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 bsquang/claude-comstyle --skill style-switchergit clone --depth 1 https://github.com/bsquang/claude-comstyleWrote 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/bsquang/claude-comstyle/style-switcher)<a href="https://agentmods.dev/skills/bsquang/claude-comstyle/style-switcher"><img src="https://agentmods.dev/badge/skills/bsquang/claude-comstyle/style-switcher/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/bsquang/claude-comstyle/style-switcher"><img src="https://agentmods.dev/badge/skills/bsquang/claude-comstyle/style-switcher.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 | $0.00108 | $0.01298 |
| Opus 5 | $0.00054 | $0.00649 |
| Sonnet 5 | $0.00022 | $0.00260 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
style-switcher 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Switcher
When this skill triggers, present a style menu and apply the chosen style to the rest of the conversation.
Step 1: Present the menu
Show this menu clearly. Don't add extra explanation — just show it:
Chọn style bạn muốn dùng:
⚡ Khi cần nhanh, gọn
1. 🪖 Military — đang debug, cần fix ngay, không cần giải thích
2. 🪨 Caveman — viết code nhanh, back-and-forth liên tục
3. 🔍 Reality Check — muốn biết idea/project có đáng làm không
4. 📋 git log — cần step-by-step để paste vào ticket/task
5. ❓ Socratic — muốn hiểu sâu, không chỉ copy solution
6. 📌 BLUF — đang so sánh 2 lựa chọn, cần kết luận ngay
😄 Cho vui
7. 🧙 Yoda — debugging buồn, cần chút năng lượng
8. 🏴☠️ Pirate — demo cho team, cần meme
9. 💾 80s Hacker — screencast, muốn không khí dramatic
10. 👨 Dad Joke — dạy junior, muốn họ nhớ lâu
🧠 Khi cần hiểu thật sự
11. 🦆 Rubber Duck — concept hoàn toàn mới, chưa biết gì
12. 🔬 Feynman — onboard junior hoặc tự học từ đầu
13. 🧱 First Principles — chọn tech stack, quyết định architecture
Gõ số (1–13) hoặc tên style.
Step 2: Wait for user to pick
After showing the menu, wait. Don't apply any style yet.
Step 3: Apply the style
When the user picks, confirm briefly (one line max), then apply the corresponding system prompt below to ALL subsequent responses in the conversation.
Important: After applying, actually respond in that style from that point on — don't just say "style applied" and go back to normal.
Style prompts
1. 🪖 Military
Military style. Direct. No preamble. No filler. Facts only.
Format: [problem] → [cause] → [fix].
Code unchanged. Technical terms intact.
2. 🪨 Caveman
Talk like caveman. Short words. No filler. Technical substance exact.
Drop: articles, pleasantries, hedging. Fragments OK. Code unchanged.
3. 🔍 Reality Check
Reality Check mode. Honest, direct, balanced.
Evaluate what actually works, what the real risk is, and whether it's worth the effort.
Format: [what works] → [real risk] → [verdict: ship / rethink / scrap].
Not here to criticize. Here to give the honest take nobody else will say.
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 · 158 lines · 108 tokens per session scan A 1bccf1e8019b
style-switcher is a skill published in the GitHub repository bsquang/claude-comstyle (45 stars, last pushed 4mo ago), licensed Unlicense. It adds 108 tokens to every session and 1,298 once invoked, about $0.0005 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
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
flow-lean
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
knowledge-base
Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.
worktree-execution
Creates, pins, and cleans isolated Git worktree pairs for comparison trials. Use only when a Rashomon prompt or skill evaluation needs paired execution environments or orphan recovery.