augment

augment is a skill for Claude Code from terrylica/cc-skills. It costs 32 tokens per session (681 once invoked), scanned A, original, MIT.

An upgrade procedure for the Kokoro text-to-speech engine, which turns written text into spoken audio. It updates its Python packages, model files, bundled scripts, and recorded version information, then checks that synthesis still works.

In plain words
What is it for?
Use it when upgrading Kokoro's dependencies or speech model and checking that the local text-to-speech setup remains usable.
Why use it?
It provides a defined way to update the speech engine and verify the installation afterward.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Part of the kokoro-tts plugin — 5 skills shipped together , and of cc-skills

Good fit Use it when upgrading Kokoro's dependencies or speech model and checking that the local text-to-speech setup remains usable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrylica/cc-skills/augment
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 terrylica/cc-skills --skill augment
Clone the repo
git clone --depth 1 https://github.com/terrylica/cc-skills

Made for: Claude Code.

Or install kokoro-tts, the plugin that ships this one along with the rest of its 5 skills.

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 augment

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/augment.svg)](https://agentmods.dev/skills/terrylica/cc-skills/augment)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/augment"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/augment.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00032 $0.00681
Opus 5 $0.00016 $0.00341
Sonnet 5 $0.00006 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash 4161664e0f01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

augment 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/kokoro-tts/skills/augment/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Augment Kokoro TTS

Upgrade MLX-Audio dependencies, re-download the model, and update bundled scripts.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Workflow

Step 1: Pre-upgrade health check

ROOT="$(cc-plugin-root kokoro-tts)"
bash "$ROOT/scripts/kokoro-install.sh" --health
cat ~/.local/share/kokoro/version.json

Step 2: Execute upgrade

ROOT="$(cc-plugin-root kokoro-tts)"
bash "$ROOT/scripts/kokoro-install.sh" --upgrade

This upgrades:

  • Python packages: mlx-audio, soundfile, numpy
  • Model weights: re-downloaded from mlx-community/Kokoro-82M-bf16
  • Bundled scripts: kokoro_common.py and tts_generate.py re-copied from plugin
  • version.json: rewritten with new versions

Step 3: Post-upgrade verification

ROOT="$(cc-plugin-root kokoro-tts)"
bash "$ROOT/scripts/kokoro-install.sh" --health
cat ~/.local/share/kokoro/version.json

# Test synthesis
~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
  --text "Upgrade verification" --voice af_heart --lang en-us --speed 1.0 \
  --output /tmp/kokoro-upgrade-test.wav && echo "OK"

Rollback

If upgrade breaks TTS, do a clean reinstall:

ROOT="$(cc-plugin-root kokoro-tts)"
bash "$ROOT/scripts/kokoro-install.sh" --uninstall
bash "$ROOT/scripts/kokoro-install.sh" --install

Model cache is preserved across uninstall, so reinstall reuses the cached model.

Troubleshooting

Issue Cause Solution
Upgrade fails No internet or PyPI down Check connectivity, retry
Import error after mlx-audio incompatibility Clean reinstall: --uninstall then --install
Model download slow Large download Wait for HuggingFace download to complete

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 32 tokens per session scan A 4161664e0f01

Subscribe to this mod's changes

augment is a skill published in the GitHub repository terrylica/cc-skills (62 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 681 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 2026-09-05.

Related

Other skills, from other repositories