prompt-bouncer

Colorful, themeable rendering for Claude Code replies: tables, headings, code, numbers, paths and links.

2 skills

Skins for Claude Code: tool rows that open onto their input and answer, highlighted code, diff, table, math, Mermaid and shell cards, links, folding, a usage band, a calm mode and fifteen themes. /skin swaps them live.

1 skill

Read-only side chat: /aside opens a pane beside the transcript where you ask about the session so far; answers come from a tool-less fork of the session's own transcript and nothing is written back into the main thread.

After a reply, lists the small guesses Claude made. Mark each Right or Wrong, and send the wrong ones back to Claude

Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they would change, with Proceed and Cancel buttons.

A Claude Code mod that keeps the one-hour prompt cache warm during breaks and asks before a cold send whether to continue here or start a new chat. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.

Tier-2/3 support engineering — bug reproduction, log and trace diagnosis, engineering escalations with repro packets, workarounds, bug-to-fix feedback loop

3 skills · 1 agent

Reasoning hygiene for AI agents: cross-source conflict detection, multi-source research with provenance, and rationalization-trap heuristics. Wave-1 Tier-2 consolidation so other plugins import skills/agents instead of duplicating. Implements provenance per claim (OmniMEM 2604.01007), cross-source conflict surfacing (ConflictQA 2604.11209), and the rationalization-trap value-rule per K2 design doc (docs/research/K2-knowledge-hygiene-from-papers.md).

3 skills · 1 agent