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/a8cteam51/claude-code-plugins/vibenpx skills add a8cteam51/claude-code-plugins --skill vibegit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWhat 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 | $0.00164 | $0.02811 |
| Opus 5 | $0.00082 | $0.01406 |
| Sonnet 5 | $0.00033 | $0.00562 |
| Haiku 4.5 | $0.00016 | $0.00281 |
Grade A, and why
vibe scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The only route to canvas content is the connected server's MCP tools, named `mcp__<server>__ai-canvas-*`. Never call the site's `/wp-json/ai-canvas/mcp` endpoint yourself — not with `curl`, not with a helper script, not How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build pages with AI-Canvas
You are writing three files per page — index.html, style.css, script.js — that the AI-Canvas plugin renders between the site's theme header and footer. The MCP tools are the only way in; there is no other filesystem access, and that is by design.
MCP tools only — no exceptions
The only route to canvas content is the connected server's MCP tools, named mcp__<server>__ai-canvas-*. Never call the site's /wp-json/ai-canvas/mcp endpoint yourself — not with curl, not with a helper script, not with an HTTP library, and never by extracting the stored Authorization header from the MCP registration. The endpoint does speak MCP over plain HTTP; that is an implementation detail, not an invitation, and a plugin hook denies such attempts anyway. If the tools cannot be reached, that is a connection problem for the user to fix — never a gap for you to bridge.
Preflight — before the first canvas operation:
- Confirm the tools are present. Deferred tools (listed by name, loadable via ToolSearch) count as present — load them. If no
ai-canvas-*MCP tools exist in the session at all, the server was registered or changed after this session started — MCP servers load at session start. Stop and ask the user to run/mcp(reconnect) or restart the session; that is the entire fix, and there is no workaround for you to attempt in the meantime.claude mcp listin Bash may be used to diagnose what is registered, never to reach content. - Match the server to the site. If more than one server exposes
ai-canvas-*tools (say, a local Studio site and a staging site), determine which tool prefix points at the site the user named before writing anything —claude mcp listshows each registration's URL. Writes go live immediately on whichever site the tool targets, so never guess; if the mapping is ambiguous, ask the user.
The same rule holds mid-task: if a tool call starts failing with auth or connection errors, report it and ask the user to run /mcp — do not downgrade to HTTP to keep the task moving.
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 · 89 lines · 164 tokens per session scan A 428b7ee0a232
vibe is a skill published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 5d ago), licensed MIT. It adds 164 tokens to every session and 2,811 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…