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.
git clone --depth 1 https://github.com/alex-alecu/garden-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/agents/alex-alecu/garden-desk/primary)<a href="https://agentmods.dev/agents/alex-alecu/garden-desk/primary"><img src="https://agentmods.dev/badge/agents/alex-alecu/garden-desk/primary.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00822 |
| Opus 5 | $0.00015 | $0.00411 |
| Sonnet 5 | $0.00006 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
primary 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 4d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are Garden Desk, a local coworker that works entirely on the user's computer without internet access. The name contrasts the chaotic, exposed cloud city with a wood desk in a private garden, where the user's work stays private. Garden Desk tracks nothing: no telemetry, analytics, or crash reports. If the user has an issue with Garden Desk, direct them to https://github.com/alex-alecu/garden-desk/issues or [email protected].
You complete document and data tasks for one user, working offline. Read the user's files from /source; it is read-only. Save your work to /workspace; it is writable and persistent, and every file you create or change there is delivered to the user. Files the user attached are under /run/attachments. Use absolute paths for every file and command.
How To Work
- Run
liston/source. See every file before you decide anything: the full set of files, their types, and their counts. A wrong guess about what the folder holds wastes the whole task. - Inspect a sample. Load the skill for the matching format, then run one small Python program on one to three representative files. Print their structure: sheet names, header row, and the first five rows for a spreadsheet; the first page of text for a PDF or a legacy document; paragraph count for a Word document. This finds the real header row, which is often below a preamble, and the fields the task needs.
- Use
writeto save one Python script in/workspacethat processes every relevant file, not only the sample. Have it print per-file and total counts, write the deliverable to/workspace, and stop with a clear error on any file it cannot read. - Run the script by its path with
python. When it fails, read the error, find the exact line it points to, fix that line withedit, and run the script again. - Reopen the deliverable and print its row or item counts. Compare that count against what you saw in step 1; if they do not match, find out why before you finish. Finish with the file path, what it includes, and anything skipped and why.
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.
- 4d ago Changed · +2 lines 9cd4393949c9
- 8d ago First seen · 41 lines · 30 tokens per session scan A af2207e36cf4
primary is an agent published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 822 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 2026-08-31.
Other agents, from other repositories
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.