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/hotovo/aider-desk/agent-creatornpx skills add hotovo/aider-desk --skill agent-creatorgit clone --depth 1 https://github.com/hotovo/aider-deskWhat 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 | $0.00060 | $0.02625 |
| Opus 5 | $0.00030 | $0.01313 |
| Sonnet 5 | $0.00012 | $0.00525 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
agent-creator 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Profile Creator
Create agent profiles stored as config.json in ~/.aider-desk/agents/{name}/ (global) or {project}/.aider-desk/agents/{name}/ (project-level).
Read all reference files before proposing a profile to ensure accuracy:
references/agent-profile-schema.md— Complete property referencereferences/subagent-guide.md— Subagent config, system prompts, context memory, filteringreferences/tool-approval-guide.md— All tool groups, correct tool keys, approval strategiesreferences/profile-examples.md— Complete working examples
Q&A Process
Gather complete requirements before proposing a profile. Ask focused questions, propose internally, and present one final summary for approval.
Step 1: Purpose & Behavior
Ask: "Describe the agent's purpose and what it should do."
Based on the response, internally propose:
- Name (derived from purpose)
- Max iterations (default
0= unlimited; use a finite value like 250 for bounded tasks, or lower for focused tasks like review/analysis: 150) - Tool groups (based on purpose — see Step 3)
- Custom instructions (free-text guidance appended to the system prompt)
- System prompt — does the agent need a fully custom system prompt that replaces the default built-in one? If the user describes specific behavioral constraints, role, or identity, propose a
systemPrompt. - Subagent config — should this profile be usable as a subagent? If yes, gather subagent-specific system prompt, invocation mode, color, description, and context memory mode.
Step 2: Provider & Model
Ask: "Which provider/model? (format: provider/model, e.g., anthropic/claude-sonnet-5)"
- Split by first slash to get provider and model
- Use as-is (correct obvious typos only)
- If the user does not specify, default to
anthropic/claude-sonnet-5(matchingDEFAULT_AGENT_PROFILE/DEFAULT_PROVIDER_MODELSinpackages/common/src/agent.ts). You may ask the user for their preferred provider/model, but if none is given, use these defaults. - Optionally ask about
temperatureandmaxTokensif the purpose implies precision (low temp) or creativity (high temp)
What ships with it
6 files 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.
- yesterday First seen · 224 lines · 60 tokens per session scan A fd8599bb10f7
agent-creator is a skill published in the GitHub repository hotovo/aider-desk (1,406 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 2,625 once invoked, about $0.0003 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
team
Guides agent team orchestration with TeamCreate, parallel teammate spawning, task coordination, specialist agent selection, and --teammate-mode configuration for concurrent workstreams. USE WHEN the user asks to "spawn a team", "create a team of agents", "use a swarm", "work in parallel", "coordinate multiple agents"…
skill-building
Guides Claude Code plugin skill creation covering SKILL.md structure, description optimization, and progressive disclosure. USE WHEN the user asks to "build a skill", "write a SKILL.md", "create a Claude Code skill", "improve a skill description", "optimize skill content", "design skill instructions", or works with…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
icon-jetbrains
Create or review IntelliJ New UI SVG icons, theme variants, sizes, and palette.