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.
npx skills add flonat/flonat-research --skill voice-editorgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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.
[](https://agentmods.dev/skills/flonat/flonat-research/voice-editor)<a href="https://agentmods.dev/skills/flonat/flonat-research/voice-editor"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/voice-editor/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.
<a href="https://agentmods.dev/skills/flonat/flonat-research/voice-editor"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/voice-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01938 |
| Opus 5 | $0.00028 | $0.00969 |
| Sonnet 5 | $0.00011 | $0.00388 |
| Haiku 4.5 | $0.00006 | $0.00194 |
Grade A, and why
voice-editor 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Editor: Transform Content to Match Your Voice
Transform generic or auto-generated content into voice-matched writing using a VOICE.md profile. Voice doesn't live in first drafts — it lives in editing choices. This skill guides the multi-pass editing process that turns generic output into something distinctively yours.
Quick Start
Provide:
- Content to edit (paste or file path)
- VOICE.md location (default:
.context/voice/voice.mdor project's.context/voice/voice.md)
The skill will:
- Run slop detection on the content
- Identify voice mismatches against your profile
- Perform multi-pass editing (Structure > Voice > Polish)
- Output edited content with change annotations
- Suggest VOICE.md updates based on patterns found
The 30-40% Rule
Even with a perfect style guide, expect to edit 30-40% of AI output to make it distinctively yours. This isn't a problem — it's the feature.
30-40% editing effort is dramatically less than 100% writing-from-scratch effort, while producing work that sounds more like you than unguided AI ever could.
If you're editing more than 50%: Your style guide needs refinement, or your prompts need work.
If you're editing less than 20%: You might be accepting too much generic content.
Editing Modes
See references/editing-modes.md for mode selection (light, standard, heavy, rescue) and expected effort per mode.
Editing Workflow
Pass 1: Structure Check
Focus: Does the organization serve the content?
Questions to ask:
- Does the opening hook or just clear throat?
- Is there a clear progression of ideas?
- Does each section earn its place?
- Is anything redundant or missing?
- Does the conclusion land or just stop?
Actions:
- Cut throat-clearing openings ("In this article, we'll explore...")
- Reorder sections for better flow
- Merge redundant sections
- Add missing transitions
- Strengthen weak conclusions
Academic mode: Skip opening mechanics checks for papers — academic openings follow different conventions (context-gap-contribution is standard, not a flaw). Focus on logical flow between sections instead.
What ships with it
2 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.
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.
- 8d ago First seen · 268 lines · 55 tokens per session scan A d74dc920c163
voice-editor is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 1,938 once invoked, about $0.0003 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.
Other skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
fin-paper-plan
Generate structured paper outline adapted to target journal.
doc-audit
Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
claim-audit
Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.