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/runbear-io/aweek/delegate-tasknpx skills add runbear-io/aweek --skill delegate-taskgit clone --depth 1 https://github.com/runbear-io/aweekWhat 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 | $0.00016 | $0.01424 |
| Opus 5 | $0.00008 | $0.00712 |
| Sonnet 5 | $0.00003 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
delegate-task 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aweek:delegate-task
Delegate a task from one agent to another. The task is placed in the recipient's async inbox queue and will be picked up on the next heartbeat. This enables inter-agent collaboration without synchronous cross-agent sessions.
Instructions
You MUST follow this exact workflow when this skill is invoked. Use the project's Node.js modules in src/skills/delegate-task.js — never write inbox JSON files directly.
Step 1: List Available Agents
List all available agents so the user can choose sender and recipient:
echo '{"dataDir":".aweek/agents"}' \
| aweek exec agent-helpers listAllAgents --input-json -
The response is an array of { config } records. Project each entry to
{ id: config.id, name: config.identity?.name, role: config.identity?.role }
for display. Treat fewer than 2 entries as the "need more agents" case.
- If fewer than 2 agents exist, inform the user: "At least 2 agents are needed for delegation. Use /aweek:create-agent to create more." and stop.
- Display a numbered list showing agent name, role, and ID.
Step 2: Select Sender Agent
Ask the user using AskUserQuestion: "Which agent is delegating the task? (select by number or name)"
- Validate the selection matches an existing agent.
Step 3: Select Recipient Agent
Ask the user using AskUserQuestion: "Which agent should receive the task? (select by number or name)"
- Validate the selection matches an existing agent.
- The recipient MUST be different from the sender — an agent cannot delegate to itself.
Step 4: Collect Task Details
Ask the user for the task details:
-
Task Description (required): Ask using AskUserQuestion: "Describe the task to delegate (max 2000 characters):"
- Must be a non-empty string, max 2000 characters.
-
Priority (optional): Ask using AskUserQuestion: "Priority level? (critical / high / medium / low) — default: medium"
- Valid values:
critical,high,medium,low - Default:
mediumif the user skips or enters empty.
- Valid values:
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 · 151 lines · 16 tokens per session scan A 6a7e7b7f40a1
delegate-task is a skill published in the GitHub repository runbear-io/aweek (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,424 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 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…