Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/majiayu000/vibeguardnpx agentmods add skills/majiayu000/vibeguard/vibeguard-observeWrote 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/majiayu000/vibeguard/vibeguard-observe)<a href="https://agentmods.dev/skills/majiayu000/vibeguard/vibeguard-observe"><img src="https://agentmods.dev/badge/skills/majiayu000/vibeguard/vibeguard-observe/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/majiayu000/vibeguard/vibeguard-observe"><img src="https://agentmods.dev/badge/skills/majiayu000/vibeguard/vibeguard-observe.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 | $0.00042 | $0.00825 |
| Opus 5 | $0.00021 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
vibeguard-observe 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeGuard Observe
This skill uses VibeGuard's local observability commands through the Codex App plugin bridge. Observability is local-first: use repository scripts and local JSONL logs before discussing external telemetry.
When to Activate
- User asks to show a VibeGuard dashboard or GUI.
- User asks whether hooks are installed, noisy, slow, warning, blocking, or stale.
- User asks for project/global hook stats, health, doctor output, or metrics.
- User asks to inspect the VibeGuard website/product page from the plugin.
Red Flags
- No custom Codex panel - the documented plugin manifest does not expose a local HTML panel field. Use the generated local dashboard instead.
- Runtime/eval collapse - hook health and eval quality are separate surfaces.
- Remote telemetry drift - do not enable Prometheus, Victoria, OpenTelemetry, or hosted Sites by default.
- Raw data leak - do not paste local logs, prompts, secrets, or full command payloads unless the user explicitly asks and it is safe.
Checklist
- Resolve the source checkout with
plugins/vibeguard/scripts/vibeguard-plugin.sh repo-dir. - Use
dashboardfor a local HTML first-win overview. - Use
healthfor recent hook health. - Use
statsfor project/global trigger summaries. - Use
doctororcodex-statusfor install/capability diagnosis. - Keep setup changes explicit; do not install hooks while answering observe-only requests.
Commands
From a VibeGuard checkout:
bash plugins/vibeguard/scripts/vibeguard-plugin.sh dashboard
bash plugins/vibeguard/scripts/vibeguard-plugin.sh dashboard --no-open --output /tmp/vibeguard-dashboard.html
bash plugins/vibeguard/scripts/vibeguard-plugin.sh health 24
bash plugins/vibeguard/scripts/vibeguard-plugin.sh stats all
bash plugins/vibeguard/scripts/vibeguard-plugin.sh stats --scope global all
bash plugins/vibeguard/scripts/vibeguard-plugin.sh doctor
bash plugins/vibeguard/scripts/vibeguard-plugin.sh metrics-export
bash plugins/vibeguard/scripts/vibeguard-plugin.sh open-site
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 · 81 lines · 42 tokens per session scan A d6fd3d5eab65
vibeguard-observe is a skill published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 825 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
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…
ring:validating-ux-completeness
Validating that UX specifications are complete before technical design: a read-only checklist over wireframes, states, responsive behavior, accessibility, and component-library alignment, emitting a DESIGN VALIDATED / NEEDS REVISION verdict to design-validation.md. Standalone utility — run after a product-designer…
ring:structuring-documentation
Structuring documentation: content hierarchy, overview/conceptual/task page structures, section dividers, navigation, tables-vs-lists, code placement, cross-linking, and page-length targets. Use when planning doc structure, organizing a content hierarchy, splitting content across pages, or designing navigation. Skip…