voxy: Skill for Codex

.codex/skills/voxy-dictionary-maintainer/SKILL.md

voxy-dictionary-maintainer is a skill for Codex from hahagood/voxy. It costs 87 tokens per session (843 once invoked), scanned A, original, MIT.

A Voxy-specific tool for maintaining the speech-recognition correction dictionary. Voxy is the application whose history and configuration files it reviews.

In plain words
What is it for?
Use it to inspect Voxy correction history, suggest custom terms, merge confirmed mappings into the configuration, and prune unwanted entries.
Why use it?
It helps turn repeated corrections into reusable terms and identify conflicts, stale entries, or noisy mappings.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

This is hahagood/voxy's own configuration. It tells Codex how to work on voxy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything voxy configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python contrib/extract_custom_terms.py --min-count 2.

Reuse

Borrowing it

Nothing to install: this file belongs to hahagood/voxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hahagood/voxy/main/.codex/skills/voxy-dictionary-maintainer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hahagood/voxy

Made for: 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 voxy-dictionary-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/hahagood/voxy/voxy-dictionary-maintainer/github.svg)](https://agentmods.dev/skills/hahagood/voxy/voxy-dictionary-maintainer)
Your own site
<a href="https://agentmods.dev/skills/hahagood/voxy/voxy-dictionary-maintainer"><img src="https://agentmods.dev/badge/skills/hahagood/voxy/voxy-dictionary-maintainer/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 voxy-dictionary-maintainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/hahagood/voxy/voxy-dictionary-maintainer"><img src="https://agentmods.dev/badge/skills/hahagood/voxy/voxy-dictionary-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 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 $0.00087 $0.00843
Opus 5 $0.00044 $0.00421
Sonnet 5 $0.00017 $0.00169
Haiku 4.5 $0.00009 $0.00084

Measured 10d ago against content hash ded874932450, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

voxy-dictionary-maintainer 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/review_terms.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/voxy-dictionary-maintainer/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voxy Dictionary Maintainer

Use this skill for Voxy-specific dictionary maintenance, not for general text cleanup.

When To Use

Trigger this skill when the user asks to:

  • inspect or summarize ~/.local/share/voxy/history.json
  • extract new llm.custom_terms candidates
  • merge confirmed mappings into ~/.config/voxy/config.toml
  • review conflicts, stale mappings, or noisy dictionary entries
  • derive a reusable correction dictionary from repeated raw / polished pairs

Files To Check First

Read only what is needed:

  1. ~/.local/share/voxy/history.json
  2. ~/.config/voxy/config.toml
  3. contrib/extract_custom_terms.py

Use scripts/review_terms.py for a deterministic first pass before making manual decisions.

Workflow

1. Collect current state

  • Confirm that history.json exists and estimate its record count.
  • Read the current [llm.custom_terms] table from config.toml.
  • If the user wants repo-facing changes, also inspect README.md and config.example.toml.

2. Generate candidate mappings

Run:

python .codex/skills/voxy-dictionary-maintainer/scripts/review_terms.py --min-count 2

This script compares extracted candidates against the current dictionary and separates:

  • new_candidates
  • existing_matches
  • conflicts

If the history is small or the user wants a broader sweep, lower --min-count to 1. Prefer 2+ for anything you intend to merge.

3. Manually filter candidates

Prefer entries that are stable across contexts:

  • product names: OpenRouter, Ollama, Anthropic
  • project names: TS-GPT
  • tools and files: GitHub, Notion, README.md
  • technical terms: token, OpenAI, iOS

Reject or review carefully:

  • summary-like rewrites
  • punctuation-only changes
  • phrase rewrites that depend on sentence context
  • partial fragments that are not valid standalone terms

If a candidate conflicts with an existing mapping, do not overwrite it automatically. Show the conflict and explain why one side should win.

Read the full file on GitHub · 118 lines

Files

What ships with it

3 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. 10d ago First seen · 118 lines · 87 tokens per session scan A ded874932450

Subscribe to this mod's changes

voxy-dictionary-maintainer is a skill published in the GitHub repository hahagood/voxy (23 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 843 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens