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 bjorn-ingmanson/thefroject-plugins --skill extract-my-voicegit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/extract-my-voice)<a href="https://agentmods.dev/skills/bjorn-ingmanson/thefroject-plugins/extract-my-voice"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/extract-my-voice/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/bjorn-ingmanson/thefroject-plugins/extract-my-voice"><img src="https://agentmods.dev/badge/skills/bjorn-ingmanson/thefroject-plugins/extract-my-voice.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 | $0.00037 | $0.00602 |
| Opus 5 | $0.00018 | $0.00301 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
extract-my-voice 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract My Voice
Analyze the user's actual writing across connected sources and create a voice reference file that Claude can use to match their tone and style.
Sources (check in order, use what's available)
- Slack: Search for messages by the user. Read across multiple channels. Minimum 50 messages for a useful analysis.
- Gmail: Read sent emails. Look for variety: different recipients, different purposes, different levels of formality.
- Notion/Docs: Read authored pages and documents. Look for longer-form writing.
- Provided samples: If no sources are connected, ask the user to paste 3-5 examples of their writing. Different formats if possible (email, post, doc, message).
Analysis
For each source, identify:
- Default tone: where do they sit on formal/casual, warm/neutral, confident/tentative
- Sentence rhythm: short/long, varied/consistent, fragments or full sentences
- Openings and closings: how they start and end emails, messages, documents
- Formatting preferences: bullets vs prose, headers vs flat text, emoji usage
- Vocabulary fingerprint: words they reach for, words they consistently avoid
- Register shifts: how does tone change by audience, channel, or format?
- Paragraph structure: length, density, how they break up ideas
If the user writes in multiple languages, analyze each language separately. Voice often changes significantly between languages.
Output
Create context/my-voice.md with:
- A prose description of their voice (not a list of rules, a description that reads naturally)
- 3-5 short quoted examples that capture the style, pulled from actual writing
- A "do / don't" section with specific guidance for Claude:
- Words and phrases to use
- Words and phrases to avoid
- Formatting rules (line length, list style, emoji policy)
- Tone rules by context (emails vs posts vs docs)
- Separate sections per language if they write in multiple languages
After saving
Tell the user: "I'll use this file as reference whenever you ask me to write something. If I drift from your voice, tell me and I'll update the file."
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.
- 12d ago First seen · 55 lines · 37 tokens per session scan A 0362b49077f7
extract-my-voice is a skill published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 602 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…