deepseek-cli

deepseek-cli is a skill for Claude Code, Codex from appleweiping/WEIPING_WHALE. It costs 0 tokens per session (996 once invoked), scanned A, original, MIT.

A set of development instructions for WEIPING_WHALE, a terminal-based coding agent built with the DeepSeek CLI.

In plain words
What is it for?
It supports substantial changes across planning, development, testing, packaging, release work, monitoring, and later upgrades.
Why use it?
It gives contributors a release-focused checklist for keeping the agent, its safety controls, memory, tools, and documentation aligned with the code.

Skill for Claude CodeCodex

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 skills/appleweiping/weiping_whale/deepseek-cli
Any agent
npx skills add appleweiping/WEIPING_WHALE --skill deepseek-cli
Clone the repo
git clone --depth 1 https://github.com/appleweiping/WEIPING_WHALE

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for deepseek-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/appleweiping/weiping_whale/deepseek-cli.svg)](https://agentmods.dev/skills/appleweiping/weiping_whale/deepseek-cli)
Your own site
<a href="https://agentmods.dev/skills/appleweiping/weiping_whale/deepseek-cli"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_whale/deepseek-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 996 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00996
Opus 5 $0.00000 $0.00498
Sonnet 5 $0.00000 $0.00199
Haiku 4.5 $0.00000 $0.00100

Measured 5d ago against content hash 331b1033e65d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepseek-cli 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.

.codex/skills/deepseek-cli/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSeek CLI Skill

Use this skill for non-trivial work on WEIPING_WHALE (including its legacy deepseek CLI alias), especially release-level improvements, runtime honesty, safety, MCP, memory, terminal UX, packaging, or documentation.

Purpose

Keep DeepSeek CLI honest, small, useful, and release-ready. The project is a terminal-native coding agent, not a web app and not a toy demo. Every substantial change should improve a complete lifecycle:

planning -> design -> development -> testing -> release -> maintenance -> monitoring -> upgrade iteration

Phase 1 - Plan

  1. Inspect the current git status and protect user changes.
  2. Read README.md, package.json, config.toml, src/index.ts, src/agent.ts, src/config.ts, src/llm/deepseek.ts, src/memory.ts, src/session.ts, src/safety/*, src/tools/*, src/mcp/*, .github/workflows/ci.yml, and the relevant tests/scripts.
  3. Identify the project relationship:
    • WEIPING_COUNCIL: orchestration and cross-model review.
    • WEIPING_WHALE: terminal worker and fast local coding agent.
    • WEIPING_LAB: experiment/workbench surface.
    • WEIPING_WIKI: public route map, not a runtime dependency.
    • AGENT_RESOURCE: optional shared skill library, not a required checkout.
  4. Define a version-level batch. Do not ship only typo fixes unless the user explicitly asks for a tiny change.

Phase 2 - Design

For non-trivial upgrades, inspect concrete source files from active open-source agent CLIs. Do not rely only on READMEs.

Recommended references:

  • Google Gemini CLI: config validation, storage/session paths, retry/error handling, tool execution tests.
  • Aider: command running, model metadata, IO and regression tests.
  • OpenCode: config schema, permission model, provider status, session and error structure.

Record the specific modules inspected in the README, release notes, or handoff when they shape the change.

Phase 3 - Develop

Prefer small internal modules with clear responsibilities:

Read the full file on GitHub · 114 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. 5d ago First seen · 114 lines · 0 tokens per session scan A 331b1033e65d

Subscribe to this mod's changes

deepseek-cli is a skill published in the GitHub repository appleweiping/WEIPING_WHALE (134 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 996 tokens. 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens