AiderDesk is an open-source desktop platform that coordinates AI-assisted software development around the Aider coding tool, letting engineers inspect and control proposed changes. It is for professional developers who want AI help while retaining their existing editor, terminal, and Git workflow. Catalogue add-ons extend its controlled development workflow.
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 skills add hotovo/aider-desk --skill agent-creatorgit clone --depth 1 https://github.com/hotovo/aider-deskWrote 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.
[](https://agentmods.dev/skills/hotovo/aider-desk/agent-creator)<a href="https://agentmods.dev/skills/hotovo/aider-desk/agent-creator"><img src="https://agentmods.dev/badge/skills/hotovo/aider-desk/agent-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hotovo/aider-desk/agent-creator"><img src="https://agentmods.dev/badge/skills/hotovo/aider-desk/agent-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00060 | $0.02625 |
| Opus 5.5 | $0.00024 | $0.01050 |
| Sonnet 5.5 | $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 1mo 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 — 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.
- 1mo ago First seen · 224 lines · 60 tokens per session scan A fd8599bb10f7
agent-creator is a skill published in the GitHub repository hotovo/aider-desk (1,457 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 2,625 once invoked, about $0.0002 per session on Opus 5.5. 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
jetbrains-session
Use when working on the JetBrains chat session UI or SessionModel/SessionController — transcript cards, retained Swing lifecycle, session background surfaces, editor-derived styling, adding session events, and session/controller testing with FakeSessionRpcApi.
chart
Use when the user asks to visualize data with charts, graphs, or plots using the chart tool (bar, line, scatter, pie, time series, etc.).
gh-issues
Use when creating, triaging, or commenting on GitHub issues for the Kilo VS Code extension or JetBrains plugin via gh. Covers issue templates, project board assignment, title conventions, and required gh scopes.
paid-ads
When the user wants help with paid advertising on Google Ads, Meta, LinkedIn, or Twitter/X — 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'retargeting,' 'audience targeting,' 'ad budget,' 'should I run ads.' Covers campaign strategy, targeting, bidding, and optimization. For bulk ad creative, see ad-creative. For landing…
referral-program
When the user wants to create, optimize, or analyze a referral, affiliate, or word-of-mouth program — 'ambassador,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'affiliate payout.' For launch-specific virality, see launch-strategy.
subagents
Use subagents to throw more compute at hard problems, keep the main context window clean, and auto-approve safe permissions via hooks. Use when a task is complex, exploratory, or can be parallelized across multiple independent workstreams.