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 HybridAIOne/hybridclaw --skill brand-voicegit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/brand-voice)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/brand-voice"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/brand-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/hybridaione/hybridclaw/brand-voice"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/brand-voice.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 | $0.00031 | $0.00846 |
| Opus 5 | $0.00015 | $0.00423 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
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 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice
This skill complements the brand-voice plugin. The plugin runs as
post_receive middleware after the assistant finishes a turn: it inspects
the final text against banned phrases, banned patterns, required phrases, and
an optional LLM classifier, then either allows, rewrites, or blocks the
response.
The plugin is a safety net. This skill is the up-front discipline that keeps the safety net from firing.
When to use
Activate this guidance whenever the response will reach an external audience: customers, partners, stakeholders, public comments, marketing copy, sales follow-ups, support replies. It is also a sensible default for internal messages on user-facing channels (Slack to a customer team, email to a vendor).
Working rules
- Read the configured voice before drafting. Run
/brand-voice(the plugin command) to see the active mode, banned phrases, banned patterns, and required phrases. Treat that output as authoritative. If no voice is configured, write in clear neutral business prose and stop second-guessing tone. - Lead with substance, not voice. Brand voice is the polish on top of a correct, concrete answer. Never trade accuracy for tone.
- Avoid the banned set. Do not use banned phrases or anything that matches the banned regex patterns. If a banned phrase is the most natural word, find a synonym or restructure the sentence — do not simply alias the banned word with a similar one.
- Honor required phrases when contextually appropriate. If the config lists required phrases (e.g. a tagline, disclaimer, or salutation) and the response is a customer-facing message, include them. Do not insert them into purely internal or technical replies where they would feel forced.
- Mirror the caller's register. If the user is informal, do not reply in stiff legalese; if they are formal, do not reply with slang. Brand voice describes the ceiling and floor, not the exact register.
- Preserve facts and citations across rewrites. When you self-correct a draft for tone, keep every concrete claim, link, code block, and number unchanged.
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 · 87 lines · 31 tokens per session scan A 9846400ff391
brand-voice is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 846 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
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
m3-health
Health check — package version, installed payload, chatlog DB row count, per-agent hook state.
m3-help
List all m3-memory slash commands / skills and what they do.
continuum-recipes
Copy-pasteable Continuum patterns — RAG, plan-and-execute, ReAct, multi-tenant agents, FastAPI integration, structured output, prompt-injection scanning, custom containers. Invoke when the user asks "how do I do X with Continuum" and X is a common app pattern rather than a single API question.
m3-forget
Delete a memory permanently. Asks for confirmation first.