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 softspark/ai-toolkit --skill brand-voicegit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/brand-voice)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/brand-voice"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/brand-voice.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.02054 |
| Opus 5 | $0.00019 | $0.01027 |
| Sonnet 5 | $0.00008 | $0.00411 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
brand-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 7d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice
Auto-loaded when writing documentation, content, or user-facing text. Enforces consistent, direct voice and eliminates LLM rhetoric.
Also loaded when a project sets output-mode: concise or output-mode: strict in CLAUDE.md, to govern conversational response length and structure (see Output Modes).
Anti-Trope List (Banned Phrases)
Opening Tropes (Never Start With)
- "In today's fast-paced world..."
- "In the ever-evolving landscape of..."
- "Let's dive into..."
- "Let's explore..."
- "Welcome to this comprehensive guide..."
- "Are you looking for...?"
- "Whether you're a beginner or an expert..."
Filler Adjectives (Remove or Replace)
| Banned | Replacement |
|---|---|
| "cutting-edge" | Describe what it does |
| "game-changer" | State the specific impact |
| "revolutionary" | State the concrete improvement |
| "robust" | Describe what makes it reliable |
| "seamless" | Describe the integration mechanism |
| "state-of-the-art" | Cite specific capabilities |
| "leveraging" | "using" |
| "harnessing" | "using" |
| "utilizing" | "using" |
| "delve" / "delve into" | "examine" / "look at" |
| "holistic" | "complete" / "full" |
| "synergy" | Describe the actual interaction |
| "paradigm shift" | Describe the change |
| "best-in-class" | Cite the benchmark or drop it |
| "empower" | Say what it enables |
| "streamline" | Say what step it removes |
| "elevate" | Say what improves and by how much |
| "unlock" | Say what becomes possible |
Closing Tropes (Never End With)
- "Happy coding!"
- "And that's it! You're all set!"
- "I hope this helps!"
- "Feel free to reach out if you have any questions"
- "Now go build something amazing!"
Structural Tropes
- Do not number every single point when prose works better
- Do not use headers for 2-sentence sections
- Do not add a "Conclusion" section that restates the intro
- Do not add "Overview" sections that say nothing the title didn't already say
- Do not pad lists to look longer than they are
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.
- 7d ago First seen · 174 lines · 39 tokens per session scan A 914d2b5afcaa
brand-voice is a skill published in the GitHub repository softspark/ai-toolkit (170 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 2,054 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 2026-08-30.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
opencode-bedrock-doc-blocks
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).