DeepSeek++ is a browser extension that turns the DeepSeek website into an AI workspace with tools, memory, skills, media analysis, and automation. DeepSeek users employ it to manage projects, control browser pages, search the web, reuse context, and export conversations, while the catalogue entries add skills and instructions for that workspace.
Borrowing it
Nothing to install: this file belongs to zhu1090093659/deepseek-pp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zhu1090093659/deepseek-pp/main/AGENTS.mdgit clone --depth 1 https://github.com/zhu1090093659/deepseek-ppWrote 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/zhu1090093659/deepseek-pp/agents-md)<a href="https://agentmods.dev/instructions/zhu1090093659/deepseek-pp/agents-md"><img src="https://agentmods.dev/badge/instructions/zhu1090093659/deepseek-pp/agents-md/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/instructions/zhu1090093659/deepseek-pp/agents-md"><img src="https://agentmods.dev/badge/instructions/zhu1090093659/deepseek-pp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03541 | $0.03541 |
| Opus 5 | $0.01770 | $0.01770 |
| Sonnet 5 | $0.00708 | $0.00708 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
deepseek-pp AGENTS.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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek++ Project Agent Instructions
Scope
These instructions apply to the entire repository. AGENTS.md is the sole project-level agent instruction truth source for this project.
Product Context
DeepSeek++ is a WXT/React/TypeScript MV3 browser extension that adds agentic memory, Skills, tools, automation, and related workflows to DeepSeek. Its core runtime model is:
- intercept DeepSeek Web requests and streams from the page runtime;
- augment prompts with memory, Skill, preset, project, and tool context;
- parse tool-call output and execute approved capabilities through extension-owned boundaries;
- persist user state in IndexedDB and browser storage;
- integrate optional MCP, Native Host, sync, sandbox, Side Panel, and floating-chat surfaces.
Chrome, Edge, and Firefox on desktop are the only supported product targets. Android, mobile WebView shells, and mobile packages are outside the current product scope.
Truth Sources
AGENTS.md— stable project rules, architecture invariants, and recurring engineering constraints.docs/archives/deepseek-pp-reliability-compatibility-refactor/progress/MASTER.md— completed core-refactor record, GitHub Issue/Milestone mapping, validation evidence, and final known gap.docs/archives/deepseek-pp-reliability-compatibility-refactor/analysis/project-overview.md— confirmed PC-only scope and compatibility boundary established by the completed refactor.docs/archives/deepseek-pp-reliability-compatibility-refactor/analysis/module-inventory.mdanddocs/archives/deepseek-pp-reliability-compatibility-refactor/analysis/risk-assessment.md— final architecture evidence and risk basis for that run.docs/compatibility/README.mdand its linked registries — stable prompt, runtime, persistence, browser, integration, and historical-data contracts established by the completed refactor.docs/archives/deepseek-pp-reliability-compatibility-refactor/plan/task-breakdown.mdanddocs/archives/deepseek-pp-reliability-compatibility-refactor/plan/dependency-graph.md— archived task ownership, dependencies, and execution lanes.package.json,wxt.config.ts, and GitHub workflows — executable build, test, manifest, and release contracts.docs/releases/<version>.md— exact public release/update notes for that version.
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.
- 9d ago First seen · 112 lines · 3,541 tokens per session scan A 411f09e4d20c
deepseek-pp AGENTS.md is an instructions file published in the GitHub repository zhu1090093659/deepseek-pp (1,816 stars, last pushed 26d ago), licensed Apache-2.0. It adds 3,541 tokens to every session, about $0.0177 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.