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 commands/pschina/deepseek-as-subagent/dsgit 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/commands/pschina/deepseek-as-subagent/ds)<a href="https://agentmods.dev/commands/pschina/deepseek-as-subagent/ds"><img src="https://agentmods.dev/badge/commands/pschina/deepseek-as-subagent/ds.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00026 | $0.00549 |
| Opus 5 | $0.00013 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
ds 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.
What it actually says
/ds — Delegate to DeepSeek
把后面跟的任务强制派给 DeepSeek 处理，绕过 Claude 的自动决策（"该派 / 不该派"）。
/ds 固定调用完整 coding API；明确只做静态文件分析的任务应由主 Agent 选择
delegate_to_deepseek_readonly。
模型选择遵循 delegate-to-deepseek skill：默认不传 model，即使用 Flash；只有任务明显属于复杂 debugging、架构级推理、困难多文件推理，或 Flash 已明显不足时才传 model="pro"。Flash 约为 Sonnet/Terra 档，Pro 约为 Opus/Sol 档；这是路由参考，不是绝对等价声明。
flash/pro 只是稳定路由槽位。不要把真实 provider 模型名传进 MCP；实际模型名由用户的 ~/.deepseek-mcp/config.json 中 flash / pro 字段决定。
你要做的
-
按
delegate-to-deepseekskill 的准则准备task、context和必要时的model：- 用 Glob / LS 收集涉及的文件路径
- 摘要项目约定（命名规则、输出 schema、边界）
- 写明成功标准
- 普通任务保持默认 Flash；困难任务才显式选择 Pro
-
调用
mcp__deepseek__delegate_to_deepseek工具，把用户的请求当作 task 传入：
用户输入: $ARGUMENTS
- 工具返回后必须验证：
- Read 抽样产物文件
- 检查数量 / schema sanity
- 失败按 skill 的 fallback 策略处理
不要做的
- ❌ 不要在调用前问用户"你确定要派吗" —— 用户敲
/ds已经是明确指令 - ❌ 不要因为 Pro 可用就默认选择 Pro
- ❌ 不要把真实 provider 模型名传给
model参数 - ❌ 不要在工具返回 ERROR 时直接放弃 —— 按 skill 的 fallback 策略重试或接管
- ❌ 不要把 API key / 凭证塞进 task / context
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.
- 5d ago First seen · 41 lines · 26 tokens per session scan A 9635bee0de64
ds is a command published in the GitHub repository PsChina/deepseek-as-subagent (30 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 549 once invoked, about $0.0001 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 commands, from other repositories
kmp-run-audit
KMP Agent Skills — run the architecture audit on a KMP project and get per-finding remediation steps from the matching skill.
kmp-setup-agents
KMP Agent Skills — initialize .claude/ in an existing KMP project so the team gets agent-driven workflows without running the full scaffold.
kmp-audit-screenshots
KMP Agent Skills — analyze Roborazzi golden screenshots for design consistency. Uses Claude's vision capability to inspect committed PNG files against the design system rules: color tokens, spacing, typography, TopAppBar structure, dark/light mode parity, and accessibility contrast.
kmp-fix-design
Scans an existing KMP project for design-system usage violations, fixes them file-by-file with per-file confirmation, then re-runs Roborazzi screenshot tests and uses Claude vision to verify each fix looks correct before moving on.
kmp-migrate-to-shadcn
Migrates an existing project from the owned kmp-compose-design-system (App components) to the published shadcn-compose library (Shadcn components). This is a full library swap, not an incremental fix — get explicit confirmation of the experimental-API risk before touching any code, same as /kmp-new-project's Step 6a…
kmp-audit-adaptive
KMP Agent Skills — check every screen for adaptive layout coverage gaps and redundant title violations across Compact (phone), Medium (tablet), and Expanded (desktop).