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

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

hookcrate install bitter-pill-audit

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…

hookcrate install context-recall

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

hookcrate install credential-guard

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

hookcrate install evidence-gate

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

hookcrate install release-scrub

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

hookcrate install reproduce-first

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

hookcrate install research-fleet

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)

hookcrate install weekly-review

Guide · 2026-10-11

Auditing your CLAUDE.md: cut, keep, sharpen

A repeatable audit for instruction files — flag vague, redundant, default and contradictory rules, estimate token cost, rewrite the survivors shorter.

Guide · 2026-10-11

How to block credential leaks in Claude Code with a PreToolUse hook

A PreToolUse hook that denies curl, wget and HTTP tool calls carrying a literal API key, lets $VAR references through, and logs every decision locally.

Guide · 2026-10-11

Reproduce before you fix: a bug-report workflow for coding agents

Make a captured failure — command output, failing test or screenshot — a hard prerequisite before any edit, and reuse the same capture to prove the fix.

Guide · 2026-10-11

Running a research fleet with Claude Code subagents and verifying every URL

Split a question into sub-questions, run parallel subagents, cross-check claims into confidence tags, and fetch every link before it reaches the report.

Guide · 2026-10-11

Scrubbing a repo for personal data before you publish

Scan a folder for emails, phones, checksum-valid IBANs, API keys and a private names list, triage every finding, and publish only when a re-run is clean.

Guide · 2026-10-11

Stop Claude Code from marking work done without evidence (the Stop hook pattern)

Use a Stop hook to refuse completion while checklist items are unchecked or lack an evidence line, with the exact missing criteria shown to Claude.