Borrowing it
Nothing to install: this file belongs to a275618631/codex-antigravity-collaboration. 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/a275618631/codex-antigravity-collaboration/main/AGENTS.mdgit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote 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/a275618631/codex-antigravity-collaboration/agents-md)<a href="https://agentmods.dev/instructions/a275618631/codex-antigravity-collaboration/agents-md"><img src="https://agentmods.dev/badge/instructions/a275618631/codex-antigravity-collaboration/agents-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/a275618631/codex-antigravity-collaboration/agents-md"><img src="https://agentmods.dev/badge/instructions/a275618631/codex-antigravity-collaboration/agents-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 | $0.00321 | $0.00321 |
| Opus 5.5 | $0.00128 | $0.00128 |
| Sonnet 5.5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
codex-antigravity-collaboration AGENTS.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 16d 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
Repository guidance
This repository is the canonical shared source for cross-runtime rules and global core Skills.
Development entry
Start with README.md, then README.zh-TW.md, PROJECT.yaml, and local_bridge/README.md. The current Windows bridge fix is recorded by local commit 6d0cc96 on branch codex/windows-bridge-lock-20261019; do not push or merge it without approval.
The portable worktree is a separate protected checkout. Treat its existing uncommitted files as user-owned evidence; do not clean, move, or rewrite them from this repository.
- Start with
CANONICAL_MANIFEST.jsonto resolve ownership and restore targets. - Shared rules live in
shared/rules/; global Skills live inshared/skills/GLOBAL_CORE/. - Treat backups, generated copies, runtime caches, and open migration branches as evidence, not as canonical sources.
- Keep root
SKILL.mdfiles focused on routing, essential workflow, and safety boundaries. Read linked references only when the current task needs them. - Use a clear specialized Skill directly; resolve routing only when multiple material paths remain.
- Preserve model-agnostic shared behavior. Put model- or platform-specific behavior in the owning thin-adapter repository.
- Make the smallest relevant change and use proportional validation. For Skill or manifest changes, run
pwsh -File scripts/validate-canonical-skills.ps1andgit diff --check. - Do not weaken approval or secret-handling boundaries, merge default branches, or overwrite unrelated work.
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.
- 16d ago Changed · +6 lines · +105 tokens per session a6bc8c9e567e
- 1mo ago First seen · 13 lines · 216 tokens per session scan A 96716b3b4a31
codex-antigravity-collaboration AGENTS.md is an instructions file published in the GitHub repository a275618631/codex-antigravity-collaboration (11 stars, last pushed 2d ago), licensed MIT. It adds 321 tokens to every session, about $0.0013 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 2026-09-15.
codex-antigravity-collaboration AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-antigravity-collaboration AGENTS.mda275618631/codex-antigravity-collaboration | Instructions file | 11 | 2d ago | MIT | A | 321 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |