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-analyzergit 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-analyzer)<a href="https://agentmods.dev/skills/flonat/flonat-research/voice-analyzer"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/voice-analyzer/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-analyzer"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/voice-analyzer.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 | $0.00050 | $0.02047 |
| Opus 5 | $0.00025 | $0.01024 |
| Sonnet 5 | $0.00010 | $0.00409 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
voice-analyzer 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Analyzer: Create a Voice Profile from Writing Samples
Extract voice patterns from writing samples and generate a comprehensive, portable style guide (VOICE.md). The output becomes infrastructure — a reference document used every time you work with AI to maintain your authentic voice instead of producing generic content.
Quick Start
Provide 3-5 writing samples where your voice feels strongest (500-2000 words each). The skill will:
- Analyze patterns across all samples
- Identify your distinctive voice markers
- Generate a VOICE.md style guide
- Create a forbidden phrases list specific to your anti-patterns
- Provide testing prompts to validate the guide
Ideal samples: Published papers, proposals, emails you're proud of, blog posts, referee responses, teaching materials
Avoid: Heavily edited collaborative pieces, boilerplate text, anything that felt forced
Sample Gathering Guidance
What Makes Good Samples
Include samples that:
- You wrote when feeling confident and natural
- Received feedback like "this sounds just like you"
- You'd be happy to write again
- Show your voice across different contexts (casual, professional, explanatory)
- Are at least 500 words (longer is better for pattern detection)
Avoid samples that:
- Were heavily edited by others
- Feel generic or corporate even to you
- Were written under heavy constraints
- Don't represent how you want to sound going forward
Minimum Requirements
- Minimum: 3 samples, 500+ words each
- Ideal: 5-7 samples, 1000+ words each
- Advanced: 10+ samples including different formats (email, long-form, paper sections)
More samples = more accurate pattern detection, but diminishing returns after 10.
Academic Sample Sources
If you're building an academic voice profile:
- Paper drafts — introduction and discussion sections show the most voice
- Referee responses — often reveal how you argue and handle criticism
- Proposals and abstracts — show how you frame contributions
- Teaching materials — lecture notes, assignment descriptions
- Emails to collaborators — longer substantive emails, not one-liners
- Blog posts or public writing — if you have any
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 · 290 lines · 50 tokens per session scan A 430587932c6b
voice-analyzer is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 50 tokens to every session and 2,047 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.