revibe

revibe is a skill for Claude Code from selvatuple/revibe-mcp. It costs 25 tokens per session (2,322 once invoked), scanned A, original, MIT.

A codebase analysis tool that examines a software project and explains its structure, files, design choices, and execution paths. It can also save this understanding for later use.

In plain words
What is it for?
Use it to review a new or copied project, map how its parts depend on each other, explain how code runs, and investigate its architecture.
Why use it?
It reduces the time needed to understand an unfamiliar repository and gives coding agents useful context before they make changes.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Install

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.

agentmods
npx agentmods add skills/selvatuple/revibe-mcp/openclaw
Any agent
npx skills add selvatuple/revibe-mcp --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/selvatuple/revibe-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for revibe

README.md
[![agentmods](https://agentmods.dev/badge/skills/selvatuple/revibe-mcp/openclaw.svg)](https://agentmods.dev/skills/selvatuple/revibe-mcp/openclaw)
Your own site
<a href="https://agentmods.dev/skills/selvatuple/revibe-mcp/openclaw"><img src="https://agentmods.dev/badge/skills/selvatuple/revibe-mcp/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,322 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.02322
Opus 5 $0.00013 $0.01161
Sonnet 5 $0.00005 $0.00464
Haiku 4.5 $0.00003 $0.00232

Measured 5d ago against content hash ae8888aae6c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

revibe 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 5d 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.

- curl
skills/openclaw/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Analyze codebases to understand architecture, file roles, design patterns, execution flows, and system design decisions. Returns structured insights inline and saves agent_context.json for persistent codebase understanding.

Revibe turns any GitHub repository into a complete architecture map — modules, dependencies, call chains, design decisions — in about 2 minutes.

When to Use

  • User asks to "analyze", "understand", or "explain" a codebase or repository
  • User clones or forks a new repo and wants to understand it quickly
  • User says "what does this project do" or "how is this structured"
  • User asks about architecture, patterns, or design decisions of a repo
  • Another skill needs codebase context to work effectively (use agent mode)

Behavior

Step 1: Extract the Target

Determine the GitHub URL from one of these sources (in priority order):

  1. Explicit URL in the message — e.g., https://github.com/owner/repo or owner/repo
  2. Current working directory — If the user says "analyze this", "understand this project", or doesn't specify a repo, detect it automatically:
    # Get GitHub URL from current git repo
    REMOTE_URL=$(git remote get-url origin 2>/dev/null)
    
    Convert SSH URLs to HTTPS:
    # [email protected]:owner/repo.git → https://github.com/owner/repo
    if [[ "$REMOTE_URL" == [email protected]:* ]]; then
      REMOTE_URL="https://github.com/${REMOTE_URL#[email protected]:}"
    fi
    # Strip .git suffix
    REMOTE_URL="${REMOTE_URL%.git}"
    
  3. Ask the user — Only if not in a git repo and no URL provided: "Which repository would you like me to analyze?"

When using the current directory, confirm briefly: "Analyzing {repo_name} from your current directory..."

Step 2: Submit for Analysis

# Set up auth
API_KEY="${REVIBE_API_KEY:-}"
AUTH_HEADER=""
if [ -n "$API_KEY" ]; then
  AUTH_HEADER="-H \"X-Revibe-Key: $API_KEY\""
fi

# Submit
RESPONSE=$(curl -s -X POST "https://app-backend.revibe.codes/api/v1/analyze" \
  -H "Content-Type: application/json" \
  ${AUTH_HEADER} \
  -d "{\"github_url\": \"${REMOTE_URL}\"}")

JOB_ID=$(echo "$RESPONSE" | jq -r '.job_id')
STATUS=$(echo "$RESPONSE" | jq -r '.status')

Read the full file on GitHub · 254 lines

Changes

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.

  1. 5d ago First seen · 254 lines · 25 tokens per session scan A ae8888aae6c3

Subscribe to this mod's changes

revibe is a skill published in the GitHub repository selvatuple/revibe-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 2,322 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

forensic-deepdive-query

Answer questions about the current repo by querying its existing forensic-deepdive artifacts (MAP.md, HOTPATHS.md, ARCHAEOLOGY.md, MENTALMODEL.md, AGENTBRIEF.md). Use when the user asks "where does X live", "who owns Y", "how did Z evolve", "what should I touch to add a new W" — AND the repo already has these…

Dhevenddra/forensic-deepdive · 119 tokens

forensic-deepdive-update

Incrementally refresh forensic-deepdive artifacts after the codebase has changed. Use when MAP.md or HOTPATHS.md is stale (>7 days or >50 commits old), or after a significant refactor when the user wants artifacts to reflect reality. Do NOT use for first-time analysis (use forensic-deepdive-extract) or simple lookups…

Dhevenddra/forensic-deepdive · 89 tokens

codebase-debugging

Find the right place to look when something is broken. Use when the user reports an error, regression, crash, flaky test, or unexpected behavior and says "why is X broken", "trace this failure", "where does this exception come from", "what changed that could cause this". Reads docs/codebase/HOTPATHS.md (dependency hot…

Dhevenddra/forensic-deepdive · 117 tokens

code-diagram

Analyzes source code and generates Mermaid diagrams. Accepts a directory, file, @reference, line range (path:10-50), multiple targets ([path1, path2]), or pasted code. Supports class, sequence, component, and architecture diagrams for Dart, TypeScript, Python, Java, Kotlin, Go, Swift, Rust.

usamaijazmughal/code-diagram · 73 tokens

systematic-debugging

Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.

jnMetaCode/superpowers-zh · 24 tokens

diagnose-backend-bug

Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…

QoderAI/better-harness · 87 tokens