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 airvalona/antigravity-like-claude-code --skill compactgit clone --depth 1 https://github.com/airvalona/antigravity-like-claude-codeWrote 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/airvalona/antigravity-like-claude-code/compact)<a href="https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/compact"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/compact/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/airvalona/antigravity-like-claude-code/compact"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/compact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00061 | $0.00494 |
| Opus 5.5 | $0.00024 | $0.00198 |
| Sonnet 5.5 | $0.00012 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
compact 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 2mo 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.
What it actually says
/compact — Context Compression
Port of Claude Code's /compact. Important limitation: a skill cannot truncate
the agent's own context window the way Claude Code's native /compact does —
that requires harness-level support. This skill instead produces the summary
half of the workflow; the user (or a follow-up instruction) still needs to run
Antigravity's native /clear afterward to actually free the context.
Arguments
/compact— summarize the whole session so far/compact <instructions>— summarize with a specific focus (e.g. "/compact focus on the auth refactor" to keep more detail on one thread and compress the rest harder)
Steps
-
Review the conversation so far and extract:
- Decisions made — architectural choices, library picks, naming conventions settled on, anything the user explicitly approved or rejected
- Changes made — files created/edited and what changed in each, at a summary level (not a full diff)
- Open threads — anything started but not finished, known bugs not yet fixed, questions still waiting on the user
-
Write this as a compact block, e.g.:
## Session summary
**Decisions:** <bullet list>
**Changes so far:** <bullet list, file: what changed>
**Open threads:** <bullet list>
**Next step:** <one line>
-
Tell the user: "Run
/clearnow to free context, then paste this back in (or say 'continue from the summary') to resume with a clean window." -
If they want it saved for later instead of resuming immediately, offer to write it to a scratch file (e.g.
.agent/session-notes/<date>.md) rather than just printing it.
Notes
Don't try to preserve everything — the whole point is compression. Err toward cutting resolved/settled details and keeping only what's still relevant to finishing the current task.
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.
- 2mo ago First seen · 51 lines · 61 tokens per session scan A 6f3f7d21078b
compact is a skill published in the GitHub repository airvalona/antigravity-like-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 494 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.