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/dapi/claude-code-marketplace/task-routingnpx skills add dapi/claude-code-marketplace --skill task-routinggit clone --depth 1 https://github.com/dapi/claude-code-marketplaceWhat 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 | $0.00434 | $0.02073 |
| Opus 5 | $0.00217 | $0.01037 |
| Sonnet 5 | $0.00087 | $0.00415 |
| Haiku 4.5 | $0.00043 | $0.00207 |
Grade A, and why
task-routing 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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Routing Skill
Version: 1.0.0
Тонкий автотриггер: обнаруживает ссылки на задачи и issue-ссылки в сообщениях пользователя и вызывает команду /route-task для классификации и маршрутизации.
Перед вызовом route-task покажи пользователю: task-routing v1.0.0
Этот скилл НЕ выполняет классификацию сам — только определяет наличие задачи и передаёт её в route-task.
Логика определения источника
1. GitHub Issue URL
Паттерн: github.com/{owner}/{repo}/issues/{number}
Если в сообщении есть ссылка на GitHub Issue:
-> Извлечь полный URL
-> Вызвать: Skill tool -> skill: "task-router:route-task", args: "{URL}"
2. Google Doc URL
Паттерн: docs.google.com/document/d/{DOCUMENT_ID}
Если в сообщении есть ссылка на Google Doc:
-> Извлечь полный URL
-> Вызвать: Skill tool -> skill: "task-router:route-task", args: "{URL}"
3. Issue-ссылка (#NNN)
Паттерн: issue #123, задачу #123 — ОБЯЗАТЕЛЬНО с action-словом И словом issue/задачу
ВАЖНО: Голый #NNN без контекста НЕ является триггером. #NNN часто встречается в коммитах, PR-ах, заголовках и не означает задачу. Активируй ТОЛЬКО при наличии ОБОИХ условий:
- Action-слово: "сделай", "возьми", "реализуй", "take", "implement", "do", "start"
- Слово-контекст: "issue", "задачу", "задачи", "task"
Если в сообщении есть action-слово + "issue"/"задачу" + #NNN:
-> Извлечь номер
-> Вызвать: Skill tool -> skill: "task-router:route-task", args: "#NNN"
Примеры ДА: "сделай issue #123", "take issue #42", "возьми задачу #99"
Примеры НЕТ: "see #123", "fixed in #42", "PR #99", "step #3"
4. Произвольный URL
Если в сообщении есть другой URL (https://...) в контексте задачи:
-> Извлечь URL
-> Вызвать: Skill tool -> skill: "task-router:route-task", args: "{URL}"
5. Локальный файл
Паттерн: абсолютный путь (/...) или относительный (~/..., ./...) к файлу плана
Если в сообщении есть путь к файлу (начинается с / или ~/ или ./):
-> Извлечь полный путь
-> Вызвать: Skill tool -> skill: "task-router:route-task", args: "{path}"
Примеры ДА: "реализуй /home/user/plan.md", "выполни ./docs/plans/fix.md"
Примеры НЕТ: "посмотри /docs/plans/fix.md", "что в ./plans/spec.md"
What ships with it
1 file 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.
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.
- 2d ago First seen · 172 lines · 434 tokens per session scan A 9b558cc0ce95
task-routing is a skill published in the GitHub repository dapi/claude-code-marketplace (16 stars, last pushed 4mo ago), licensed MIT. It adds 434 tokens to every session and 2,073 once invoked, about $0.0022 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…