What is deepcode-self-refer?

A reference guide for using and configuring the Deep Code command-line tool, including its commands, settings, Skills, MCP connections, permissions, notifications, and saved sessions. MCP is a standard way for an AI tool to connect to outside services.

Use it to explain configuration, available commands and models, MCP server setup, web search, permissions, notifications, session history, or editor integration.

It helps answer Deep Code setup and troubleshooting questions from the bundled documentation instead of relying on guesswork.

deepcode-self-refer — Skill for Claude Code and Codex by lessweb

About the project

Deep Code CLI is a terminal-based AI coding assistant optimized for the DeepSeek V4 model, with controls for reasoning depth and support for extensible agent skills. Developers use it to work with code from any project directory. The catalogue skills extend its capabilities.

lessweb/deepcode-cli · 2,158 stars · on GitHub · deepcode.vegamo.cn

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.

Any agent

npx skills add lessweb/deepcode-cli --skill deepcode-self-refer

Clone the repo

git clone --depth 1 https://github.com/lessweb/deepcode-cli

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lessweb/deepcode-cli/deepcode-self-refer/github.svg)](https://agentmods.dev/skills/lessweb/deepcode-cli/deepcode-self-refer)

Your own site

<a href="https://agentmods.dev/skills/lessweb/deepcode-cli/deepcode-self-refer"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/deepcode-self-refer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lessweb/deepcode-cli/deepcode-self-refer"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/deepcode-self-refer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,962 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

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 →

medium Prompt Injection · line 34
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.01962
Opus 5.5	$0.00034	$0.00785
Sonnet 5.5	$0.00017	$0.00392
Haiku 4.5	$0.00009	$0.00196

Measured 1mo ago against content hash a1505ee6e61c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deepcode-self-refer 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 1mo 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.

packages/core/templates/skills/bundled/deepcode-self-refer/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Code Self-Refer

This Skill helps you answer user questions about Deep Code CLI itself by consulting the reference documentation bundled with this Skill. All docs live in the references/ subdirectory — always refer to them for authoritative answers.

When to use this Skill

Use this Skill when the user asks any question about Deep Code itself, such as:

"列出可用的 skills"
"如何配置 MCP？"
"给当前项目配置 playwright mcp"
"怎么启用搜索功能？"
"支持哪些模型？"
"如何配置思考模式？"
"怎么设置权限？"
"任务完成后怎么发通知？"
"支持哪些斜杠命令？"
"会话历史保存在哪里？"
"/undo 是怎么工作的？"
"Deep Code 和 VSCode 插件怎么配合？"
Any other question about Deep Code CLI's features, configuration, or usage.

Instructions

Step 1: Identify the topic

Map the user's question to the appropriate document(s):

Topic	Document	Key contents
Overview, features, quick start	`references/README.md`	Installation, slash commands, keyboard shortcuts, supported models, FAQ
Configuration & settings	`references/configuration.md`	`settings.json` fields, config hierarchy, env vars, thinking mode, reasoning effort, webSearchTool, enabledSkills
MCP setup & usage	`references/mcp.md`	MCP server config format, GitHub/Playwright/Filesystem examples, tool naming (`mcp__<name>__<tool>`), troubleshooting
Permissions	`references/permission.md`	Permission scopes (12 types), allow/deny/ask/defaultMode config, priority rules, persistence
Notifications	`references/notify.md`	Notify script path, injected env vars, Slack/Feishu/iTerm2/macOS/Linux/Windows examples
Session persistence	`references/session-persistence.md`	Storage paths, JSONL format, session index, compaction, `/undo` mechanics, code snapshots

Read the full file on GitHub · 146 lines

Files

What ships with it

11 files 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.

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.

1mo ago Changed a1505ee6e61c
1mo ago First seen · 146 lines · 86 tokens per session scan A 48bfee898ce2

Subscribe to this mod's changes

deepcode-self-refer is a skill published in the GitHub repository lessweb/deepcode-cli (2,158 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 1,962 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents ai-agent deepseek

plugin-creator

Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…

openinterpreter/openinterpreter · 86 tokens

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.

zhayujie/CowAgent · 61 tokens

update-v8-version

Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.