From dead-end-registry
Lists a repo's recorded dead ends — approaches tried and abandoned with reasons and cost. Helps avoid repeating failed strategies.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dead-end-registry:dead-endsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
!`node "${CLAUDE_SKILL_DIR}/../../dead-end-registry.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-end-registry.js" --render`
!node "${CLAUDE_SKILL_DIR}/../../dead-end-registry.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-end-registry.js" --render
The list above is this repository's recorded dead ends — approaches that were tried
and then reverted or ruled out, newest first, each with the date it was tried, why it
was walked back, and the estimated token cost of the detour. It is produced by the
dead-end-registry hook, which mines your transcripts as you work.
Briefly summarize the 1–3 most relevant entries and, if any bear on what the user is currently doing, gently flag that they have been down this road before. If the list is empty, just say so. Keep it short; do not re-run any commands.
npx claudepluginhub karanb192/claude-code-hooks --plugin dead-end-registryOrchestrates Entire skills to read historical checkpoints for understanding code evolution, provenance, and intent. Delegate to sub-skills for explain, search, review, replay, and more.
Loads a context primer from past sessions to resume work, catch up on repo state, or recall the open thread.
Searches memories from past Claude Code sessions in the current project. Use when historical context, past decisions, or prior conversations could inform the current task.