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.
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 zhu1090093659/deepseek-pp --skill skillgit 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/skills/zhu1090093659/deepseek-pp/skill)<a href="https://agentmods.dev/skills/zhu1090093659/deepseek-pp/skill"><img src="https://agentmods.dev/badge/skills/zhu1090093659/deepseek-pp/skill/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/zhu1090093659/deepseek-pp/skill"><img src="https://agentmods.dev/badge/skills/zhu1090093659/deepseek-pp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 117 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00042 | $0.01767 |
| Opus 5 | $0.00021 | $0.00883 |
| Sonnet 5 | $0.00008 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
deepseek-automation 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 10d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Automation
Use this project-local skill for the DeepSeek++ automation implementation. The feature goal is: create Codex-style automations that can run immediately in a new DeepSeek chat session and then continue in that same automation session on a cron/RRULE-like schedule.
Start Every Session
- Read
docs/progress/MASTER.md. - Confirm tracking mode. Current mode is
GITHUB_STANDARD. - Query GitHub before starting work:
gh issue list -R zhu1090093659/deepseek-pp --label "spec-driven" --state open --json number,title,labels,milestone
- Pick the next open issue in dependency order unless the user names a task.
- Read the selected Issue body and linked local docs under
docs/analysis/anddocs/plan/. - Update
docs/progress/MASTER.mdCurrent Status at session start and end.
Architecture Rules
- Keep scheduling in background code.
- Keep actual DeepSeek request execution in the DeepSeek page main-world context.
- Use content script only as a narrow bridge between background and main world.
- Do not add automation business logic directly into
fetch-hook.tsunless the task is explicitly about hook compatibility. - Prefer new focused files under
core/automation/. - Do not rely on background-only
fetch('/api/v0/chat/completion')for MVP; DeepSeek web completion has challenge/proof-of-work behavior. - Preserve existing memory, skill, preset, and tool-call behavior unless the Issue explicitly changes it.
DeepSeek Web Facts
Verified on 2026-05-21:
- Completion endpoint:
/api/v0/chat/completion. - History endpoint:
/api/v0/chat/history_messages. - Completion request fields include
chat_session_id,parent_message_id,model_type,prompt,ref_file_ids,thinking_enabled,search_enabled,action, andpreempt. - New session and same-session continuation work from the web UI.
- Reload restores the automation test session from history.
- Persist the latest valid parent message id after every run and reconcile it against history.
What ships with it
1 file 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.
- 10d ago First seen · 186 lines · 42 tokens per session scan A d438881339d0
deepseek-automation is a skill published in the GitHub repository zhu1090093659/deepseek-pp (1,818 stars, last pushed 27d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,767 once invoked, about $0.0002 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 skills, from other repositories
seekbridge-browser
Operate the user's real Chrome through SeekBridge with task-owned tabs, semantic element refs, verified actions, and safe recovery. Use for navigating websites with DeepSeek-powered agents, working in signed-in web apps, collecting page information, filling ordinary forms, testing web interfaces, taking screenshots…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
weibo-poster
A writing guide for Weibo, a Chinese microblogging platform similar to a short-post social network. It covers concise posts, longer posts, hashtags, @ mentions, image layouts, and posting-time suggestions.