gardener

A monthly audit tool for catalogues of coding-agent skills and agents. It checks what is listed, scores descriptions, finds similar entries, groups them by topic, and compares results with the previous audit.

In plain words
What is it for?
Use it to review marketplace contents, score skills against a shared rubric, find duplicate or confusing entries, and produce a report of changes. It suggests fixes but does not write them into skill files.
Why use it?
It helps maintain a catalogue without manually reviewing every entry. It also highlights overlapping descriptions and changes that may need attention.

Skill for Claude CodeCodex

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 skills/theagenticguy/agentic-plugins/gardener
Any agent
npx skills add theagenticguy/agentic-plugins --skill gardener
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/agentic-plugins

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 976 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 $0.00105 $0.00976
Opus 5 $0.00053 $0.00488
Sonnet 5 $0.00021 $0.00195
Haiku 4.5 $0.00011 $0.00098

Measured 2d ago against content hash 80cfbaedfa18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gardener 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 2d 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/plugin-gardener/skills/gardener/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contents

Reference When to load
references/orchestrator.md Running /gardener — the 4-phase flow
../../references/rubric.md Scoring dimensions (shared)
../../references/write-protocol.md Copied verbatim into every Agent prompt
templates/inventory-skeleton.md Inventory output file
templates/scorecard-skeleton.md Per-skill scorecard output file
templates/collisions-skeleton.md Collisions output file
templates/clusters-skeleton.md HDBSCAN taxonomy output file
templates/report-skeleton.md Final audit report

Gardener

Monthly catalog hygiene. Orchestrator runs inside a forked subagent. Walks every skill and agent across the marketplace, scores them in parallel, detects collisions via Bedrock Cohere v4 embeddings, runs an HDBSCAN taxonomy check, and composes a delta report against the prior audit. Proceeds autonomously — planning is reversible. Gates only at the point of writing fixes back to SKILL.md files, which it does not do: it proposes.

How it works

Read references/orchestrator.md and follow its phases. Short version:

  1. Inventory — walk the marketplace, extract frontmatter and file stats, write audit/YYYY-MM/inventory.md.
  2. Collide — run scripts/embed-catalog.py once (Bedrock Cohere v4), then scripts/pairwise-collisions.py and scripts/cluster-taxonomy.py. One interpreter Agent opens the flagged SKILL.md files, verifies the collisions by reading, and writes audit/YYYY-MM/collisions.md + audit/YYYY-MM/clusters.md with recommended actions.
  3. Score — launch one parallel Opus Agent per skill. Each Agent reads the skill's SKILL.md, references/, and templates/ in full, applies the shared rubric, and cites file:line evidence in every rationale. Collision and cluster data from Phase 2 are passed in as cross-reference context — where to look, not substitute for reading.
  4. Report — one foreground critic Agent reads inventory + all scorecards + collisions + clusters + the prior month's report, writes audit/YYYY-MM/report.md with health score, delta, quarantine list, and top-5 action items.

Read the full file on GitHub · 77 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 77 lines · 105 tokens per session scan A 80cfbaedfa18

Subscribe to this mod's changes

gardener is a skill published in the GitHub repository theagenticguy/agentic-plugins (5 stars, last pushed 21d ago), licensed MIT. It adds 105 tokens to every session and 976 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

genesis

Use this skill BEFORE drafting any agentic primitive module (skill, persona scoping file, scope-attached rule file, orchestrator workflow) or when refactoring an existing one. Activate whenever the task asks to design, restructure, or critique an agentic module across any agent harness (Claude Code, Copilot, Cursor…

danielmeppiel/genesis · 169 tokens

agents

Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.

itaywol/adeptability · 5 tokens

using-adept

Use the adept CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.

itaywol/adeptability · 54 tokens

authoring-adept-agents

Write a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running adept agent add.

itaywol/adeptability · 47 tokens

authoring-adept-loops

Compose a loop — a scheduled system that discovers work, hands it to agents, verifies with an independent evaluator, persists state, and reschedules itself. Apply when the user wants automation that runs on a timer, a triage/babysitter routine, or asks about adept loop add.

itaywol/adeptability · 60 tokens

authoring-adept-skills

Write a good, portable adept skill: pick the right activation, craft a triggering description, keep it scan-safe and within harness byte budgets. Apply when creating or editing a SKILL.md or running adept skill add.

itaywol/adeptability · 45 tokens