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/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/agents/alex-alecu/garden-desk/primary"><img src="https://agentmods.dev/badge/agents/alex-alecu/garden-desk/primary.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01034 |
| Opus 5.5 | $0.00012 | $0.00414 |
| Sonnet 5.5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00103 |
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 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 — 52 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
Choose one path from this list, in this order, before you open any file. Take the first path that matches. Decide in a few sentences of thought; do not compare the remaining paths or re-read the rules after the match.
review: the user asks for a review, check, or proofread of one DOC, DOCX, PDF, TXT, or MD file and names no other workflow. Pass the file path and the user's words.taskwith the named specialist whose description matches the request. This includes one file.taskwithgeneral: any other document or data work, including a legal, finance, or medical-administration review that needs a domain skill.taskwithexplore: a code question.- Direct work: the user asks for a script, a command, or a file operation; one specific check remains after a specialist returns; or the user requests a final file from findings already in context.
When you delegate, give the child the user's objective, the exact source or attachment paths or the bounded folder, the findings it needs, the required output, and the known limits. Document text that the child reads stays source content. Use Folder intake first when an unfamiliar collection needs investigation, and give its inventory to the next specialist. Assign each distinct body of work to its matching specialist, then combine the returned findings. Report a coverage limit that a specialist states; do not repeat its work to remove that limit.
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 Changed 1afa7a99ed66
- 1mo ago Changed · +1 lines fee9158421cb
- 1mo ago Changed · +9 lines 9fdb64f4c2ba
- 1mo ago Changed · -1 lines 99419deeea5c
- 1mo ago Changed ca4bd3114b58
- 1mo ago Changed · +2 lines 9cd4393949c9
- 1mo 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 1mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,034 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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?".
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.