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/rbinar/cli-dispatch/ds-delegatenpx skills add rbinar/cli-dispatch --skill ds-delegategit clone --depth 1 https://github.com/rbinar/cli-dispatchWhat 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 | $0.00397 | $0.04896 |
| Opus 5 | $0.00198 | $0.02448 |
| Sonnet 5 | $0.00079 | $0.00979 |
| Haiku 4.5 | $0.00040 | $0.00490 |
Grade A, and why
ds-delegate 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-ds — DeepSeek delegation worker
claude-ds is a portable wrapper installed to ~/.local/bin by /cli-dispatch:setup;
it runs the Claude Code CLI against DeepSeek's Anthropic-compatible API. Since it's on
PATH, call it directly as claude-ds (no old zsh -ic function trick needed).
When / when not
- The built-in
Agent/subagent tool does NOT support DeepSeek (modelenum: sonnet/opus/haiku/fable). This is the only way to hand work to DeepSeek. - Conversation context is not shared → the prompt must be self-contained.
Wrappers
ds-agent(SIMPLEST — subagent-style) — one synchronous command: give it a task, it runs to completion, streams tool activity to stderr, and prints only the final answer to stdout. Default agentic (may write/run in--cwd);--read-onlyfor analysis-only. Best when you just want "delegate this and give me the result" in a single call.claude-ds-stream— runsclaudewith stream-json, parses output into a session directory (live + observable + resumable). Use when you want to run in the background and poll, or need the session id /--resume//cli-dispatch:watchworkflow.claude-ds— plain env wrapper (claude "$@"). No parsing/session; fast one-shot only.
ds-agent — single command (subagent-style)
ds-agent "<task>" # agentic in cwd; live progress on stderr; answer on stdout
ds-agent --read-only "<question>" # no writes / no bash
ds-agent --cwd <dir> "<task>" # work in <dir> (use an isolated dir for safety)
ds-agent --resume <id> "<follow-up>" # continue a session
echo "<task>" | ds-agent # task via stdin
stdout = final answer only (safe to capture/pipe); stderr = banner + live tool activity.
Exit code is the worker's. -q silences the banner/progress. It forwards
--max-runtime/--idle-timeout to the underlying claude-ds-stream.
Session directory: ${XDG_CACHE_HOME:-$HOME/.cache}/cli-dispatch/sessions/<id>/ (legacy claude-ds path still read as a fallback)
status.json— compact rolling summary (the only file to poll: state, lastTool, toolCounts, finalResultPreview)progress.log— terse human-readable stream (▸ Edit foo.ts,✓/✗, truncated text)transcript.jsonl— raw stream-json (resume/audit; NOT read while polling)meta.json— prompt preview, cwd, branch, model, start/end
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 · 242 lines · 397 tokens per session scan A 41217802bac0
ds-delegate is a skill published in the GitHub repository rbinar/cli-dispatch (5 stars, last pushed 14d ago), licensed MIT. It adds 397 tokens to every session and 4,896 once invoked, about $0.0020 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 2026-08-31.
Other skills, from other repositories
use-v4-flash-worker
Use the DeepSeek-backed v4flashworker through the installed one-shot plaintext SubagentStart Hook. Use whenever Codex considers spawning, continuing, or troubleshooting this worker; it governs task suitability, plaintext staging, native forkturns=none spawning and return, one-shot state recovery, and the configured…
deepcode-self-refer
Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such…
skill-writer
Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use when the user wants to create, write, author, design, troubleshoot, validate, or improve a Skill, or needs help with SKILL.md, frontmatter, or skill structure.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
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.