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 dbhq-uk/verve-skill --skill vervegit clone --depth 1 https://github.com/dbhq-uk/verve-skillWrote 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/dbhq-uk/verve-skill/verve)<a href="https://agentmods.dev/skills/dbhq-uk/verve-skill/verve"><img src="https://agentmods.dev/badge/skills/dbhq-uk/verve-skill/verve/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/dbhq-uk/verve-skill/verve"><img src="https://agentmods.dev/badge/skills/dbhq-uk/verve-skill/verve.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 | $0.00190 | $0.02926 |
| Opus 5 | $0.00095 | $0.01463 |
| Sonnet 5 | $0.00038 | $0.00585 |
| Haiku 4.5 | $0.00019 | $0.00293 |
Grade A, and why
verve 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 today.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verve
Cut the AI tells from a piece of writing, then put a voice back into it, without changing what it says. British English by default, American on request or when the source is already American.
Both halves matter. Text with the tells stripped but no voice left reads as machine-made too, just blandly rather than floridly.
Prerequisites
None. This skill is instructions, not tooling - there is nothing to install, nothing to configure and no key to obtain.
Usage
Text comes from the message, a file, or the clipboard. Options are natural language.
- Inline: "verve this: [text]"
- File: "verve draft.md"
- Clipboard: "verve my clipboard"
| Option | Values | Default |
|---|---|---|
| Tone | neutral, casual, professional, academic | neutral |
| Strength | light, moderate, heavy | moderate |
| Variety | British, American | match the source, else British |
| Audience | who it is for, in plain words | infer from the text, else assume competence |
| Explain | "explain what you changed" | off |
| Output | conversation, "save to [file]" | conversation |
Examples: "verve draft.md in a casual tone", "verve essay.md heavily and explain what you changed", "verve report.md and save to final.md", "verve this in US English", "verve this for our CTO".
Set any of these once instead of repeating them, in .verve.md or a ## Verve
section of CLAUDE.md, alongside terms verve must never change. The defaults in
that table apply when nothing is saved. See references/preferences.md.
Hard constraints (never violate)
These outrank every other instruction in this skill. A rewrite that breaks one of them has failed, however good it reads.
- Every fact, number, name, date and citation survives unchanged. For a date that means its value, the day and month and year; the written format may follow the variety, but never becomes all-numeric, which is ambiguous. Nothing else in this list has a format exception.
- Technical terms keep their exact wording. No synonym swaps.
- Never invent statistics, examples, quotes, sources or credentials.
- The argument keeps its logical structure and its claims. Cutting filler is the job; cutting content is not.
- Any illustrative example you add is labelled hypothetical.
- If a change would alter meaning, stop and ask instead of applying it.
What ships with it
8 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.
- today Changed · +25 lines 50d3de9cb5e4
- 3d ago Changed · +57 lines · +78 tokens per session de913108a89c
- 9d ago First seen · 147 lines · 112 tokens per session scan A e5b46dbd834a
verve is a skill published in the GitHub repository dbhq-uk/verve-skill (4 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 2,926 once invoked, about $0.0010 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
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.