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.
git clone --depth 1 https://github.com/chieflatif/vibeos-pluginWrote 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/plugins/chieflatif/vibeos-plugin/vibeos)<a href="https://agentmods.dev/plugins/chieflatif/vibeos-plugin/vibeos"><img src="https://agentmods.dev/badge/plugins/chieflatif/vibeos-plugin/vibeos/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/plugins/chieflatif/vibeos-plugin/vibeos"><img src="https://agentmods.dev/badge/plugins/chieflatif/vibeos-plugin/vibeos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vibeos 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 27 skills, 32 agents, 14 hooks travel with it, and installing the plugin installs all of them — 2,995 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill plan A 65 tokens
- Skill discover A 84 tokens
- Skill audit A 92 tokens
- Skill autonomous A 66 tokens
- Skill help A 65 tokens
- Skill checkpoint A 70 tokens
- Skill comp A 49 tokens
- Skill session-audit A 56 tokens
- Skill codex-audit A 121 tokens
- Skill vibeos-build A 48 tokens
- Skill gate A 54 tokens
- Skill status A 67 tokens
- Skill vibeos-comp A 48 tokens
- Skill wo A 56 tokens
- Skill project-status A 68 tokens
- Skill vibeos-autonomous A 56 tokens
- Skill vibeos-session-audit A 58 tokens
- Skill vibeos-status A 52 tokens
- Skill vibeos-audit A 49 tokens
- Skill vibeos-plan A 48 tokens
- Skill vibeos-checkpoint A 49 tokens
- Skill vibeos-discover A 57 tokens
- Skill vibeos-wo A 54 tokens
- Skill vibeos-help A 58 tokens
- Skill vibeos-project-status A 47 tokens
- Skill vibeos-gate A 51 tokens
- Skill upgrade B 95 tokens
- Agent investigator A 54 tokens
- Agent plan-auditor A 45 tokens
- Agent product-drift-auditor A 56 tokens
- Agent security-auditor A 41 tokens
- Agent architecture-auditor A 33 tokens
- Agent correctness-auditor A 45 tokens
- Agent evidence-auditor A 34 tokens
- Agent system-invariant-auditor A 71 tokens
- Agent test-auditor A 41 tokens
- Agent tester A 34 tokens
- Agent backend A 34 tokens
- Agent contract-validator A 54 tokens
- Agent delivery-infrastructure-auditor A 60 tokens
- Agent dependency-intelligence-auditor A 58 tokens
- Agent flow-auditor A 57 tokens
- Agent integration-captain A 50 tokens
- Agent prompt-engineer A 48 tokens
- Agent red-team-auditor A 44 tokens
- Agent doc-writer A 28 tokens
- Agent frontend A 33 tokens
- Agent architecture-auditor-same-tree A 26 tokens
- Agent contract-validator-same-tree A 24 tokens
- Agent correctness-auditor-same-tree A 27 tokens
- Agent delivery-infrastructure-auditor-same-tree A 46 tokens
- Agent dependency-intelligence-auditor-same-tree A 44 tokens
- Agent evidence-auditor-same-tree A 27 tokens
- Agent flow-auditor-same-tree A 42 tokens
- Agent product-drift-auditor-same-tree A 29 tokens
- Agent red-team-auditor-same-tree A 28 tokens
- Agent security-auditor-same-tree A 26 tokens
- Agent system-invariant-auditor-same-tree A 47 tokens
- Agent test-auditor-same-tree A 26 tokens
- Hook PreToolUse A not measured
- Hook Stop A not measured
- Hook UserPromptSubmit A not measured
- Hook ConfigChange A not measured
- Hook Notification A not measured
- Hook PostToolUse A not measured
- Hook PreCompact A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook SubagentStop A not measured
- Hook TaskCompleted A not measured
- Hook TaskCreated A not measured
- Hook TeammateIdle A not measured
- Hook WorktreeCreate A not measured
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.
- 1mo ago Changed 202a2b1ed551
- 1mo ago Changed a821c22acb06
- 1mo ago Changed 847ab2aa013b
- 1mo ago First seen · 9 lines scan A 2e1f9fcdcafe
vibeos is a plugin published in the GitHub repository chieflatif/vibeos-plugin (2 stars, last pushed 1mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.