HookCrate

Battle-tested skills, hooks and workflow packs for Claude Code.

Browse, preview, install with one command.

Packs

Every pack ships with a preview of a real session so you can see it working before you install.

Bitter Pill Audit

Skill

Audits a CLAUDE.md or instructions file for redundant, vague and contradictory rules with keep / cut / sharpen verdicts and token estimates.

Triggers: User asks to audit, trim, clean up, simplify or review a CLAUDE.md, system prompt, AGENTS.md or rules file

bunx hookcrate install bitter-pill-audit

Context Recall

Skill

Searches prior session logs and notes for a topic and summarizes the last three relevant sessions so work resumes with context.

Triggers: User says: what did we do about X, pick up where we left off, continue the Y work, remind me how Z works, last time we…

bunx hookcrate install context-recall

Credential Guard

Hook

Blocks shell and HTTP tool calls that would ship a literal API key or token to an outbound command.

Triggers: PreToolUse on Bash — any shell command

bunx hookcrate install credential-guard

Evidence Gate

Hook

Refuses to let a task be marked complete while checklist criteria are unchecked or lack an evidence line.

Triggers: Stop — every time Claude tries to end its turn

bunx hookcrate install evidence-gate

Release Scrub

Skill

Scans a folder for emails, phone numbers, IBANs, API keys and a configurable names list before anything is published.

Triggers: User is about to publish, open-source, share, zip, or push a folder to a public remote

bunx hookcrate install release-scrub

Reproduce First

Skill

Forces a captured reproduction (command output, failing test or screenshot) before any code edit on a bug report.

Triggers: Claude reads a bug report: 'X is broken', 'this fails', 'error when', 'not working', 'regression', a pasted stack trace

bunx hookcrate install reproduce-first

Research Fleet

Skill

Decomposes a research question into sub-questions, runs parallel subagents, cross-checks claims and verifies every URL before reporting.

Triggers: User asks to research, investigate, compare, find out, or 'what's the state of' a non-trivial topic

bunx hookcrate install research-fleet

Weekly Review

Workflow

A Stop hook that appends a structured summary of every session to REVIEW.md, plus a skill that rolls the week up when it is due.

Triggers: Stop hook — end of every Claude turn (appends an entry; nudges when rollup is 7+ days overdue)

bunx hookcrate install weekly-review

Install

  1. Buy a license. Your key (sf_…) is shown on the confirmation page.
  2. Save it once: bunx hookcrate login sf_YOUR_KEY
  3. In any project: bunx hookcrate install <pack> — files land in .claude/skills/ or .claude/hooks/.
  4. Hooks print the exact settings.json fragment to add; pass --apply to merge it for you. bunx hookcrate update pulls new versions.

Pricing

One license, every pack, every update. Per seat, no redistribution — see the license terms.

Monthly
$9 / month

Cancel any time. Installed packs keep working; updates stop when the subscription ends.

Subscribe
Lifetime
$99 lifetime

Pay once. All current and future packs, forever.

Buy lifetime