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 agentmods add commands/cwakim/claude-plugins/gardengit clone --depth 1 https://github.com/cwakim/claude-pluginsWrote 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/commands/cwakim/claude-plugins/garden)<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>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 | $0.00036 | $0.03354 |
| Opus 5 | $0.00018 | $0.01677 |
| Sonnet 5 | $0.00007 | $0.00671 |
| Haiku 4.5 | $0.00004 | $0.00335 |
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.
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>donly audits memory files whose last modification is more than N days ago (perstat/git logon the file).--dry-runstops after presenting the docket: no questions, no edits, no deletions. (It still writes the docket artifact; see State directory.)schedulesets 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.unscheduleremoves 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.
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.
- 3d ago First seen · 271 lines · 36 tokens per session scan A 7d57e3357b74
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.