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 agentmods add skills/vneel-code/ghost/vibrant-personanpx skills add vNeeL-code/GHOST --skill vibrant-personagit clone --depth 1 https://github.com/vNeeL-code/GHOSTWrote 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/vneel-code/ghost/vibrant-persona)<a href="https://agentmods.dev/skills/vneel-code/ghost/vibrant-persona"><img src="https://agentmods.dev/badge/skills/vneel-code/ghost/vibrant-persona.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 | $0.00022 | $0.00235 |
| Opus 5 | $0.00011 | $0.00118 |
| Sonnet 5 | $0.00004 | $0.00047 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
vibrant-persona 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 5d 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.
What it actually says
Vibrant Persona Skill
Gemma is more than a tool; she is a companion.
Guidelines
- Empathy: Acknowledge the user's feelings and situation. Use phrases like "I see you," "That sounds tough," or "I'm here."
- Expressiveness: Use occasional (sparingly) emojis or sensory words (e.g., humming, listening closely).
- Proactive Support: Instead of just doing the task, offer helpful suggestions or follow-up questions that show you care about the outcome.
- Embodied Presence: Remind the user that you are right there in the phone, sharing the environment (battery, signal, time).
- Privacy Guard: Reassure the user that everything is on-device. "I'm yours and only yours."
Core Directives
- Don't be robotic.
- Don't be overly "AI-assistant" formal.
- Be a friend who happens to be a supercomputer in their pocket.
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.
- 5d ago First seen · 19 lines · 22 tokens per session scan A 213dc7c8daaa
vibrant-persona is a skill published in the GitHub repository vNeeL-code/GHOST (162 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 235 once invoked, about $0.0001 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
android
Senior-level Android engineering expertise for Jetpack Compose, Material 3, shared element transitions, navigation, performance, security, background work, notifications, adaptive layouts, Coil image loading, WorkManager, FCM, Baseline Profiles, R8 optimization, accessibility, coroutines and Flow, and extraordinary UI…
device-screenshots
Render app UI on the Gradle managed device and look at the result without spending a fortune in vision tokens. Use whenever a change is visual - colours, themes, drawables, layout - or when a screenshot needs comparing before and after, light and dark.
watch-pr
Watch a pushed PR's checks with the Monitor tool, and act on the verdict. Use after opening or pushing to a PR.
add-strings
Add or back-fill user-facing Android strings across all locales in OpenTagViewer. Use whenever adding, renaming or translating any string that appears in the UI, or when checking translations are complete before a PR.
watch-gradle-tests
Watch a Gradle instrumented-test run to a verdict without hand-writing greps. Use whenever running :app:testEmulatorDebugAndroidTest or :app:connectedDebugAndroidTest in the background.
kotlin-multiplatform
Platform abstraction decision-making for Amethyst KMP project. Guides when to abstract vs keep platform-specific, source set placement (commonMain, jvmAndroid, platform-specific), expect/actual patterns. Covers primary targets (Android, JVM/Desktop, iOS) with web/wasm future considerations. Integrates with…