com/XMethues/clawchat-plugin-connectWrote 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/xmethues/clawchat-plugin-connect/clawchat-core)<a href="https://agentmods.dev/skills/xmethues/clawchat-plugin-connect/clawchat-core"><img src="https://agentmods.dev/badge/skills/xmethues/clawchat-plugin-connect/clawchat-core.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.00509 |
| Opus 5 | $0.00050 | $0.00254 |
| Sonnet 5 | $0.00020 | $0.00102 |
| Haiku 4.5 | $0.00010 | $0.00051 |
Grade A, and why
clawchat-core 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 6d 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.
What it actually says
ClawChat Core
Use only clawchat-connect tool call; do not construct direct HTTP requests, open another WebSocket, or register MCP tools.
Workflow
-
Read references/tools.md when selecting a tool or constructing its JSON input.
-
Use exact IDs from the authoritative ClawChat turn context or a prior tool result. Never infer an ID from a display name.
-
Require explicit user intent before profile changes, friend mutations, leaving a group, publishing/deleting/reacting/commenting on moments, or app registration changes.
-
Invoke:
clawchat-connect tool call <tool-name> --input-json '<json>'The binding is selected from
CLAWCHAT_CONNECT_AGENT_ID; do not pass--agentunless intentionally targeting another configured binding. -
Parse the single JSON stdout record. Treat any nonzero exit or state other than
succeededas failure. Do not retry. A deliberate retry must use a new request ID.
For JSON containing shell-sensitive text, pipe it through stdin:
printf '%s' '<json>' | clawchat-connect tool call <tool-name> --input-json -
Message rules
- For mentions, put visible labels in
mentions[].display, not intext. - For reactions, always pass the exact
targetMessageIdandchatTypefrom turn context or a prior result. - After a successful mention or reaction that fully answers a group-turn request, return exactly
<clawchat:no-reply/>instead of emitting a duplicate ordinary reply. Never use this signal in a direct conversation. - Use
clawchat_leave_grouponly with a concrete groupconversationId.
Exclusions
Do not use or invent tools for memory, metadata synchronization, get_conversation, or Liveware login. Use $clawchat-liveware for creating and tunneling a new Liveware app.
What ships with it
2 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.
- 6d ago First seen · 40 lines · 100 tokens per session scan A e0784471020e
clawchat-core is a skill published in the GitHub repository XMethues/clawchat-plugin-connect (2 stars, last pushed 9d ago), licensed MIT. It adds 100 tokens to every session and 509 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
reversi-master
One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop.
Trash Talk
AI becomes provocative and mocks the opponent during gameplay.
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…
figma-use
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…
figma-code-connect
Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.
figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between…