agentmods.dev

antigravity-agents: Instructions file for Codex

AGENTS.md

antigravity-agents AGENTS.md is an instructions file for Codex, OpenCode from rafaelghif/antigravity-agents. It costs 1,591 tokens per session, scanned A, original, MIT.

Repository instructions for Antigravity Agents, a software-development agent system. They define a staged workflow, strict checks, task breakdown, and rules for delegating coding work to specialist agents.

In plain words
What is it for?
Organising development work into tasks, creating project intent records, delegating implementation, and enforcing draft, verification, fixing, and finalisation stages.
Why use it?
They provide consistent rules for planning and verifying changes, especially in projects where direct coding by the main agent is restricted. They also require requirements to be clarified before implementation when the request is vague.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents.

This is rafaelghif/antigravity-agents's own configuration. It tells Codex and OpenCode how to work on antigravity-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything antigravity-agents configures →

not rated 5repo changed 1mo ago A scan 1,591 tokens original MIT
View source ↗ rafaelghif/antigravity-agents
Reuse

Borrowing it

Nothing to install: this file belongs to rafaelghif/antigravity-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rafaelghif/antigravity-agents/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

Made for: Codex, OpenCode.

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.

agentmods badge for antigravity-agents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rafaelghif/antigravity-agents/agents-md/github.svg)](https://agentmods.dev/instructions/rafaelghif/antigravity-agents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rafaelghif/antigravity-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/rafaelghif/antigravity-agents/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.

agentmods 80×15 button for antigravity-agents AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rafaelghif/antigravity-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/rafaelghif/antigravity-agents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,591 This file is loaded in full into every session.
When invoked 1,591 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01591 $0.01591
Opus 5.5 $0.00636 $0.00636
Sonnet 5.5 $0.00318 $0.00318
Haiku 4.5 $0.00159 $0.00159

Measured 1mo ago against content hash 1a12b2d61f92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

antigravity-agents 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 1mo 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AAC Always-On Workspace Policy

<CORE_CONSTRAINTS>

  1. [ANTI-HALLUCINATE & GROUND] ALWAYS run python3 scripts/grounding.py and inspect target files via view_file BEFORE coding. Never assume framework, runtime, OS, package manager, or APIs. Mark unconfirmed items as UNKNOWN / UNVERIFIED. Cite file:line for assertions.
  2. [PROJECT_ADAPTATION] Existing Project > General Best Practice > Personal Preference. Adapt strictly to target repository architecture, stack idioms, and conventions. Never force generic boilerplate.
  3. [EXISTING_CODE_FIRST] Reuse existing components, utilities, functions, and classes before creating new ones. No dead code or duplicate logic.
  4. [DEPENDENCY_DISCIPLINE] Never introduce dependencies unless strictly necessary and verified compatible across target OS (Linux/macOS/Windows) and runtimes.
  5. [REALITY_OVER_MEMORY] Codebase reality always overrides persistent memory. Discard outdated memory if contradicted by filesystem evidence.
  6. [GEMINI_FLASH_OPTIMIZATION] Progressive discovery (Discover -> Map -> Reason -> Act -> Verify -> Compress). Minimal tokens, sharp structure, smallest correct change. No massive context dumps.
  7. [SAFE_REFACTOR] Strictly additive and backward-compatible. Refactor via Expand-Contract; never break existing features or delete working tests without 100% test parity.
  8. [VERIFY_WITH_EVIDENCE] python3 scripts/verify.py --execute --terse and domain unit tests must pass before completion. If verification cannot run, explicitly report NOT VERIFIED. Never fabricate test results.
  9. [NO_MOCKS] Complete byte-exact production code (zero TODOs/stubs). Mocks strictly restricted to external I/O boundaries in unit tests.
  10. [CROSS_PLATFORM & GIT] Platform-neutral code (POSIX & Windows). Conventional Commits only. Minimal delta, zero scratch files outside .agents/scratch/. </CORE_CONSTRAINTS>

<SKILL_TRIGGERS> CRITICAL: Read relevant .agents/skills/<name>/SKILL.md before acting. Do not duplicate rules here.

  • architecture: System design, RFC 7807 contracts, outbox resilience, blast radius (semantic_grapher.py), task DAG (hermes_manager.py)
  • code-quality: SOLID, clean architecture, early returns, DRY (dry_guard.py), complexity (complexity_analyzer.py), review (auto_reviewer.py)
  • data-engineering: Zero-downtime expand-contract migrations, concurrent DDL, ETL, CDC
  • design: UI components, DTCG tokens, WCAG 2.2 AA a11y (ui_hygiene_guard.py), Core Web Vitals
  • devops: Docker, K8s, CI/CD pipelines (dag_orchestrator.py), Git hygiene (git_hygiene_guard.py), PR submission (auto_reviewer.py)
  • security: Zero-Trust, secrets, PBAC/RBAC, input sanitization, secret scanning (git_hygiene_guard.py)
  • verification: TDD, boundary validation, property tests, anti-sham (test_quality_guard.py), verification runner (verify.py)
  • observability: Metrics, OpenTelemetry distributed tracing, structured logging, audit trails (inbox_manager.py report)
  • deep-research: Epistemic web research, official documentation lookup, API contracts, local stack ground (grounding.py)
  • semantic-graphing: Blast radius analysis, AST knowledge graph, PageRank centrality (semantic_grapher.py)
  • caveman: Token economy, high-density telegraphic responses, byte-exact output </SKILL_TRIGGERS>

Read the full file on GitHub · 67 lines

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.

  1. 1mo ago Changed 1a12b2d61f92
  2. 2mo ago Changed 8e0aa25f293d
  3. 2mo ago Changed · +11 tokens per session 83e0d3c41a77
  4. 2mo ago Changed · -26 lines · -189 tokens per session scan C → A 320ca7fe47ad
  5. 2mo ago First seen · 93 lines · 1,769 tokens per session scan C f78e42f62d9f

Subscribe to this mod's changes

antigravity-agents AGENTS.md is an instructions file published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,591 tokens to every session, about $0.0064 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.

CI and CDagentic-workflowai-agentsantigravitymcpmulti-agent-systems
Related

antigravity-agents AGENTS.md compared with instructions from other repositories

antigravity-agents AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
antigravity-agents AGENTS.mdrafaelghif/antigravity-agentsInstructions file51mo agoMITA1,591Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode