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 instructions/halilc4/tabby-mcp/claude-mdgit clone --depth 1 https://github.com/halilc4/tabby-mcpWrote 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/instructions/halilc4/tabby-mcp/claude-md)<a href="https://agentmods.dev/instructions/halilc4/tabby-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/halilc4/tabby-mcp/claude-md.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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
tabby-mcp CLAUDE.md 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 5d 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.
tabby-mcp
MCP server for controlling Tabby terminal via Chrome DevTools Protocol (CDP).
Architecture
server.py -> tools.py -> cdp.py -> Tabby (CDP port 9222)
server.py- MCP server entry point, stdio transporttools.py- MCP tool definitions (execute_js, query, screenshot)cdp.py- TabbyConnection class, CDP communication
Development
# Install dependencies
uv sync
# Run server
uv run tabby-mcp
# Tabby must be started with CDP debugging:
# tabby.exe --remote-debugging-port=9222
MCP Tools
| Tool | Description |
|---|---|
list_targets |
List CDP targets (tabs) with index, title, url, ws_url |
execute_js |
Execute JS in Tabby context (async IIFE wrap by default) |
query |
Query DOM elements (auto-waits for Angular) |
screenshot |
Capture screenshot of Tabby window or element |
execute_js parameters
target- Tab index (0=first, -1=last) or ws_urlcode- JavaScript code. Usereturnto return valueswrap- Wrap in async IIFE (default: true). Fresh scope + await support. Set to false for raw execution (global functions, etc.)
query parameters
selector- CSS selectorinclude_children- Include children preview (default: false)include_text- Include textContent (default: true)skip_wait- Skip Angular/element wait (default: false)
Query automatically waits for Angular Zone.js stable and element existence.
Use skip_wait=true only when you know the element already exists.
screenshot parameters
target- Tab index (0=first, -1=last) or ws_urlselector- CSS selector for element screenshot (optional, full window if omitted)format- Image format: "png" or "jpeg" (default: "jpeg")quality- JPEG quality 0-100 (default: 80, ignored for PNG)save_path- File path to save screenshot (optional, returns base64 if omitted)
CDP Helper methods (cdp.py)
execute_js(expression, target, wrap=True)- Execute JS, return result. wrap=True for IIFE+asynclist_targets()- List tabs with index, title, url, ws_urlquery(selector)- Query elements, return info (tagName, id, className, text)query_with_retry(selector, max_retries, delay)- Query with retry for dynamic elementsclick(selector, index)- Click elementget_text(selector)- Return textContentwait_for(selector, timeout, visible)- Wait for element to exist (internal)wait_for_angular(timeout)- Wait for Angular Zone.js stable (internal)screenshot(format, quality, selector)- Capture screenshot, return base64. selector=None for full window
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.
- 5d ago First seen · 79 lines · 727 tokens per session scan A d2dbe4a5fb66
tabby-mcp CLAUDE.md is an instructions file published in the GitHub repository halilc4/tabby-mcp (7 stars, last pushed 6mo ago), licensed MIT. It adds 727 tokens to every session, about $0.0036 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 instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).