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 extension-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/extension-creator)<a href="https://agentmods.dev/skills/hotovo/aider-desk/extension-creator"><img src="https://agentmods.dev/badge/skills/hotovo/aider-desk/extension-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/extension-creator"><img src="https://agentmods.dev/badge/skills/hotovo/aider-desk/extension-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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.
- medium Rogue Agent · line 169 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.
- medium Rogue Agent · line 175 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.
- low Excessive Agency · line 8 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00044 | $0.05544 |
| Opus 5 | $0.00022 | $0.02772 |
| Sonnet 5 | $0.00009 | $0.01109 |
| Haiku 4.5 | $0.00004 | $0.00554 |
Grade A, and why
extension-creator scanned grade A with 1 finding 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 12d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Pattern:** Node.js built-in modules (`fs`, `path`, `child_process`, `os`, etc.) are available in extensions. How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extension Creator
Create AiderDesk extensions that extend functionality through events, commands, tools, agents, and modes.
When to Use
Use this skill when:
- Building a new AiderDesk extension
- Creating extension commands, tools, or event handlers
- Implementing the Extension interface
- Setting up extension metadata and documentation
Do not use when:
- Simply activating an existing extension
- Making general code changes unrelated to extensions
- Running tests or builds
Rules
Rule: Choose installation target first
When: Starting extension creation
Then: Ask the user where to install the extension
If: Working inside the AiderDesk project (the current project is the aider-desk repository)
Then: Offer three options:
- Current Project — Install to
.aider-desk/extensions/in the current project (project-scoped) - Global — Install to
~/.aider-desk/extensions/(available in all projects) - In-Repo — Create inside
packages/extensions/extensions/(ships with AiderDesk app)
If: Working outside the AiderDesk project
Then: Offer two options:
- Current Project — Install to
.aider-desk/extensions/in the current project (project-scoped) - Global — Install to
~/.aider-desk/extensions/(available in all projects)
Must: Wait for user's choice before proceeding. The chosen target determines the entire workflow.
Reference: references/install-targets.md for full details on each target.
Rule: Follow the correct flow for the chosen target
When: User has chosen an installation target
If: Target is Current Project or Global
Then: Follow the Project / Global Flow:
- Determine extension type (single-file or folder)
- Create extension file(s) in the target directory (
.aider-desk/extensions/or~/.aider-desk/extensions/) - Implement Extension interface methods
- Export metadata and default class
- Verify the extension loads (auto-discovered, no registry needed)
What ships with it
22 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.
- assets/scripts/validate-extension-ui.mjs 16 KB runs code
- assets/templates/Component.jsx.template 2.1 KB
- assets/templates/ConfigComponent.jsx.template 1.3 KB
- assets/templates/folder-extension-with-config/index.ts.template 2.2 KB
- assets/templates/folder-extension/config.ts.template 805 B
- assets/templates/folder-extension/index.ts.template 1.1 KB
- assets/templates/folder-extension/package.json 255 B
- assets/templates/folder-extension/tsconfig.json 580 B
- assets/templates/single-file.ts.template 653 B
- assets/templates/ui-component-external.ts.template 2.1 KB
- assets/templates/ui-component.ts.template 2.0 KB
- references/command-definition.md 4.1 KB
- references/config-components.md 13 KB
- references/event-types.md 16 KB
- references/examples-gallery.md 18 KB
- references/extension-interface.md 44 KB
- references/extension-types.md 4.4 KB
- references/external-libraries.md 4.9 KB
- references/in-repo-flow.md 4.7 KB
- references/install-targets.md 3.8 KB
- references/project-global-flow.md 3.1 KB
- references/ui-components.md 30 KB
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.
- 12d ago First seen · 503 lines · 44 tokens per session scan A dd39be30b7ef
extension-creator is a skill published in the GitHub repository hotovo/aider-desk (1,423 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 5,544 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
fix-bugs
Autonomously fix bugs from any source — Slack threads, failing CI tests, docker logs, or a plain description. Use when you have a bug report or failing test and want Claude to investigate and fix without step-by-step guidance.