garden-voice

garden-voice is a skill for Claude Code from khou/gardenkit. It costs 92 tokens per session (1,298 once invoked), scanned A, original, MIT.

A writing-style profile built from your own Slack messages and saved as a reusable voice guide. It records patterns such as sentence rhythm, capitalization, and wording, with short redacted examples.

In plain words
What is it for?
Use it to create or refresh a voice profile from Slack messages, then guide future drafts in your style.
Why use it?
It avoids guessing how you write from a vague description. Drafting tasks can use real examples to match your usual tone more closely.

Skill for Claude Code

Written for Claude Code: SessionStart hook event.

Good fit Use it to create or refresh a voice profile from Slack messages, then guide future drafts in your style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/khou/gardenkit/garden-voice
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 khou/gardenkit --skill garden-voice
Clone the repo
git clone --depth 1 https://github.com/khou/gardenkit

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 garden-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/khou/gardenkit/garden-voice.svg)](https://agentmods.dev/skills/khou/gardenkit/garden-voice)
Your own site
<a href="https://agentmods.dev/skills/khou/gardenkit/garden-voice"><img src="https://agentmods.dev/badge/skills/khou/gardenkit/garden-voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,298 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 $0.00092 $0.01298
Opus 5 $0.00046 $0.00649
Sonnet 5 $0.00018 $0.00260
Haiku 4.5 $0.00009 $0.00130

Measured 7d ago against content hash e791bec026ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

garden-voice 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 7d 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.

skills/garden-voice/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

garden-voice

Builds and maintains ~/garden/meta/voice.md: the user's voice profile derived from their own messages. Loaded on-demand by drafting tasks for tone-matching.

Why this exists

Asking a user to describe their writing voice in the abstract gives shallow results. Sampling their actual messages and synthesizing patterns gives the agent a concrete, calibrated reference. Per the source video, having a voice profile is reportedly the single biggest output-quality multiplier for any drafting work.

Modes

init

First-time bootstrap. Sample broadly across the user's recent sent messages.

  1. Find user ID via slack_search_users (use the user's name or email from meta/user.md).
  2. Pull sent messages. Use slack_search_public_and_private with query from:<USER_ID>. Paginate to gather ~500–1000 messages. Skip threads where the only content is reactions or single-emoji replies.
  3. Aggregate text into a single corpus.
  4. Redact (see redaction rules below): strip proper nouns, numbers, URLs, but preserve all linguistic content.
  5. Synthesize patterns: observe and write down:
    • Sentence rhythm (terse / flowing / fragments)
    • Capitalization habits (lowercase casual / sentence case / mixed)
    • Punctuation tics (em-dashes, ellipses, parenthetical asides, trailing ? for soft asks)
    • Vocabulary preferences (favored words, slang, technical register)
    • Emoji and reaction patterns (which, how often, in what positions)
    • Greeting / closing patterns
    • Sentence starters and connector words
    • Tone markers (irony, hedging, directness)
  6. Pick 10–15 anchored examples: short snippets (≤2 sentences each, redacted) that demonstrate the patterns concretely.
  7. Write ~/garden/meta/voice.md per the output format below.
  8. Commit to the vault git repo with message voice: init from <N> Slack messages.

refresh

Periodic update: appends new observations rather than overwriting.

  1. Read existing voice.md to know what patterns are already noted.
  2. Pull last ~200 messages since the file's updated: date.
  3. Diff: any new patterns or notable shifts in style?
  4. Update voice.md: refresh anchored examples (drop oldest, add freshest), append new pattern observations.
  5. Commit with voice: refresh: <summary of changes>.

Read the full file on GitHub · 138 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. 7d ago First seen · 138 lines · 0 tokens per session scan A e791bec026ce

Subscribe to this mod's changes

garden-voice is a skill published in the GitHub repository khou/gardenkit (4 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 1,298 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

ara-research-manager

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…

Orchestra-Research/AI-Research-SKILLs · 91 tokens

loop-engineering

Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.

Mark393295827/third-brain-v7-skills · 35 tokens

harness-engineering

Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.

Mark393295827/third-brain-v7-skills · 34 tokens

agent-teams-command

Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command scaled from 5 to 100+ agents.

Mark393295827/third-brain-v7-skills · 39 tokens

agentic-engineering

Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.

Mark393295827/third-brain-v7-skills · 33 tokens

anthropic-os

Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B creativity, experiments, and prediction-error learning.

Mark393295827/third-brain-v7-skills · 42 tokens