What is antigravity-context-architecture?

A guide to how Google Antigravity stores and assembles context for coding agents. It explains project instructions, persistent knowledge, saved work artifacts, workflows, and editor or manager sessions.

Use it to design durable project memory, tune context behavior, organize instructions and skills, or diagnose repeated work in Antigravity.

It helps explain why an agent remembers or misses information across tasks and where different kinds of project context belong.

antigravity-context-architecture — Skill by navendubrajesh

Install

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.

Any agent

npx skills add navendubrajesh/context-management-for-agents --skill antigravity-context-architecture

Clone the repo

git clone --depth 1 https://github.com/navendubrajesh/context-management-for-agents

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture/github.svg)](https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture)

Your own site

<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/antigravity-context-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 972 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00102	$0.00972
Opus 5.5	$0.00041	$0.00389
Sonnet 5.5	$0.00020	$0.00194
Haiku 4.5	$0.00010	$0.00097

Measured 2mo ago against content hash f4411ad66587, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

antigravity-context-architecture 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.

skills/antigravity-context-architecture/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Antigravity Context Architecture

Google Antigravity is an agent-first development platform with two surfaces: an Editor (synchronous, hands-on) and a Manager (asynchronous multi-agent orchestration). Context is not just chat history — it combines AGENTS.md, Skills, Knowledge Items (KIs), Artifacts, and workflows into persistent, reviewable state.

When to Activate

Activate this skill when:

Designing how Antigravity retains knowledge across conversations
Understanding Artifacts vs Knowledge Items vs conversation history
Orchestrating multiple agents via Manager Surface
Deciding what belongs in AGENTS.md vs .agents/skills/ vs Knowledge Items
Diagnosing why Antigravity repeats work or ignores prior decisions

Do not activate this skill for adjacent work owned by other skills:

Do not activate for platform-agnostic attention theory: context-fundamentals.
Do not activate for writing AGENTS.md and skills manifests: antigravity-customization.
Do not activate for Artifact lifecycle across long Manager sessions: antigravity-session-management.
Do not activate for custom external RAG: memory-systems.

Core Concepts

AGENTS.md as first-read context

Antigravity reads AGENTS.md at session start — project overview, constraints, verification commands, and "Do Not" rules. It is the highest-priority user-authored context layer and should stay lean; depth belongs in Skills or Knowledge Items.

Skills (.agents/skills/)

Skills follow the SKILL.md + optional references/ pattern — loaded on demand when relevant, mirroring progressive disclosure. Use for reusable capability packages (deployment procedures, domain workflows) rather than repo-wide invariants.

Knowledge Items (persistent memory)

KIs are curated facts distilled from past work — stored in Antigravity's Knowledge directory and checked at session start to avoid redundant rediscovery. Unlike chat history, KIs are edited, deduplicated knowledge — API schemas, business rules, architecture decisions.

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/antigravity-internals.md 1.6 KB

Changes

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 · 72 lines · 102 tokens per session scan A f4411ad66587

Subscribe to this mod's changes

antigravity-context-architecture is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 972 once invoked, about $0.0004 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.

Building agents Memory and context

antigravity-context-architecture next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
antigravity-context-architecturenavendubrajesh/context-management-for-agents	Skill	2	1mo ago	MIT	A	102	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex