InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Source-backed /goal contracts for Claude Code, Codex and Cursor, with a searchable catalog and separate reusable seed patterns.

    Stale GitHub, majiayu000 51 ★CC0-1.0Updated 46 days ago

    git clone https://github.com/majiayu000/awesome-goal-prompts.git
  2. Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

    Stale GitHub, withkynam 1,151 ★MITUpdated 4 months ago

    git clone https://github.com/withkynam/vibecode-pro-max-kit.git
  3. oh-my-fable

    Prompts

    Anthropic's Claude prompting guides (Fable 5.2, Opus 5.5) as a Claude Code plugin (KO/EN/ZH): always-on working rules, and /fable turns a rough request into goal, context, scope and done.

    Indexed GitHub, Junhan2 61 ★MITUpdated 7 days ago

    git clone https://github.com/Junhan2/oh-my-fable.git
  4. llmtrim

    Prompts

    Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

    Indexed GitHub, fkiene 274 ★MPL-2.0Updated 5 days ago

    git clone https://github.com/fkiene/llmtrim.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.