garden

garden is a command for coding agents from cwakim/claude-plugins. It costs 36 tokens per session (3,354 once invoked), scanned A, original, MIT.

A command for auditing a project's persistent memory for outdated, conflicting, duplicated, or unverifiable entries.

In plain words
What is it for?
Use it to review memory files, limit the audit by memory type or age, run a dry check, and clean up confirmed problems.
Why use it?
Project memory can become inaccurate as the codebase changes. The audit verifies claims against the repository and presents uncertain changes for confirmation.

Command

Part of the memory-gardener plugin — 1 command, 1 hook shipped together

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.

agentmods
npx agentmods add commands/cwakim/claude-plugins/garden
Clone the repo
git clone --depth 1 https://github.com/cwakim/claude-plugins

Or install memory-gardener, the plugin that ships this one along with the rest of its 1 command, 1 hook.

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 garden

README.md
[![agentmods](https://agentmods.dev/badge/commands/cwakim/claude-plugins/garden.svg)](https://agentmods.dev/commands/cwakim/claude-plugins/garden)
Your own site
<a href="https://agentmods.dev/commands/cwakim/claude-plugins/garden"><img src="https://agentmods.dev/badge/commands/cwakim/claude-plugins/garden.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,354 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.03354
Opus 5 $0.00018 $0.01677
Sonnet 5 $0.00007 $0.00671
Haiku 4.5 $0.00004 $0.00335

Measured 3d ago against content hash 7d57e3357b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

garden 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 3d 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.

plugins/memory-gardener/commands/garden.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Gardener

Audit this project's persistent memory directory and clean it up. Memory rots in predictable ways: "not yet done" flags that got done, entries that contradict newer ones, duplicates saved in different sessions, index lines drifting from file contents, and facts the repo now records on its own. Most of that staleness is verifiable from the project itself, so verify it yourself first and bring the user only the residue that a human has to answer.

The contract: housekeeping is silent, meaning changes are confirmed. You may fix a broken index line on your own, but you never rewrite, merge, or delete what a memory claims without showing it in the docket and getting a yes.

Arguments

$ARGUMENTS is optional and freeform:

  • A memory type (user, feedback, project, reference) limits the audit to memories of that type. Multiple types may be given.
  • --older-than <N>d only audits memory files whose last modification is more than N days ago (per stat/git log on the file).
  • --dry-run stops after presenting the docket: no questions, no edits, no deletions. (It still writes the docket artifact; see State directory.)
  • schedule sets up a local scheduled job (cron, or launchd on macOS) that runs the dry-run periodically; follow the Schedule mode section instead of steps 1-5.
  • unschedule removes that job; see Schedule mode.

Examples: /garden, /garden project, /garden feedback --older-than 60d, /garden --dry-run, /garden schedule, /garden unschedule.

State directory

The gardener keeps its bookkeeping in ~/.claude/projects/<slug>/garden/ (sibling of the memory/ store, never inside it, so it can't pollute the audit):

  • docket.md: the docket from the most recent audit (written on every run, including dry-runs, so a scheduled headless dry-run leaves its findings behind for a human to read).
  • needs-real-run: marker containing the count of open items (confirmed stale + suspected). Written when that count is > 0, deleted when it is 0.
  • last-real-run: epoch timestamp of the last completed real run.
  • last-nudge, cron.log: used by the SessionStart nudge hook and the cron job respectively.

Read the full file on GitHub · 271 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. 3d ago First seen · 271 lines · 36 tokens per session scan A 7d57e3357b74

Subscribe to this mod's changes

garden is a command published in the GitHub repository cwakim/claude-plugins (2 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 3,354 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.