# phantom: a set by ghostwright

The ghostwright/phantom repository on GitHub: 38 cards with a description and an install command. Inside: 32 prompts and 6 skills. They install into Claude Code, ChatGPT and Codex.

38 cards

- HTML: https://affpapa.org/en/nevibecode/by/ghostwright/phantom
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [phase-10f-codex-review-fix](https://affpapa.org/en/nevibecode/prompts/phase-10f-codex-review-fix.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10f-codex-review-fix — a Claude slash command that keeps the agent on three Claude review findings from PR 106, with the fix scoped to Phase 10F.
- [phase-10i-transcript-recovery-final-re-review](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-recovery-final-re-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10i-transcript-recovery-final-re-review is a Claude Code prompt for re-reviewing transcript recovery and verifying attachment metadata redaction fixes.
- [phase-10i-transcript-recovery-review](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-recovery-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10i-transcript-recovery-review prompt audits transcript recovery after Murph compaction, context handling, and secret exposure.
- [phase-10f-run-console-ui](https://affpapa.org/en/nevibecode/prompts/phase-10f-run-console-ui.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10f-run-console-ui — a prompt for building a run console UI in Phantom on Murph: displays live tool activity, counts, and session state with durable rehydration after refresh.
- [phase-10h-phantom-chat-review](https://affpapa.org/en/nevibecode/prompts/phase-10h-phantom-chat-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10h-phantom-chat-review prompt runs an in-depth audit of Phantom's chat UI and event pipeline after PR 109.
- [list-plugins](https://affpapa.org/en/nevibecode/skills/list-plugins.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — list-plugins reads settings.json and reports active Claude Code plugins with their marketplace IDs.
- [phase-10b-durable-timeline-reviewer](https://affpapa.org/en/nevibecode/prompts/phase-10b-durable-timeline-reviewer.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10b-durable-timeline-reviewer — a specialized prompt for reviewing Phase 10B of Phantom's chat system: validates timeline correctness, durability, idempotency, and data privacy.
- [phase-10h-chat-integrity-review](https://affpapa.org/en/nevibecode/prompts/phase-10h-chat-integrity-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10h-chat-integrity-review reviews uncommitted git diffs for Phantom chat transcript integrity in Claude Code.
- [phase-10h-pi-thinking-research](https://affpapa.org/en/nevibecode/prompts/phase-10h-pi-thinking-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10h-pi-thinking-research prompt asks Claude Code to examine how Pi presents model thinking, tool activity, and long-running work, then write chat UI guidance for Phantom.
- [phase-10h-provider-thinking-research](https://affpapa.org/en/nevibecode/prompts/phase-10h-provider-thinking-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10h-provider-thinking-research — a Claude slash command that digs through Murph, Pi and Phantom sources to find what providers really expose about thinking and reasoning events.
- [phase-10b-durable-timeline-re-reviewer](https://affpapa.org/en/nevibecode/prompts/phase-10b-durable-timeline-re-reviewer.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10b-durable-timeline-re-reviewer prompt for Claude Code re-audits fixes in Phantom PR #106 Phase 10B, checking durable timelines for secret leaks and validating session resume states.
- [phase-10i-transcript-recovery-re-review](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-recovery-re-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10i-transcript-recovery-re-review prompt guides Claude Code through a second review of transcript-recovery fixes, including project file inspection, required checks, and a written report.
- [phase-10k-page-artifact-ui-builder](https://affpapa.org/en/nevibecode/prompts/phase-10k-page-artifact-ui-builder.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10k-page-artifact-ui-builder is a Claude Code prompt for extracting page artifacts from tool results and displaying them in a compact chat card.
- [phase-10l-phantom-continuity-researcher](https://affpapa.org/en/nevibecode/prompts/phase-10l-phantom-continuity-researcher.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10l-phantom-continuity-researcher is a Claude Code prompt for diagnosing session continuity in Phantom, including context compaction, transcript recovery, and SQLite state analysis.
- [phase-10l-murph-continuity-researcher](https://affpapa.org/en/nevibecode/prompts/phase-10l-murph-continuity-researcher.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10l-murph-continuity-researcher investigates how Murph handles context compaction and interrupted turns, then produces a code-backed fix and test plan.
- [phase-10j-tool-card-collapse-research](https://affpapa.org/en/nevibecode/prompts/phase-10j-tool-card-collapse-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10j-tool-card-collapse-research is a prompt for Claude Code and ChatGPT that examines Phantom tool cards: collapsing completed calls while keeping errors and blocked work visible.
- [phase-10i-transcript-search-research](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-search-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10i-transcript-search-research guides an architectural study for historical chat transcript search in Phantom after Murph compaction.
- [phase-10a-activity-correctness-reviewer](https://affpapa.org/en/nevibecode/prompts/phase-10a-activity-correctness-reviewer.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10a-activity-correctness-reviewer prompt asks Claude Code to review Phantom’s Phase 10A patch and report concrete findings with file and line references.
- [phase-10m-chat-ui-polish-review](https://affpapa.org/en/nevibecode/prompts/phase-10m-chat-ui-polish-review.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10m-chat-ui-polish-review — a read-only review prompt for Phantom's Murph chat UI: it walks the components, the run timeline and artifact cards, then ranks what to fix next.
- [phase-10m-artifact-memory-architecture](https://affpapa.org/en/nevibecode/prompts/phase-10m-artifact-memory-architecture.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10m-artifact-memory-architecture is a Claude Code prompt for designing agent memory, artifact storage, and continuity across long sessions after context compaction, without editing files.
- [phase-10i-chat-detail-research](https://affpapa.org/en/nevibecode/prompts/phase-10i-chat-detail-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10i-chat-detail-research prompt asks Claude Code to examine Phantom’s chat UI and recommend the next implementation slices.
- [phase-10i-memory-architecture-research](https://affpapa.org/en/nevibecode/prompts/phase-10i-memory-architecture-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10i-memory-architecture-research — a Claude slash command that researches how Phantom chat should keep user-facing memory apart from the agent's working memory, then writes a report with a plan.
- [phase-10a-murph-pi-event-research](https://affpapa.org/en/nevibecode/prompts/phase-10a-murph-pi-event-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10a-murph-pi-event-research is a Claude Code prompt that audits Murph and Pi runtime events to surface agent progress, compaction, and tool calls in Phantom chat.
- [phase-10a-product-experience-research](https://affpapa.org/en/nevibecode/prompts/phase-10a-product-experience-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10a-product-experience-research prompt guides research into Phantom’s long-running agent chat, from run status to tool details and error states.
- [phase-10c-murph-progress-research](https://affpapa.org/en/nevibecode/prompts/phase-10c-murph-progress-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10c-murph-progress-research is a Claude Code prompt for researching Murph’s progress contract to improve tool call cards in Phantom chat.
- [phase-10b-durable-timeline-research](https://affpapa.org/en/nevibecode/prompts/phase-10b-durable-timeline-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10b-durable-timeline-research directs an autonomous research run on durable chat timelines and SSE reconnect logic in Phantom without touching source files.
- [echo](https://affpapa.org/en/nevibecode/skills/echo.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — Before answering a substantive question, echo searches memory for a similar earlier decision.
- [phase-10m-pi-murph-continuity-research](https://affpapa.org/en/nevibecode/prompts/phase-10m-pi-murph-continuity-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10m-pi-murph-continuity-research is a prompt for Claude Code and ChatGPT that investigates context recovery and compaction in Murph and Phantom, checking whether they reinvent Pi primitives.
- [phase-10i-transcript-recovery-builder](https://affpapa.org/en/nevibecode/prompts/phase-10i-transcript-recovery-builder.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10i-transcript-recovery-builder prompt for Claude Code builds transcript recovery for Phantom on Murph, letting agents search chat history after context compaction.
- [thread](https://affpapa.org/en/nevibecode/skills/thread.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — Trace how your thinking on a topic changed over time.
- [phase-10a-chat-pipeline-research](https://affpapa.org/en/nevibecode/prompts/phase-10a-chat-pipeline-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10a-chat-pipeline-research — a slash command that walks Phantom's chat pipeline from SDK events through SSE to React rendering.
- [overheard](https://affpapa.org/en/nevibecode/skills/overheard.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — overheard scans two weeks of stored memory to surface unfulfilled commitments and prepares followup drafts.
- [phase-10d-chat-ui-polish-research](https://affpapa.org/en/nevibecode/prompts/phase-10d-chat-ui-polish-research.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10d-chat-ui-polish-research prompt guides a review of Phantom’s chat UI using screenshots and project files, then asks for a design direction and an implementation plan.
- [ritual](https://affpapa.org/en/nevibecode/skills/ritual.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — Detects recurring behaviors from your session history and transforms them into scheduled tasks.
- [show-my-tools](https://affpapa.org/en/nevibecode/skills/show-my-tools.md) — skill · ghostwright · Claude Code, Codex, Cursor +4 · ★ 1497 repo stars — show-my-tools audits the agent environment and lists loaded skills, memory files, plugins, hooks, and subagents.
- [phase-10h-chat-integrity-builder](https://affpapa.org/en/nevibecode/prompts/phase-10h-chat-integrity-builder.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10h-chat-integrity-builder prompt directs Claude Code to fix transcript integrity in the Phantom chat, including attachment handling and SDK errors.
- [phase-10a-activity-correctness-builder](https://affpapa.org/en/nevibecode/prompts/phase-10a-activity-correctness-builder.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — The phase-10a-activity-correctness-builder prompt for Claude Code governs activity visibility during long-running requests, showing users that work continues when the interface is quiet.
- [phase-10b-durable-timeline-builder](https://affpapa.org/en/nevibecode/prompts/phase-10b-durable-timeline-builder.md) — prompt · ghostwright · Claude Code, ChatGPT · ★ 1497 repo stars — phase-10b-durable-timeline-builder guides Claude Code to implement durable chat run timelines, redaction, and stream reconnect logic as a principal engineer.

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
