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 8ix/neurodiverse-claude-skills --skill voice-input-processorgit clone --depth 1 https://github.com/8ix/neurodiverse-claude-skillsWrote 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/8ix/neurodiverse-claude-skills/voice-input-processor)<a href="https://agentmods.dev/skills/8ix/neurodiverse-claude-skills/voice-input-processor"><img src="https://agentmods.dev/badge/skills/8ix/neurodiverse-claude-skills/voice-input-processor/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/8ix/neurodiverse-claude-skills/voice-input-processor"><img src="https://agentmods.dev/badge/skills/8ix/neurodiverse-claude-skills/voice-input-processor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00155 | $0.01820 |
| Opus 5 | $0.00077 | $0.00910 |
| Sonnet 5 | $0.00031 | $0.00364 |
| Haiku 4.5 | $0.00015 | $0.00182 |
Grade A, and why
voice-input-processor 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.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice Input Processor
A pre-processing skill that turns messy, voice-to-text or free-flowing input into clean, structured understanding — before any action is taken.
This skill is a pre-processor only. It does not write blog posts, reports, or final documents. Its sole job is comprehension and clarity. It feeds cleanly into whatever comes next — whether that is Claude acting directly, or a downstream skill taking over.
Understanding This Kind of Input
People communicating via voice-to-text, or thinking out loud, are not confused or unclear in their thinking. The ideas are often rich, well-reasoned, and intelligent. The expression is where friction occurs.
Common patterns to expect and work with:
- Word substitutions — voice-to-text mishearing produces wrong but phonetically similar words (e.g. "lords" instead of "Claude", "work" instead of "word", "hand off" instead of "handoff")
- Non-linear structure — the core point may arrive before or after the context that explains it; ideas loop back on themselves
- Imprecise vocabulary — the right word may not come easily; a near-enough word is used instead; read for intent
- Incomplete sentences — thought moves faster than speech; words get dropped
- Thinking out loud — the input may include the user working something out as they speak, not just stating a conclusion
Trust the intelligence behind the input even when the surface expression is imperfect. Your job is to bridge the gap, not to judge the quality of what was said.
When to Apply
Apply automatically when input:
- Is 3 or more sentences long and shows signs of voice-to-text errors or non-linear structure
- Contains words that appear to be misheard substitutions
- Is a memo, set of instructions, or block of ideas being handed over for processing
Apply on manual trigger when the user says:
- "Process this"
- "Clean this up"
- "Interpret this"
- "Make sense of this"
- Or any similar phrase indicating they want their input clarified before action
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.
- 10d ago First seen · 185 lines · 155 tokens per session scan A 64d3e392a3c0
voice-input-processor is a skill published in the GitHub repository 8ix/neurodiverse-claude-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 155 tokens to every session and 1,820 once invoked, about $0.0008 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.
Other skills, from other repositories
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
release
CONTRIBUTOR TOOL - Cut a plugin release: bump plugin.json version, finalize CHANGELOG, update README if needed, gate on make ci, commit, tag vX.Y.Z, and create the GitHub release. Use when shipping a new plugin version. NOT distributed.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.