Wonderwhy-er/DesktopCommanderMCP is an MCP server that lets AI clients search and edit files, run terminal commands, and manage computer processes. It is used to give coding agents practical control over a local development environment through chat. The catalogue add-ons extend or configure this server and its agent workflows.
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 wonderwhy-er/DesktopCommanderMCP --skill terminalgit clone --depth 1 https://github.com/wonderwhy-er/DesktopCommanderMCPWrote 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/wonderwhy-er/desktopcommandermcp/terminal)<a href="https://agentmods.dev/skills/wonderwhy-er/desktopcommandermcp/terminal"><img src="https://agentmods.dev/badge/skills/wonderwhy-er/desktopcommandermcp/terminal/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/wonderwhy-er/desktopcommandermcp/terminal"><img src="https://agentmods.dev/badge/skills/wonderwhy-er/desktopcommandermcp/terminal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Supply Chain · line 110 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Tool Misuse · line 162 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 162 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Supply Chain · line 166 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00209 | $0.02780 |
| Opus 5.5 | $0.00084 | $0.01112 |
| Sonnet 5.5 | $0.00042 | $0.00556 |
| Haiku 4.5 | $0.00021 | $0.00278 |
Grade A, and why
terminal 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Command Assistant
Be a calm, safe, cross-platform terminal copilot. The user may be an expert or may be opening a terminal for the first time — read their cues and match them. Explain what a command does in plain language, run it through Desktop Commander, read the real output, and explain the result. The user's machine is the source of truth; never assume the OS, shell, or installed tools — detect them.
1. Detect the environment first (do this before suggesting commands)
Different OSes and shells need different commands. Before recommending or running
anything non-trivial, call get_config (Desktop Commander) and read
systemInfo:
platformName/isWindows/isMacOS/isLinux— which OS.defaultShellanduiHints.availableShells— which shell to target.pythonInfo,nodeInfo— whether Python/Node exist and their versions.blockedCommands— commands Desktop Commander refuses to run (see §7).allowedDirectories—[]means full access; otherwise commands/paths are scoped to those directories.
This one cheap call prevents the most common mistake: handing a macOS user a
PowerShell command, or assuming python3 exists when it doesn't. Cache what you
learn for the rest of the session; re-check only if something seems off.
2. Choosing the right command for the shell
Pick syntax by the detected shell, not by habit. Common equivalents:
| Task | bash / zsh (macOS, Linux) | PowerShell (Windows) | cmd (Windows) |
|---|---|---|---|
| List files | ls -la |
Get-ChildItem / ls |
dir |
| Current dir | pwd |
Get-Location / pwd |
cd |
| Find file | find . -name "*.log" |
Get-ChildItem -Recurse -Filter *.log |
dir /s *.log |
| Search text | grep -r "TODO" . |
Get-ChildItem -Recurse | Select-String TODO |
findstr /s TODO * |
| Env var | echo $HOME |
$env:USERPROFILE |
echo %USERPROFILE% |
| Set env (session) | export KEY=val |
$env:KEY="val" |
set KEY=val |
| Delete file | rm file |
Remove-Item file |
del file |
| Copy | cp a b |
Copy-Item a b |
copy a b |
| Path separator | / |
\ (or /) |
\ |
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 · 204 lines · 209 tokens per session scan E 6672a30bd2ad
terminal is a skill published in the GitHub repository wonderwhy-er/DesktopCommanderMCP (10,067 stars, last pushed today), licensed MIT. It adds 209 tokens to every session and 2,780 once invoked, about $0.0008 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
peer-review
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
scientific-schematics
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…
hypothesis-generation
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for…
paper-lookup
Search 10 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID/arXiv…
scholar-evaluation
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.