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 skills add MUSE-CODE-SPACE/vibe-coding-mcp --skill vibe-codinggit clone --depth 1 https://github.com/MUSE-CODE-SPACE/vibe-coding-mcpWrote 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/muse-code-space/vibe-coding-mcp/vibe-coding)<a href="https://agentmods.dev/skills/muse-code-space/vibe-coding-mcp/vibe-coding"><img src="https://agentmods.dev/badge/skills/muse-code-space/vibe-coding-mcp/vibe-coding/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/muse-code-space/vibe-coding-mcp/vibe-coding"><img src="https://agentmods.dev/badge/skills/muse-code-space/vibe-coding-mcp/vibe-coding.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00139 | $0.01699 |
| Opus 5.5 | $0.00056 | $0.00680 |
| Sonnet 5.5 | $0.00028 | $0.00340 |
| Haiku 4.5 | $0.00014 | $0.00170 |
Grade B, and why
vibe-coding 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 yesterday.
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.
hooks to `~/.claude/settings.json`, backs the file up first). Tell the user to restart How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-coding — session memory for AI pair programming
You have the vibe-coding-mcp MCP server available (tools are prefixed muse_). It stores
coding sessions as JSON files under ~/.vibe-coding-mcp/sessions/ and can read Claude Code's
own transcripts from ~/.claude/projects/. Nothing leaves the machine unless the user publishes.
0. First: make sure capture is actually running
Before producing any report, check that there is data. Call muse_session_history with
action: "stats". If totalSessions is 0, or the user asks for "setup":
- Run
npx -y vibe-coding-mcp doctorand show the user the result. - If hooks are not installed, run
npx -y vibe-coding-mcp init(addsStop+SessionEndhooks to~/.claude/settings.json, backs the file up first). Tell the user to restart Claude Code once. - To backfill history that already exists on disk, call
muse_capture_transcriptwith{ "action": "capture", "all": true }. This parses every transcript for the current project and stores one session per Claude Code session (re-running is safe: it updates instead of duplicating).
If the MCP server itself is missing, the user needs: claude mcp add vibe-coding-mcp -- npx -y vibe-coding-mcp.
1. Pick the workflow from the user's words
| User says | Do this |
|---|---|
| "save / capture this session", "remember what we did" | muse_capture_transcript { action: "capture" } (newest transcript for cwd). Report title, files, decisions count. |
| "what did I do today", "daily log" | muse_digest { period: "today", groupBy: "project", includePrompts: true } → tidy the Markdown. Or use the /daily-vibe-log prompt. |
| "standup" | /standup prompt, or muse_digest for yesterday and today, then muse_git status. Output Yesterday / Today / Blockers, max 3 bullets each. |
| "weekly report", "what did I ship this week", "monthly retro" | /weekly-report prompt, or muse_digest `{ period: "week" |
| "why did we choose X", "what was the decision about Y" | vibe-coding://search/<keyword> resource or muse_session_history { action: "search", keyword } → muse_session_history { action: "get", sessionId } → quote designDecisions and the matching prompts. |
| "document this session as README/DESIGN/API/ARCHITECTURE" | /document-session prompt, or muse_session_history get → muse_generate_dev_document → (optional) muse_normalize_for_platform → muse_publish_document. |
| "write the PR description for this refactor" | /refactor-context prompt: session → muse_summarize_design_decisions → muse_analyze_code (Mermaid) → muse_git diff. Sections: Why / What changed / Trade-offs / How to review. |
| "write an ADR for …" | muse_summarize_design_decisions on the session's conversation, then muse_generate_dev_document DESIGN, then publish to Obsidian/Notion if asked. |
| "publish to Notion/Obsidian/Slack…" | Read vibe-coding://config first. If the platform is not configured, say which env var is missing (see references/tools.md) instead of trying. |
What ships with it
4 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.
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.
- yesterday First seen · 86 lines · 139 tokens per session scan B 0d1d6af00125
vibe-coding is a skill published in the GitHub repository MUSE-CODE-SPACE/vibe-coding-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,699 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
confluence
Organize Confluence page trees, macros, labels, and permissions; perform scoped content updates through the REST API.
documentation-writer
Write clear, comprehensive technical documentation. Covers README files, API docs, tutorials, architecture guides, and documentation systems.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.
excel-mcp-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through Excel MCP tools. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query…
investor-materials
Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update. NOT the slide narrative (that is pitch-deck), NOT the projection spreadsheet (that…
meeting-notes
Use when a meeting just ended and a transcript or rough notes must become a record the absent can act on — decisions with their why, actions with an owner and a real date, open questions, a recap inside 24–48h — or to clean an AI-notetaker draft that invented tasks or swapped speakers. NOT the durable ADR with…