update-readme

A command for researching and updating an awesome-list README, a document that collects useful tools and resources.

In plain words
What is it for?
Refreshing all or selected categories of an AI coding tools list, including IDE assistants, coding agents, cloud platforms, MCP tools, and learning resources.
Why use it?
It organizes repeated research and uses a local SQLite cache, a small database, to avoid fetching the same information unnecessarily.

Command for Claude Code

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 commands/roboco-io/awesome-vibecoding/update-readme
Clone the repo
git clone --depth 1 https://github.com/roboco-io/awesome-vibecoding

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.02825
Opus 5 $0.00000 $0.01412
Sonnet 5 $0.00000 $0.00565
Haiku 4.5 $0.00000 $0.00282

Measured 2d ago against content hash 02453e083653, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-readme 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 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.

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.

.claude/commands/update-readme.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly README Update

You are updating the awesome-vibecoding README.md with the latest AI coding tools.

Arguments

  • $ARGUMENTS: Category filter (all, ide, agentic, cloud, learning). Default: all
    • If 'all': Update all categories
    • If specific: Only update that category
  • $FORCE: Cache force refresh (true/false). Default: false
    • If 'true': Ignore all cache TTLs, re-fetch everything from sources

Task

Research and update each section of the README with new tools using multiple sources and search strategies. Use the SQLite cache to avoid redundant API calls and track candidates across runs.

Categories

  1. IDE & Editor Assistants - AI-powered code completion and IDE integrations
  2. Agentic Coding Environments - Autonomous AI systems for end-to-end development
  3. Cloud & Platform Integrations - Browser-based and cloud AI development platforms
  4. MCP Servers & Tooling - Model Context Protocol servers and related tools
  5. Learning Resources - Research papers, articles, videos about vibe coding

Step 0: Cache Initialization

Before any research, initialize the SQLite cache database.

mkdir -p .cache

# Verify DB integrity; recreate if corrupted
TABLES=$(sqlite3 .cache/awesome-vibecoding.db ".tables" 2>/dev/null || echo "")
if [ -z "$TABLES" ] || ! echo "$TABLES" | grep -q "search_cache"; then
  rm -f .cache/awesome-vibecoding.db
fi

# Create tables (idempotent)
sqlite3 .cache/awesome-vibecoding.db "CREATE TABLE IF NOT EXISTS search_cache (query TEXT NOT NULL, source TEXT NOT NULL, response TEXT NOT NULL, created_at TEXT NOT NULL DEFAULT (datetime('now')), ttl_days INTEGER NOT NULL DEFAULT 7, PRIMARY KEY (query, source));"

sqlite3 .cache/awesome-vibecoding.db "CREATE TABLE IF NOT EXISTS tool_metadata (url TEXT PRIMARY KEY, name TEXT NOT NULL, category TEXT, stars INTEGER, last_commit TEXT, description TEXT, in_readme INTEGER NOT NULL DEFAULT 0, checked_at TEXT NOT NULL DEFAULT (datetime('now')), ttl_days INTEGER NOT NULL DEFAULT 30);"

sqlite3 .cache/awesome-vibecoding.db "CREATE TABLE IF NOT EXISTS candidate_queue (url TEXT PRIMARY KEY, name TEXT NOT NULL, category TEXT, description TEXT, source TEXT, discovered_at TEXT NOT NULL DEFAULT (datetime('now')), status TEXT NOT NULL DEFAULT 'pending', reject_reason TEXT, CHECK (status IN ('pending','added','rejected','deferred')));"

sqlite3 .cache/awesome-vibecoding.db "CREATE TABLE IF NOT EXISTS run_stats (run_id TEXT PRIMARY KEY, run_at TEXT NOT NULL DEFAULT (datetime('now')), cache_hits INTEGER NOT NULL DEFAULT 0, cache_misses INTEGER NOT NULL DEFAULT 0, api_calls_saved INTEGER NOT NULL DEFAULT 0, tools_added INTEGER NOT NULL DEFAULT 0, tools_queued INTEGER NOT NULL DEFAULT 0, db_size_bytes INTEGER);"

Read the full file on GitHub · 285 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. 2d ago First seen · 285 lines · 0 tokens per session scan A 02453e083653

Subscribe to this mod's changes

update-readme is a command published in the GitHub repository roboco-io/awesome-vibecoding (201 stars, last pushed 1mo ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 2,825 tokens. 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 2026-08-30.