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/frane/vibesurfer/docsnpx skills add frane/vibesurfer --skill docsgit clone --depth 1 https://github.com/frane/vibesurferWhat 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 | $0.00000 | $0.00331 |
| Opus 5 | $0.00000 | $0.00166 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade B, and why
docs scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The same `vs skill install` call also writes an `mcpServers.vibesurfer = {command: "vs", args: ["mcp"]}` entry into each agent's MCP config (`.claude.json`, `~/.codex/config.toml`, `<workspace>/.cursor/mcp.json`, `~/.gem What it actually says
Skill
The skill that gets installed into every detected agent by vs skill install lives at:
That file is the single source of truth — it's what the agent reads, and it's the file vs skill install writes (verbatim) into each agent's conventional skill location:
| Agent | Path |
|---|---|
| Claude Code | ~/.claude/skills/vibesurfer/SKILL.md |
| Codex CLI | ~/.codex/skills/vibesurfer/SKILL.md |
| Cursor | <workspace>/.cursor/skills/vibesurfer/SKILL.md |
| Gemini | ~/.gemini/extensions/vibesurfer/GEMINI.md (renamed) |
| OpenClaw | ~/.openclaw/workspace/skills/vibesurfer/SKILL.md |
| Canonical | ~/.agents/skills/vibesurfer/SKILL.md |
The same vs skill install call also writes an mcpServers.vibesurfer = {command: "vs", args: ["mcp"]} entry into each agent's MCP config (.claude.json, ~/.codex/config.toml, <workspace>/.cursor/mcp.json, ~/.gemini/settings.json, Library/Application Support/Claude/claude_desktop_config.json on macOS) so the agent can talk to vibesurfer over MCP as well as via the SKILL.md.
What ships with it
23 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.
- ARCHITECTURE.md 8.4 KB
- codes.md 4.2 KB
- decisions/0001-engine-webkit.md 4.0 KB
- decisions/0002-no-transactions.md 1.6 KB
- decisions/0003-line-protocol-not-json.md 1.5 KB
- decisions/0004-stable-refs-not-line-numbers.md 2.1 KB
- decisions/0005-tree-deltas-default.md 2.2 KB
- decisions/0006-composite-flags-are-observation-driven.md 2.0 KB
- decisions/0007-pipeline-syntax-v2.md 2.3 KB
- decisions/0008-inspector-protocol-internal-only.md 2.1 KB
- demo-claude.gif 1039 KB
- demo/demo.tape 1018 B
- demo/record-claude.sh 5.6 KB runs code
- demo/render.sh 2.2 KB runs code
- DEVELOPMENT.md 3.0 KB
- img/demo-trending.png 347 KB
- known-issues.md 4.3 KB
- M6_PLAN.md 5.9 KB
- PRIMITIVES.md 8.1 KB
- PROTOCOL.md 12 KB
- RATIONALE.md 5.5 KB
- REALITY_CHECK.md 6.8 KB
- ROADMAP.md 6.6 KB
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.
- 2d ago First seen · 19 lines · 0 tokens per session scan B bdd4ee6b2ed8
docs is a skill published in the GitHub repository frane/vibesurfer (15 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 331 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kane-cli
Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable test.md. Use for any task requiring a real browser (navigate…
yutori-computer-use
Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop.
yutori-research
Execute deep web research on any topic using Yutori's research agents. Use for competitive analysis, market research, finding documentation, or answering complex questions that require synthesizing information from multiple sources.
yutori-browse
Automate browser tasks like form filling, data extraction, or multi-step web workflows. Use when the user needs to interact with websites that require clicking, typing, or navigation.
build-capability
When you need an ability the bridge does not have, build it from the general tools instead of asking for a bespoke one. This skill is the map of how.
arena-bridge
Skill and protocol specification for AI agents (Arena.ai Agent Mode, Claude Code, Codex, Cursor, and custom agentic frameworks) interacting with Skainet Bridge.