An interactive agent-creation tool for aweek, a scheduler for coding agents. It collects an agent's identity and interviews you to create its long-term goals, plans, strategies, and notes.

Use it to create a new coding subagent, define its role and instructions, and prepare its plan for weekly task scheduling.

It creates a usable agent configuration and plan in one guided process instead of leaving you to assemble several files manually. The new agent can then be scheduled for its first week.

hire — Skill for Claude Code by runbear-io

Install

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.

Any agent

npx skills add runbear-io/aweek --skill hire

Clone the repo

git clone --depth 1 https://github.com/runbear-io/aweek

Made for: Claude Code.

Or install aweek, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/runbear-io/aweek/hire.svg)](https://agentmods.dev/skills/runbear-io/aweek/hire)

Your own site

<a href="https://agentmods.dev/skills/runbear-io/aweek/hire"><img src="https://agentmods.dev/badge/skills/runbear-io/aweek/hire.svg" alt="Measured on agentmods" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,812 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00043	$0.02812
Opus 5	$0.00022	$0.01406
Sonnet 5	$0.00009	$0.00562
Haiku 4.5	$0.00004	$0.00281

Measured 6d ago against content hash 7bff458494b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hire 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 6d 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.

skills/hire/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aweek:hire

Hire a new aweek agent interactively. Each aweek agent is a 1-to-1 wrapper around a Claude Code subagent defined in .claude/agents/<slug>.md. This skill captures identity (name, description, system prompt) AND conducts a short interview to populate the agent's planning markdown. It writes three things:

The subagent .md at .claude/agents/<slug>.md.
The aweek scheduling JSON shell at .aweek/agents/<slug>.json.
A fully-written plan.md at .aweek/agents/<slug>/plan.md, built from the interview answers (not the blank template).

After the hire finishes, the user can move straight to /aweek:plan Branch B to schedule their first week — no editor round-trip required.

The skill is a thin UX wrapper on top of src/skills/hire-create-new-menu.js (for the create-new branch) and src/skills/hire-all.js (when adopting an existing unhired subagent). All persistence and validation live in those modules — do not write agent JSON or .claude/agents/<slug>.md files directly.

Instructions

You MUST follow this exact workflow when this skill is invoked.

Step 0: Route Between Pick-Existing and Create-New

Before asking for any identity input, decide which branch of the wizard to run. The rule is simple: if there are one or more unhired Claude Code subagents already on disk under .claude/agents/<slug>.md (i.e. a file exists but there is no matching .aweek/agents/<slug>.json), offer the user a choice between adopting one of them or creating a brand-new subagent. When none are available, skip the branching question and go straight to the create-new path.

aweek exec hire-route determineHireRoute

The JSON result has the shape { route: 'create-new' | 'choose', unhired: string[], forcedCreateNew: boolean }.

route === 'create-new' (also forcedCreateNew: true): Tell the user no unhired subagents were found under .claude/agents/ and jump straight to Step 1 (create-new). Do NOT ask "Pick existing or Create new?" in this case.
route === 'choose': Use AskUserQuestion to offer exactly two options:
1. Pick existing — adopt one of the slugs listed in unhired.
2. Create new — write a fresh .claude/agents/<slug>.md via the Step 1 flow below.

Read the full file on GitHub · 276 lines

Changes

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.

6d ago First seen · 276 lines · 43 tokens per session scan A 7bff458494b8

Subscribe to this mod's changes

hire is a skill published in the GitHub repository runbear-io/aweek (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,812 once invoked, about $0.0002 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.

Building agents Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens