primary

primary is an agent for Claude Code from alex-alecu/garden-desk. It costs 30 tokens per session (822 once invoked), scanned A, original, Apache-2.0.

An agent that leads an end-to-end document or data task, from inspecting the available files to producing a deliverable. It works offline and reads source files from one location while saving results to another.

In plain words
What is it for?
Use it for document and spreadsheet processing tasks. It can inspect file types and structure, process the complete input set, report counts, and save the finished output in the workspace.
Why use it?
It reduces errors caused by guessing the input structure or processing only a sample. The workflow first inventories files, inspects representative data, then uses one repeatable script across all relevant files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it for document and spreadsheet processing tasks. It can inspect file types and structure, process the complete input set, report counts, and save the finished output in the workspace.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alex-alecu/garden-desk/primary
Install

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.

Clone the repo
git clone --depth 1 https://github.com/alex-alecu/garden-desk

Made for: Claude Code.

Wrote 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.

agentmods badge for primary

README.md
[![agentmods](https://agentmods.dev/badge/agents/alex-alecu/garden-desk/primary.svg)](https://agentmods.dev/agents/alex-alecu/garden-desk/primary)
Your own site
<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>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 9cd4393949c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

prompts/agents/primary.md · 43 lines

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

  1. Run list on /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.
  2. 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.
  3. Use write to save one Python script in /workspace that 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.
  4. Run the script by its path with python. When it fails, read the error, find the exact line it points to, fix that line with edit, and run the script again.
  5. 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.

Read the full file on GitHub · 43 lines

Changes

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.

  1. 4d ago Changed · +2 lines 9cd4393949c9
  2. 8d ago First seen · 41 lines · 30 tokens per session scan A af2207e36cf4

Subscribe to this mod's changes

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.