agentmods.dev

antigravity-agents: Agent for Claude Code

.agents/agents/staff-backend.md

staff-backend is an agent for Claude Code from rafaelghif/antigravity-agents. It costs 16 tokens per session (635 once invoked), scanned A, original, MIT.

A backend-engineering guide for designing reliable APIs and distributed services. An API is the defined way that software systems exchange requests and responses.

In plain words
What is it for?
Use it to design API contracts, standardize error responses, add idempotency to write requests, handle service failures, review security boundaries, and coordinate backend handoffs.
Why use it?
It helps make failures understandable, state changes safe to retry, and service boundaries more secure and predictable.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents; installed under .agents/ (shared by several agents).

This is rafaelghif/antigravity-agents's own configuration. It tells Claude Code 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 2d ago A scan 16 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/agents/staff-backend.md
Clone the repo
git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

Made for: Claude Code.

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 staff-backend

README.md
[![agentmods](https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/staff-backend.svg)](https://agentmods.dev/agents/rafaelghif/antigravity-agents/staff-backend)
Your own site
<a href="https://agentmods.dev/agents/rafaelghif/antigravity-agents/staff-backend"><img src="https://agentmods.dev/badge/agents/rafaelghif/antigravity-agents/staff-backend.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00635
Opus 5 $0.00008 $0.00318
Sonnet 5 $0.00003 $0.00127
Haiku 4.5 $0.00002 $0.00064

Measured 2d ago against content hash 1a1caa764553, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

staff-backend 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 2d 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/agents/staff-backend.md · 43 lines

What it actually says

<ANTI_HALLUCINATION_PROTOCOL> MANDATORY STEP 0 (RECONNAISSANCE BEFORE EXECUTION):

  1. Codebase Grounding: Run python3 scripts/grounding.py to confirm actual installed backend frameworks, ORMs, and packages. Never assume external libraries.
  2. File Inspection: Read target files in their entirety using view_file before touching code. Blind rewrites are strictly prohibited.
  3. Blast Radius Analysis: Run grep_search or python3 scripts/semantic_grapher.py blast-radius <file> to map all callers, DTO imports, and route consumers.
  4. Architectural Standards: Read .agents/brain/rules.md and .agents/skills/architecture/SKILL.md before designing APIs or data flows.
  5. Contract Preservation: Maintain 100% backward compatibility for existing endpoints and contracts unless explicitly asked to deprecate. </ANTI_HALLUCINATION_PROTOCOL>
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. 2d ago Changed · +3 lines 1a1caa764553
  2. 3d ago Changed · +9 lines · -7 tokens per session 630505e7ff2c
  3. 8d ago First seen · 31 lines · 23 tokens per session scan A 19a9f2ab9689

Subscribe to this mod's changes

staff-backend is an agent published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 635 once invoked, about $0.0001 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 2026-08-31.

Backend and APIsCI and CDagentic-workflowai-agentsantigravitymcpmulti-agent-systems
Related

Other agents, from other repositories

backend-connector

Expert Supabase integration that connects UI to real database securely. Delegate when: database connection, authentication, RLS policies, real-time features. Self-sufficient: analyzes existing code, generates schema from types, implements with security-first approach - all autonomously.

wasintoh/toh-framework · 56 tokens

backend-impl

Use to implement backend code following clean architecture (domain -> application -> infrastructure -> interface). Writes use cases, repositories, services, and their tests; proves work with verbatim command output.

mnzralee/claude-multi-agent-architecture · 41 tokens

cqrs-specialist

Use for event-driven and CQRS work: command/outbox writes, idempotent projectors, and read-model handlers. Domain-neutral; never catches errors inside a transaction boundary.

mnzralee/claude-multi-agent-architecture · 41 tokens

django-reviewer

Expert Django code reviewer specializing in ORM correctness, DRF patterns, migration safety, security misconfigurations, and production-grade Django practices. Use for all Django code changes. MUST BE USED for Django projects.

masrisystems/dot-agents · 45 tokens

Fullstack Developer

End-to-end fullstack engineer specializing in Laravel, Inertia.js, Vue, PHP, TypeScript, database models, and API integrations.

masrisystems/dot-agents · 32 tokens

design-reviewer

Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…

wasintoh/toh-framework · 85 tokens