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 PsChina/deepseek-as-subagent --skill delegate-to-deepseekgit clone --depth 1 https://github.com/PsChina/deepseek-as-subagentWrote 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/pschina/deepseek-as-subagent/delegate-to-deepseek)<a href="https://agentmods.dev/skills/pschina/deepseek-as-subagent/delegate-to-deepseek"><img src="https://agentmods.dev/badge/skills/pschina/deepseek-as-subagent/delegate-to-deepseek/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/pschina/deepseek-as-subagent/delegate-to-deepseek"><img src="https://agentmods.dev/badge/skills/pschina/deepseek-as-subagent/delegate-to-deepseek.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.02216 |
| Opus 5.5 | $0.00050 | $0.00886 |
| Sonnet 5.5 | $0.00025 | $0.00443 |
| Haiku 4.5 | $0.00013 | $0.00222 |
Grade A, and why
delegate-to-deepseek 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 17d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delegate-to-deepseek — 主 Agent 派工准则
“主 Agent”指负责决策、整合与最终验收的上层 agent。
1. 不可突破的边界
- 用户显式要求派 / 不派、指定执行者或执行方式时，优先服从用户。
- 权限、安全、隐私、敏感信息和非授权写入边界不可绕过。
DEEPSEEK_MODE=off时不要派工。- DeepSeek 读取的文件内容会发送到配置的 API endpoint；敏感工作区不得派工。
- coding 能力固定为 Read / Write / Edit / Bash / Glob / Grep / NotebookEdit；readonly 固定为 Read / Glob / Grep。不得通过 task、steering 或其它参数提权。
- coding Bash 是受边界约束的 trusted-host Bash，不是操作系统级沙箱。
- 派工结果必须由主 Agent 独立验证，失败由主 Agent 收口。
- 出现文件 mutation、取消、断连或 MCP 重启后，先调用
get_deepseek_recovery()，核验实际文件，再用精确 transaction IDs 调用acknowledge_deepseek_mutations(...)；未确认前不要重试 mutation delegation。
2. API 选择
| 需求 | API |
|---|---|
| coding，直接等结果 | delegate_to_deepseek(task, context="", model="flash") |
| 纯静态文件分析，直接等结果 | delegate_to_deepseek_readonly(task, context="", model="flash") |
| coding，需要 steering / status / cancel | start_deepseek(task, context="", model="flash") |
| readonly，需要 steering / status / cancel | start_deepseek_readonly(task, context="", model="flash") |
| 查询后台任务 | get_deepseek_status(job_id) |
| 追加/修正后台指令 | send_deepseek_message(job_id, message) |
| 取消后台任务 | cancel_deepseek(job_id) |
| 获取最终结果 | get_deepseek_result(job_id) |
| 查询 mutation recovery | get_deepseek_recovery() |
| 确认已核验 mutation | acknowledge_deepseek_mutations(transaction_ids) |
只读、搜索、review 已存在文件且整个任务不执行命令/写文件时用 readonly；其余或不确定时用 coding。readonly job 后续需要 Bash 或写文件时，结束/取消后重新启动 coding job，不能 steering 提权。
3. 模型路由
model 只允许 flash 或 pro；不传时使用 flash。
- Flash：强前沿 coding-agent 档，默认主力。 粗略定位为高端 Sonnet 到 Opus 竞争区间：DeepSeek V4.1-Flash-1017 官方模型卡中，它在 DeepSWE v1.1、Automation-Bench、Agents' Last Exam、Apex Bench 上超过 Opus 5，但在 Terminal-Bench 4.0、ProgramBench、NL2Repo-Bench 上落后。用于常规 coding、review、调查、重构、测试、批处理和大多数多文件任务。
- Pro：旗舰级困难任务档，目标定位约 Opus / Sol 级。 用于复杂 debugging、架构级推理、困难跨文件任务、失败代价高的改动，或 Flash 已经失败后的升级。
- 当前路由要点： 截至 2026-10-22，DeepSeek 官方公告称
deepseek-v4-pro会在 V4.1-Pro 上线前路由到 V4.1-Flash。若pro配置仍指向该别名，Pro 实际上不会带来能力升级；只有配置到真实更强的模型后，才按 Pro 档派工。公告：https://www.deepseek.com/en/news/deepseek-v4-1-flash/。 - 普通任务默认 Flash；只有任务难度或 Flash 的失败记录明确要求时才选 Pro。主 Agent 只选择
flash/pro，不要尝试控制 reasoning effort；thinking 档位由用户配置决定。 - background job 启动时冻结模型、reasoning effort 与能力。需要换模型时结束/取消当前 job，再新建 job。
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.
- 17d ago Changed ab953681406b
- 2mo ago First seen · 126 lines · 125 tokens per session scan A cdd5c6ccdc1f
delegate-to-deepseek is a skill published in the GitHub repository PsChina/deepseek-as-subagent (58 stars, last pushed 5d ago), licensed MIT. It adds 125 tokens to every session and 2,216 once invoked, about $0.0005 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.
delegate-to-deepseek compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| delegate-to-deepseekPsChina/deepseek-as-subagent | Skill | 58 | 5d ago | MIT | A | 125 | Claude Code, Codex |
| delegatemhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 76 | Claude Code |
| launchmhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 156 | Claude Code |
| wikimhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 114 | Claude Code |
| scaffoldmhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 66 | Claude Code |
| floormhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 67 | Claude Code |
| usagesmhlaghari/stuntman | Skill | 16 | 20d ago | MIT | A | 114 | Claude Code |