speak-with-plants

speak-with-plants is a skill for Claude Code, Codex from Hmbown/Wizards-of-the-Ghosts. It costs 82 tokens per session (681 once invoked), scanned A, original, CC0-1.0.

A way to study the structure and history of a codebase, dependency graph, file tree, or data model.

In plain words
What is it for?
Use it to inspect how a project has grown, find neglected areas, and understand relationships between its parts.
Why use it?
It helps expose patterns that are easy to miss when looking at one file or recent events. This gives context before making changes to a mature system.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect how a project has grown, find neglected areas, and understand relationships between its parts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/wizards-of-the-ghosts/speak-with-plants
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.

Any agent
npx skills add Hmbown/Wizards-of-the-Ghosts --skill speak-with-plants
Clone the repo
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts

Made for: Claude Code, Codex.

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 speak-with-plants

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/speak-with-plants/github.svg)](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/speak-with-plants)
Your own site
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/speak-with-plants"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/speak-with-plants/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.

agentmods 80×15 button for speak-with-plants

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/speak-with-plants"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/speak-with-plants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 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 $0.00082 $0.00681
Opus 5 $0.00041 $0.00341
Sonnet 5 $0.00016 $0.00136
Haiku 4.5 $0.00008 $0.00068

Measured 9d ago against content hash 060afdab8eb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

speak-with-plants 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 9d 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.

generated/hermes/investigation-and-preparation/speak-with-plants/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speak with Plants

Read the slow truth hidden in roots, branches, and growth rings.

What This Skill Does

Speak with Plants listens to slow, structural systems: codebases, dependency graphs, file trees, schema histories, and repositories with seasons baked into them. These systems do not bark in alarms; they reveal themselves through branching patterns, accreted layers, and places where nothing has moved in years. The spell helps you hear what the structure has been quietly telling maintainers all along. In this grimoire, Speak with Plants is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Speak with Plants (spell).

When To Use

  • You need to understand a mature codebase, file system, or data model before changing it.
  • The important signals are structural, historical, or layered rather than real-time and noisy.
  • You suspect the answer lies in growth patterns, not isolated incidents.

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Inspect the roots and branches: directory layout, dependencies, schema evolution, ownership clues, and naming patterns.
  3. Interpret what those structures reveal about coupling, neglected areas, and natural extension points.
  4. Return a reading of the system's slow logic, plus where pruning, grafting, or restraint is warranted.
  5. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • A structural interpretation of the codebase or data shape.
  • A list of natural extension points, dead wood, and fragile junctions.
  • A recommendation for where to modify the system with the least long-term stress.

Pitfalls / Guardrails

  • Keep the metaphor anchored to a real mechanism instead of drifting into lore.
  • Do not mistake age or complexity for authority; some old branches should still be cut.
  • Avoid projecting grand narratives from one local structural clue.

Read the full file on GitHub · 66 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. 9d ago First seen · 66 lines · 82 tokens per session scan A 060afdab8eb5

Subscribe to this mod's changes

speak-with-plants is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (107 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 82 tokens to every session and 681 once invoked, about $0.0004 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 2026-09-03.