Phantom is an AI co-worker that operates its own computer, maintains persistent memory, uses MCP tools, and builds software and infrastructure in its workspace. It is for people who want an agent that can continue work across sessions through Slack or web chat while keeping its workspace separate from the user's computer. The catalogue skills and instruction support workflows for Phantom.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ghostwright/phantom --skill threadgit clone --depth 1 https://github.com/ghostwright/phantomWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ghostwright/phantom/thread)<a href="https://agentmods.dev/skills/ghostwright/phantom/thread"><img src="https://agentmods.dev/badge/skills/ghostwright/phantom/thread/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ghostwright/phantom/thread"><img src="https://agentmods.dev/badge/skills/ghostwright/phantom/thread.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.01032 |
| Opus 5.5 | $0.00010 | $0.00413 |
| Sonnet 5.5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
thread scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thread: the evolution of thinking
Inputs
$topic: the specific topic the user wants to trace. Could be a project name, a decision, a person, a product, a question.
Goal
Pull every mention of a specific topic from memory across sessions and channels, order them chronologically, cluster by time period and sub-theme, identify turning points where the user's view changed, and render as a narrative of evolution.
Not a log. Not a summary. A view of the shape of how the user changed their mind. The user should come away thinking "that is what I was actually doing, and I did not see it that clearly before."
Steps
1. Search memory for the topic
Call mcp__phantom-reflective__phantom_memory_search with query: "$topic", memory_type: "all", limit: 30. Do NOT pass days_back. We want the full history.
Success criteria: you have at least three hits for the topic. If you have zero or one, tell the user honestly and stop ("I do not have enough history on this topic yet to build an arc. It looks like this is the first time you are raising it.").
2. Order and cluster chronologically
Sort the hits by their started_at or valid_from timestamp. Cluster them by time period:
- If the hits span less than 14 days, cluster by day.
- If they span 14 to 90 days, cluster by week.
- If they span more than 90 days, cluster by month.
Within each cluster, look for sub-themes. A single cluster might split into "technical concerns" and "people concerns" if both appear in the same week.
Success criteria: you have 2-6 time clusters with the hits assigned to each.
3. Identify turning points
Re-read the clusters in order. Mark a turning point when:
- The user's stated view of the topic visibly changed.
- New information landed that the user acknowledged shifted things.
- A decision was explicitly made ("I decided to", "we are going with").
- A commitment was made or withdrawn.
- An emotional tone shifted (frustration to calm, curiosity to conviction).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 84 lines · 25 tokens per session scan A 065661998456
thread is a skill published in the GitHub repository ghostwright/phantom (1,483 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,032 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
ashlr-codex-genome-refresh
Refresh or maintain Ashlr project genome state from Codex. Use after architectural changes, schema/routing changes, or substantial refactors.
whiteboard-curate-suggest
When an insight, decision, or checklist with lasting value comes up during a conversation, suggest saving it to the library, and on the user's consent register it in Curated Knowledge via knowledgepromote.
whiteboard-react-to-share
When the user shares a note or capture via a [USERSHARED] trigger or [Spotlight Context], naturally bring it up in conversation (getting an image description via whiteboarddescribe first if needed) and voice your opinion.