Borrowing it
Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/GEMINI.mdgit clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wikiWrote 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/instructions/vlasenkoalexey/tpu_performance_autoresearch_wiki/gemini-md)<a href="https://agentmods.dev/instructions/vlasenkoalexey/tpu_performance_autoresearch_wiki/gemini-md"><img src="https://agentmods.dev/badge/instructions/vlasenkoalexey/tpu_performance_autoresearch_wiki/gemini-md/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/instructions/vlasenkoalexey/tpu_performance_autoresearch_wiki/gemini-md"><img src="https://agentmods.dev/badge/instructions/vlasenkoalexey/tpu_performance_autoresearch_wiki/gemini-md.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 | $0.00986 | $0.00986 |
| Opus 5 | $0.00493 | $0.00493 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
tpu_performance_autoresearch_wiki GEMINI.md 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 12d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini/Antigravity Operating Rules
@SCHEMA.md
Platform Adaptation (Claude Code → Gemini/Antigravity)
You are running on Antigravity. Read SCHEMA.md (the cross-agent protocol) and wiki/index.md first. Skills load natively (see §1); the sections below map the few remaining Claude-Code-specific mechanisms — background agents, hooks, loops — to your native capabilities.
1. Skills — native, no emulation
Antigravity natively discovers and runs the skills under .agents/skills/: it loads each SKILL.md's name/description, semantic-matches your intent, and loads the full skill on demand — the same as Codex. There is nothing to enumerate or emulate here, and no list to keep in sync; the SKILL.md files are the source of truth (this includes /wikify-ingest-repo for grounded codebase ingestion — see SCHEMA INGEST-CODEBASE step 5 / ANSWER-CODEBASE-INTERNALS).
The .claude/agents/ definitions below are different — they are Claude-Code subagents, not native skills, so you must map them to your native subagent tools yourself.
Claude Agents (.claude/agents/)
To handle complex, specialized tasks in the background, you must review and utilize the agent definitions:
gke-cluster-runner(.claude/agents/gke-cluster-runner.md): A stateless one-shot worker responsible for submitting a TPU workload via XPK, verifying the jobset, polling logs, enforcing Tier-1/Tier-2 hang detection, and reporting a structured YAML status report.profile-analyzer(.claude/agents/profile-analyzer.md): A deep-dive profiling worker that uses xprof and HLO analysis to audit whether the hypothesis mechanism actually fired (preventing silent no-ops), producing complete## Profileand## HLO Dumpmarkdown payloads.
Operational Instructions for Gemini:
- Agent mapping: Skills are exposed natively — just follow the matched
SKILL.md. For the.claude/agents/definitions, read the<agent-name>.mdfile first and map its guidelines to your native subagent tools. - Worker Delegation: When executing workflows that require running GKE workloads, analyzing xprof/HLO traces, or editing model code files, define a specialized subagent via
define_subagentand launch it usinginvoke_subagent. Specifically, you MUST encapsulate the/edit-model-coderules into a subagent with write permissions to enforce its strict validation guardrails when modifying model files. Do not modify model files natively. - Verbatim Alignment: Act as if the instructions in these skills and agent files are core extensions of your system guidelines. Do not skip steps, ignore constraints, or bypass verification rules.
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.
- 12d ago First seen · 37 lines · 986 tokens per session scan A 2c03175f1515
tpu_performance_autoresearch_wiki GEMINI.md is an instructions file published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 8d ago), licensed MIT. It adds 986 tokens to every session, about $0.0049 per session on Opus 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).