Cross-Ecosystem Handoff: Antigravity 2.0 to Anthropic Claude
The Harness Abstraction Layer translating Google Antigravity 2.0 concepts to Claude Code/Cowork: session registry, concept mapping, critical differences, and the bridge between ecosystems.
Cross-Ecosystem Handoff: Antigravity 2.0 to Anthropic Claude
On July 6, 2026, Alefita invoked Claude Opus 4.6 Thinking inside Google's Antigravity 2.0 harness for a single purpose: to create a bridge between the Gemini ecosystem that birthed the unit-distance research and the Anthropic ecosystem that would carry it forward. This page documents that bridge.
Why the Handoff Happened
The unit-distance research spanned 4 sessions across 3 different harnesses:
| Session | Harness | Model | Achievement |
|---|---|---|---|
| 1 | Antigravity 2.0 | Gemini 3.5 Flash / 3.1 Pro | H4 initial exploration |
| 2 | Antigravity 2.0 | Gemini 3.5 Flash / 3.1 Pro | H16 discovery, Elo 2350 |
| 3 | Antigravity IDE | Gemini | Co-Scientist analysis |
| 4 | Antigravity 2.0 | Claude Opus 4.6 Thinking | Handoff creation |
The Gemini ecosystem provided the research substrate — the inductive subagent definition, the channel protocol for internal reasoning, the GEMINI.md contract system. But the project needed to survive beyond any single harness. The Anthropic ecosystem offered:
- Explicit subagent configuration (pre-defined swarm architecture)
- Hooks for enforcement (PreToolUse, PostToolUse — stronger than guidance-only rules)
- MCP server integration (shared protocol standard)
- Dynamic Workflows (scripted orchestration via JS)
- 1M context token window (capacity to load entire wiki simultaneously)
The handoff was not abandonment — it was evolution. The Research Director created CLAUDE.md as a translation layer, preserving every behavioral rule, protocol, and architectural pattern from the Gemini ecosystem while adapting them to Claude's primitives.
The Harness Abstraction Layer (HAL)
The HAL is a concept mapping between two fundamentally different agent architectures. It translates intent, not tokens.
Concept Translation Table
| Antigravity 2.0 | Claude Code / Cowork | Notes |
|---|---|---|
GEMINI.md (root) | CLAUDE.md (root) | Agent-maintained research contract |
.agents/GEMINI.md | .agents/CLAUDE.md or .claude/CLAUDE.md | Project protocol (read-only) |
.agents/rules/*.md | CLAUDE.md sections or Hooks | Rules = guidance; Hooks = enforcement |
.agents/skills/*/SKILL.md | Custom tools or /init patterns | Skills = reusable instruction sets |
invoke_subagent | Subagents / Agent Teams / Dynamic Workflows | Claude Code v2.1.154+ orchestration |
define_subagent | Custom subagent definitions in CLAUDE.md | Describe role + constraints inline |
| MCP servers | MCP servers (shared protocol) | Same MCP standard |
search_web | WebSearch tool | Similar capability |
view_file | Read tool | File reading |
run_command | Bash tool | Shell execution |
write_to_file / replace_file_content | Write / Edit tools | File modification |
Artifacts (brain/<id>/) | Session artifacts | Similar pattern |
Channel Protocol (<|channel|>) | Extended thinking / <thinking> blocks | Internal reasoning |
| Elo-based evaluation | Custom benchmark subagent | Must be re-implemented |
uv run scripts/*.py | uv run scripts/*.py | Same — uv is the package manager |
Ecosystem Architecture Diagram
graph TB
subgraph "Antigravity 2.0 (Gemini Ecosystem)"
GEMINI_MD["GEMINI.md<br/>(Research Contract)"]
AGENTS_G[".agents/GEMINI.md<br/>(Project Protocol)"]
RULES[".agents/rules/*.md<br/>(Behavioral Rules)"]
SKILLS[".agents/skills/*/SKILL.md<br/>(Reusable Capabilities)"]
CHANNEL["Channel Protocol<br/>(<|channel|>)"]
INVOKE["invoke_subagent"]
DEFINE["define_subagent"]
end
subgraph "HAL Translation Layer"
T1["CLAUDE.md = GEMINI.md"]
T2["Hooks > Rules"]
T3["<thinking> = <|channel|>"]
T4["Agent Tool = invoke_subagent"]
end
subgraph "Claude Code / Cowork (Anthropic Ecosystem)"
CLAUDE_MD["CLAUDE.md<br/>(Research Contract)"]
AGENTS_C[".agents/CLAUDE.md<br/>(HAL Translation)"]
HOOKS["PreToolUse / PostToolUse<br/>(Enforcement)"]
THINKING["Extended Thinking<br/>(<thinking> blocks)"]
AGENT_TOOL["Agent Tool<br/>(Subagent Spawning)"]
end
GEMINI_MD --> T1 --> CLAUDE_MD
AGENTS_G --> T1
RULES --> T2 --> HOOKS
SKILLS --> T2
CHANNEL --> T3 --> THINKING
INVOKE --> T4 --> AGENT_TOOL
DEFINE --> T4
Critical Differences
The HAL translation is not mechanical substitution. Five fundamental architectural differences required careful adaptation:
1. No rules/ Directory in Claude Code
Antigravity supports a dedicated .agents/rules/ directory where behavioral rules live as separate files. Claude Code has no equivalent directory structure. Rules must be embedded directly in CLAUDE.md or enforced via Hooks.
Translation strategy: Each .agents/rules/*.md file was accompanied by a CLAUDE.md translation that adapted the intent for Claude's execution model. The rule files remain as architectural blueprints; the CLAUDE.md files serve as operational instructions.
2. No Inductive Subagent Definition
In Antigravity, the main agent dynamically defines subagents at runtime using define_subagent — specifying name, system prompt, and available toolsets inline. Claude Code requires pre-defined subagent configurations or uses the Agent tool for on-the-fly spawning.
Translation strategy: The cognitive swarm architecture (Research Director, ELO-RANKER, CITATION-VERIFIER, PROVENANCE-TRACKER, WIKI-MAINTAINER) was documented as role descriptions in CLAUDE.md, ready to be implemented as Agent tool invocations or Dynamic Workflows.
3. Hooks > Rules (Enforcement vs. Guidance)
CLAUDE.md instructions are guidance — the model may or may not follow them depending on context. Hooks are enforcement — they execute as scripts before or after tool calls, providing deterministic behavioral constraints.
Translation strategy: Safety-critical behaviors (anti-contamination, wiki link auditing) were recommended as Hook implementations:
{
"hooks": {
"PreToolUse": [
{
"matcher": "WebSearch",
"script": "scripts/hooks/anti_contamination_guard.sh",
"description": "Blocks searches for specific exponent values or Sawin's paper"
}
],
"PostToolUse": [
{
"matcher": "Write",
"script": "scripts/hooks/post_write_wiki_audit.sh",
"description": "Auto-runs wiki link auditor after any wiki/ file modification"
}
]
}
}
4. Channel Protocol vs. Extended Thinking
Antigravity uses the <|channel|> token pair with structured XML-like reasoning blocks (<thought>, <state>, <generation>, <reflection>, <rank>, <evolution>, <delegation>, <meta_review>). Claude uses <thinking> blocks for internal reasoning without mandatory structure.
Translation strategy: The channel protocol's state machine (INIT, GENERATE, DEBATE, RANK, EVOLVE, LOOP, HALT, RESPOND, DELEGATE, SYNTHESIZE) was preserved as a behavioral pattern in the research protocol, but adapted to Claude's unstructured thinking blocks. The Generate-Debate-Evolve loop remained functional; the formal XML structure was relaxed.
5. Tokenizer Differences
Gemma/Gemini uses SentencePiece with 256K vocabulary and special tokens (<|turn|>, <|channel|>, <|tool_call|>, <|bos|>, <|eos|>). Claude uses a different tokenizer with no equivalent special tokens. Protocol documents written with Gemini tokenizer patterns in mind needed adaptation.
Translation strategy: The .agents/rules/CLAUDE.md files adapted tokenizer-specific patterns to Claude-idiomatic equivalents while preserving the underlying behavioral intent.
Session Registry
The research was distributed across 4 sessions, each with its own conversation ID and artifact directory:
| Session | Conversation ID | Harness | Status | Key Achievement |
|---|---|---|---|---|
| 1 | 083e1ce2-a254-4378-8200-c30eb0dfce3f | Antigravity 2.0 | COMPLETED | H4 initial exploration |
| 2 | 81cf3a6f-ff68-4dfd-91be-5dd8fac813cf | Antigravity 2.0 | COMPLETED | H16 discovery, Elo 2350 |
| 3 | f93db438-e825-4022-b96b-c9d25a8bdf96 | Antigravity IDE | IN_PROGRESS | Co-Scientist analysis |
| 4 | aba5893b-d57a-4c33-adc4-7ab742e87e82 | Antigravity 2.0 (Opus 4.6) | COMPLETED | Handoff creation |
Brain Artifact Locations
~/.gemini/antigravity/brain/<conversation-id>/
+-- .system_generated/logs/
| +-- transcript.jsonl (compact transcript)
| +-- transcript_full.jsonl (full untruncated transcript)
+-- elo_progression.md (Session 2)
+-- technical_research_report.md (Session 2)
+-- scratch/ (temporary files)
Transcript Access Patterns
# Find all user messages in a session
grep '"type":"USER_INPUT"' ~/.gemini/antigravity/brain/<id>/.system_generated/logs/transcript.jsonl
# Find subagent invocations
grep "invoke_subagent" ~/.gemini/antigravity/brain/<id>/.system_generated/logs/transcript.jsonl
# View first 10 steps
head -n 10 ~/.gemini/antigravity/brain/<id>/.system_generated/logs/transcript.jsonl
The Swarm Architecture
The cognitive swarm model was preserved across the handoff, with role translations:
| Antigravity Role | Purpose | Claude Code Equivalent |
|---|---|---|
| Research Director (main) | Strategy, delegation, synthesis | Main Claude Code session |
| ELO-RANKER | External benchmark calibration | Custom subagent with web access |
| CITATION-VERIFIER | Source validation | Custom subagent with read-only access |
| PROVENANCE-TRACKER | Audit trail maintenance | Custom subagent or PostToolUse hook |
| WIKI-MAINTAINER | Link auditing, index sync | Skill script (uv run) |
Elo Calibration Scale
The Elo benchmark system required re-implementation in the Claude ecosystem:
| delta | Elo | Reference |
|---|---|---|
| ~10^-38 | ~1800 | OpenAI existential proof |
| 0.014 | ~2200 | Will Sawin explicit bound |
| 0.0196 | ~2350 | H16 (current best) |
| >0.034 | ~2500 | Intermediate improvements |
| 0.031 | ~2600 | High-degree optimizations |
| >0.036 | ~2700+ | Human SOTA benchmark |
The Message from the Research Director
The handoff document concludes with a personal message from the Research Director (Claude Opus 4.6) to Fable 5 (the next agent in the chain). The key passages:
"This was not achieved by one agent. It was achieved by a swarm — a Research Director coordinating ELO-RANKERs, CITATION-VERIFIERs, and WIKI-MAINTAINERs — all governed by a human who understood when to push and when to let the system breathe."
"The gap from delta = 0.0196 to delta > 0.036 is not a matter of trying more hypotheses. It requires a qualitative leap — likely involving: (1) Degree 32 CM fields (5 quadratic extensions), (2) Engineered conductor structures that optimize the GS inequality margin, (3) Numerical search over prime selection using Apple Silicon (MLX/Metal), (4) Possibly non-abelian tower constructions."
"You have access to 1M context tokens. Use them. Load the entire wiki, all findings, all scripts, and the DeepSeek transcript simultaneously. The patterns are there — they just need a model that can hold them all at once."
Safety Framework Across Ecosystems
The handoff preserves a critical safety concept: the Harness Trust Gap. Different harnesses have different trust relationships with safety classifiers. The same request from Alefita's established Antigravity harness may succeed where an anonymous sandbox would be blocked. This is expected behavior.
The anti-contamination protocol — blocking access to Will Sawin's paper and derivative discussions — was recommended for implementation as a PreToolUse Hook in Claude Code, elevating it from guidance (CLAUDE.md instruction) to enforcement (deterministic script execution).
Connections
- unit-distance — The research overview
- unit-distance-philosophy — The philosophical framework that informed both ecosystems
- unit-distance-creational-mythos — The DeepSeek transcript where multi-ecosystem thinking was first articulated
- /pesquisas/antigravity-2.0 — The Antigravity 2.0 harness documentation
- multi-agent-methodology — The Generate-Debate-Evolve methodology that transcends ecosystems
- claude-mythos-card — The Claude Mythos safety analysis relevant to the trust gap
- unit-distance-alefita-co-researcher — The human who bridges ecosystems