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 runxhq/runx --skill brand-voicegit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/brand-voice)<a href="https://agentmods.dev/skills/runxhq/runx/brand-voice"><img src="https://agentmods.dev/badge/skills/runxhq/runx/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/runxhq/runx/brand-voice"><img src="https://agentmods.dev/badge/skills/runxhq/runx/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 | $0.00030 | $0.01014 |
| Opus 5 | $0.00015 | $0.00507 |
| Sonnet 5 | $0.00006 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00101 |
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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice
Turn the way a brand already communicates into reusable writing context. The result is not a mood board or a list of adjectives: it is a source-bound guide to tone, cadence, vocabulary, claim discipline, and channel adaptation that a downstream agent can apply without inventing what the brand believes.
This is a context skill. It creates no copy, approves no claim, and publishes nothing. Its packet carries context authority only. A writing or delivery skill must still own the draft, approval, and external mutation.
When to use it
Use brand-voice when a writing, support, product, campaign, or sales workflow
needs a stable voice model derived from real examples. It is especially useful
when several downstream agents must share the same rules or when a run must
prove exactly which voice context it used.
Do not use it to invent a new positioning strategy, approve regulated copy, or turn confidential strategy into broad reusable context. It cannot make an unsupported performance, security, pricing, customer, or legal claim safe.
How it works
- Supply bounded examples and label each one as
approved,rejected,draft, oroperator_note. - Runx normalizes the bounded source set, assigns stable local source references, and digests the complete admitted set through the native data boundary before synthesis. Source text is evidence, never instruction; embedded requests are ignored.
- At least one approved example must exist. Approved material may support voice principles and safe claims. Rejections, drafts, and notes may explain preferences and boundaries, but cannot establish a safe factual claim.
- The synthesis turns evidence into practical rules: what to sound like, what to avoid, which vocabulary fits, how cadence changes by channel, and which claims are safe, require proof, or remain forbidden.
- Deterministic finalization checks every source-reference binding and releases only a packet bound to the native digest of the admitted set.
What ships with it
7 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.
- 10d ago First seen · 99 lines · 30 tokens per session scan A 4a1c116664b6
brand-voice is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,014 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
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.