deepseekCLI CLAUDE.md

Repository instructions describing a completed Chrome browser bridge for deepseekCLI, including its extension, native connection, and browser-control design.

In plain words
What is it for?
Understanding how the Chrome extension, native host, browser bridge, and runtime backend selection fit together when maintaining or extending the project.
Why use it?
They preserve the project’s current state, important decisions, and test results so later work can continue without repeating the investigation.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cynchro/deepseekcli/claude-md
Clone the repo
git clone --depth 1 https://github.com/cynchro/deepseekCLI
Per session 1,728 This file is loaded in full into every session.
When invoked 1,728 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01728 $0.01728
Opus 5 $0.00864 $0.00864
Sonnet 5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured 2d ago against content hash bf426f0d207d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepseekCLI 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 2d 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.

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estado de sesión: extensión de Chrome como backend real del navegador

Tarea actual

El usuario preguntó si el proyecto tenía Playwright/Chrome, y la conversación derivó en: probar el auto-detect de CDP existente contra su Chrome real (falló: Chrome M136+ bloquea el puerto CDP remoto en el perfil default por seguridad) → investigar cómo lo resuelve la extensión oficial "Claude in Chrome" (permiso debugger + Native Messaging, no CDP-por-TCP) → diseñar (plan mode) y construir el mismo mecanismo para deepseekcli: chrome_bridge/ (extensión Manifest V3 + native host) + pwa/browser_bridge.py (puente sync↔async) + core/tools/browser.py con selección de backend en runtime.

Progreso

Completo y verificado end-to-end contra un Chrome real del usuario (no solo mocks/tests). Suite completa: 257 passed, 2 skipped.

  • chrome_bridge/ (nuevo paquete): extension/ (manifest.json MV3 con permiso debugger, key fija para ID reproducible — hgjekbbfnfopnhdgjgmmlncejahjbmcp —, background.js relay hacia chrome.debugger, íconos generados desde chinese.png), native_host.py (relay puro stdio↔WebSocket vía Native Messaging), install.py (detecta navegadores Chromium instalados y registra el manifest de Native Messaging Host + launcher ejecutable).
  • pwa/browser_bridge.py (nuevo): BrowserBridge, puente sync↔async — mismo patrón que SessionHub._pending_confirms (dict id -> (threading.Event, slot) + asyncio.run_coroutine_threadsafe). Endpoint nuevo /ws/browser-bridge en pwa/main.py.
  • core/tools/browser.py: refactor a _PlaywrightDriver/_ExtensionDriver detrás de _ensure_driver() — extensión conectada tiene prioridad; si no, cae a la cadena Playwright/CDP existente (DEEPSEEK_CDP_URL → puerto 9222 → Chromium propio visible). Los 8 nombres de tool no cambiaron. browser_click/browser_type muestran un cursor visual (punto rojo inyectado vía Runtime.evaluate, se desliza y pulsa) — aplica a ambos drivers.
  • deep browser install-extension [--port]: nuevo comando (cli/commands.py + subcomando en deep.py).
  • Documentación: README (sección "Navegador" + fila en la tabla de tools), doc/CHANGELOG.md, doc/arquitectura.md (sección 11.4).

Read the full file on GitHub · 98 lines

Changes

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.

  1. 2d ago First seen · 98 lines · 1,728 tokens per session scan A bf426f0d207d

Subscribe to this mod's changes

deepseekCLI CLAUDE.md is an instructions file published in the GitHub repository cynchro/deepseekCLI (21 stars, last pushed 19d ago), licensed MIT. It adds 1,728 tokens to every session, about $0.0086 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens