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 agentmods add skills/lessweb/deepcode-cli/deepcode-self-refernpx skills add lessweb/deepcode-cli --skill deepcode-self-refergit clone --depth 1 https://github.com/lessweb/deepcode-cliWhat 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 | $0.00086 | $0.01962 |
| Opus 5 | $0.00043 | $0.00981 |
| Sonnet 5 | $0.00017 | $0.00392 |
| Haiku 4.5 | $0.00009 | $0.00196 |
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 yesterday.
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 — 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 (10 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 |
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.
- references/configuration_en.md 15 KB
- references/configuration.md 13 KB
- references/mcp_en.md 6.2 KB
- references/mcp.md 5.8 KB
- references/notify_en.md 5.4 KB
- references/notify.md 5.4 KB
- references/permission_en.md 4.5 KB
- references/permission.md 4.3 KB
- references/README.md 9.6 KB
- references/session-persistence_en.md 8.1 KB
- references/session-persistence.md 7.1 KB
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.
- yesterday First seen · 146 lines · 86 tokens per session scan A 48bfee898ce2
deepcode-self-refer is a skill published in the GitHub repository lessweb/deepcode-cli (2,224 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 1,962 once invoked, about $0.0004 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
weibo-poster
微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.
xiaohongshu-writer
小红书笔记写作助手 - 标题优化、emoji策略、话题标签、封面文案、笔记结构.
code-review
Review code changes for quality, security, performance, and correctness following project-specific standards. Use when reviewing pull requests, examining git diffs, or when the user asks for a code review. This skill should be used proactively — when the user asks for a review without specifying commits, automatically…
word-writer
Word 文档助手 - 文章撰写、格式排版、模板选择、目录生成、批量处理.
litho-document-skill
This skill should be used when the user asks to "generate project documentation", "analyze codebase architecture", "create C4 architecture diagrams", "document a repository", "generate technical docs", "使用 Litho 生成文档", "分析代码库架构", "生成架构文档", "为项目生成技术文档", "生成 C4 模型文档", "为这个项目写文档", "自动生成文档", "帮我分析这个代码库", or any request…