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 mphinance/alpha-skills --skill mph-voice-refreshgit clone --depth 1 https://github.com/mphinance/alpha-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/mphinance/alpha-skills/mph-voice-refresh)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/mph-voice-refresh"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/mph-voice-refresh/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/mphinance/alpha-skills/mph-voice-refresh"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/mph-voice-refresh.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 | $0.00078 | $0.00914 |
| Opus 5 | $0.00039 | $0.00457 |
| Sonnet 5 | $0.00016 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
mph-voice-refresh 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MPH Voice Refresh
Keeps the VOICE.md corpus alive. Without this, the writer keeps reusing the same "Michael impersonations" until they sound canned.
When to invoke
- User asks to refresh / update / mine the voice corpus
- User says drafts are "sounding the same" or "you keep using that phrase"
- It's been more than ~3 weeks since last refresh (check the date at the bottom of VOICE.md)
Two sources, two miners
| Source | Script | What it captures |
|---|---|---|
Chat transcripts (~/.claude/projects/*/*.jsonl) |
scripts/mine_voice.py |
Unfiltered, conversational — tics like .., lol, or whatever, Ugh., mid-sentence self-corrections. The way Michael actually types. |
Substack RSS feed (mphinance.substack.com/feed) |
scripts/mine_feed.py |
Polished, published — paired openers, contradiction-filter constructions, punchy closers. The way Michael writes for readers. |
Both write to the same VOICE.md, but into separate sections. Don't mix them — chat voice has tics that don't belong in a Substack draft, and published voice has constructions that would sound forced in chat.
Flow
-
Read current state. Read VOICE.md so you know what's already in the corpus and what's already retired.
-
Run the relevant miner.
- For chat voice refresh (most common — run every few weeks):
python skills/mph-voice-refresh/scripts/mine_voice.py --days 30 - For published voice refresh (run after Michael ships a new Substack post):
python skills/mph-voice-refresh/scripts/mine_feed.py --limit 8 - Run both back-to-back if it's been a while.
- For chat voice refresh (most common — run every few weeks):
-
Review with Michael. Show the candidate lists. Do NOT auto-apply. Ask which additions to keep and which retirements to confirm. Voice is subjective; the miner is a candidate generator, not the authority.
-
Apply approved changes. Append confirmed additions to the appropriate section of VOICE.md:
- Chat candidates → "Idioms & tics" / "Sentence rhythms" / "Long-form examples"
- Feed openers/closers → "Published voice — Substack patterns"
- Confirmed Claude repeats →
RETIRED - Update the "Last refreshed" date at the bottom.
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.
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.
- 9d ago First seen · 62 lines · 78 tokens per session scan A 621653c2c2cc
mph-voice-refresh is a skill published in the GitHub repository mphinance/alpha-skills (21 stars, last pushed 11d ago), licensed MIT. It adds 78 tokens to every session and 914 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…